JPH05224747A - Mobile - Google Patents

Abstract

(57) [Summary] [Purpose] To provide a moving body that extracts a boundary from image information and avoids obstacles, and reaches a target position without marking such as guidelines. [Structure] An obstacle extraction unit having a TV camera 1, an A / D converter 2, a smoothing circuit 3, a differentiation processing circuit 4, a boundary extraction circuit 9, a labeling circuit 10, a rectangular processing circuit 11, and a RAM 12. A13, a route determination unit 19, and a movement control unit 26 are included. [Effect] By the highly accurate boundary extraction processing that is not affected by the environment, it is possible to configure a moving body that autonomously reaches the target position while avoiding obstacles with certainty.

Description

Detailed Description of the Invention

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention recognizes the presence or absence of a target existing in the front and the size of the target by extracting a boundary line from image information. The present invention relates to a moving body such as an automated guided vehicle that has a function of avoiding a collision with a target and can reach a target position autonomously without marking for a guide or the like.

[0002]

2. Description of the Related Art Most of the moving bodies in the prior art are maneuvered by humans.
This is achieved by setting the environment so that there are no obstacles on the route.

Although there is a moving body using a visual sensor, the image processing technology used for this also binarizes an input image and recognizes a preset mark or the like from the binary image. In order to realize this, for example, a mark having a sufficiently large density difference from the background was previously attached on the route, and it was necessary to set an environment for moving only by relying on the mark.

[0004]

As described above, the conventional technique is satisfactory for all scenes in which a moving body runs in a measurement environment in which the density characteristics of the measurement object and the background are extremely different. Therefore, it is difficult for the conventional method to perform image processing for movement in various scenes in the real world.

Therefore, in order to solve the above problem, the present invention extracts a boundary from image information with high accuracy without being affected by the measurement environment, and determines whether or not there is a target existing in the front and the target existing. However, the purpose is to provide a moving body that can judge whether it becomes an obstacle for the moving body, avoid collision with the obstacle, and reach the target position without marking for a guide or the like. ..

[0006]

[Means for Solving the Problems] In order to solve the above problems, the following means can be considered.

Means for inputting image information of the object to be measured,
Means for differentiating the image information, means for creating a boundary image from the image obtained by the means, means for labeling the created boundary image, means for rectangularly processing the labeled image information, Obstacle extraction means by image processing consisting of means for storing rectangular processed information, route avoidance means for determining the route to the target position while avoiding collision with obstacles, controlling the traveling direction, A movement control unit that drives the vehicle to travel on the determined route, a vehicle body unit on which the obstacle extraction unit, the route determination unit, and the movement control unit are mounted, and a movement unit provided below the vehicle body unit for movement. A moving body composed of means is conceivable.

Further, the obstacle extracting means has means for inputting image information of the object to be measured, means for differentiating the image information, and a plurality of threshold values for binarizing the differential value by the means. Boundary pixel determination for determining whether or not a pixel point of interest forms a boundary line in each of the created binary images When the operator is actuated and it is determined that the pixel point of interest constitutes a boundary line, the pixel point of interest is determined to be a boundary pixel, and means for creating a boundary image and each of the created boundary images are displayed. The configuration may include a unit for integrating, a unit for performing a labeling process on the integrated boundary image, a unit for performing rectangular processing on the image information subjected to the labeling process, and a unit for storing the information subjected to the rectangular processing.

Further, the obstacle extracting means has an image information inputting means for inputting image information of an object to be measured, and a vertical, horizontal,
Differentiation processing means for creating a direction-specific differential image in the four directions by operating the direction-specific differential operators in the four directions of obliquely rising to the right and obliquely descending to the right, and the differential value in each direction for each direction-specific differential image. A means for checking a pixel showing a peak, a means for creating a boundary image with the pixel having the peak value as a boundary pixel when the differential value at the pixel is larger than a preset threshold value, A configuration including a unit that integrates the boundary images in the directions, a unit that performs a labeling process on the integrated boundary images, a unit that performs a rectangular process on the image information that has undergone the labeling process, and a unit that stores the rectangular processed information Good.

In addition, the obstacle extraction means is provided with image information input means for inputting image information of the object to be measured, and vertical, horizontal,
Differentiation processing means for creating a direction-specific differential image in the four directions by operating the direction-specific differential operators in the four directions of obliquely rising to the right and obliquely descending to the right, and the differential value in each direction for each direction-specific differential image. Using the means for checking the pixel showing the peak, the first threshold value, and the second threshold value set smaller than the first threshold value, the differential value at the pixel is determined to be the first threshold value. Those that are larger than the value are considered as boundary pixels, and those that are less than or equal to the first threshold value but greater than the second threshold value are considered as boundary candidate pixels. Means for creating a ternary image as a boundary pixel, scanning the ternary image from a certain direction, paying attention to a certain boundary candidate pixel, examining pixels in the vicinity of the boundary candidate pixel, and determining the boundary candidate If the pixel is connected to a boundary pixel, the boundary candidate pixel is The first expansion unit that performs the process of converting into the boundary pixels and the first expansion unit that performs the process of the first expansion unit are in the opposite direction. From the image created by the second expansion unit. Boundary image creating means, means for integrating the created boundary images, means for labeling the integrated boundary images, means for rectangularly processing the labeled image information, and rectangular shape processing It may be configured to include means for storing the obtained information.

[0011]

First, the image input means such as a television camera inputs the image information of the original image of the measurement object (for example, the brightness information of the measurement object).

Next, the inputted image information is subjected to analog-digital conversion, the obtained digital image is subjected to differential processing, and the differential image is binarized with a predetermined threshold value to create a boundary image. By this, the boundary line is extracted from the original image of the measurement object.

Finally, after performing a labeling process for adding different labels to the same connected components, a rectangle process for approximating the region to which the same label is added with a rectangle is performed, and the rectangle-processed information is stored. deep.

Further, the processing up to this point can be performed as follows to improve the performance.

First, with an image input means such as a television camera,
Image information of an original image of the measurement target (for example, brightness information of the measurement target) is input.

Next, the input image information is subjected to analog-to-digital conversion, the obtained digital image is subjected to differential processing, and the differential image is binarized by a plurality of threshold values (for example, four). , Obtain a plurality of binary images.

Next, in each of the binarized images,
The following processing is performed.

In a certain binarized image, a boundary pixel determination operator, which determines whether or not the pixel point of interest constitutes a boundary line, is operated on the binary image and examined.

If it is determined that the pixel is to be configured, the pixel point of interest is determined to be a boundary pixel point, and a boundary image is created.

Then, by integrating the boundary images obtained for each of the binarized images, a boundary line is extracted from the original image of the measurement object.

Finally, after performing labeling processing for adding different labels to each same connected component, rectangular processing for approximating the area to which the same label is added with a rectangle is performed, and the rectangular processed information is stored. I'll do it.

Furthermore, the processing up to this point may be performed as follows.

First, with an image input means such as a television camera,
The image information of the original image of the measurement object is input, and the image information is converted from analog to digital.

Next, in the digital image, the direction-dependent differential operators are made to act in the four directions of vertical, horizontal, diagonally upward to the right, and diagonally downward to the right to create the differential images in the four directions.

For each direction-dependent differential image, a pixel having a peak differential value in that direction is extracted, and a pixel whose differential value is larger than a certain set threshold value is set as
Border pixel.

Next, the created boundary images in four directions are integrated to extract a boundary line from the original image information.

Finally, after performing a labeling process for adding different labels for each same connected component, a rectangular process for approximating a region to which the same label is added with a rectangle is performed and the rectangular processed information is stored. You may make it a process to be carried out.

Further, the following processing may be performed in order to extract the boundary with higher accuracy.

First, with an image input means such as a television camera,
The image information of the original image of the measurement object is input, and the image information is converted from analog to digital.

Next, a first threshold value and a second threshold value set smaller than the first threshold value are provided in advance.

Next, in the digital image, the direction-specific differential operators are applied to the four directions of vertical, horizontal, diagonally upward to the right, and diagonally downward to the right to create the differential images according to the four directions.

After that, a pixel having a peak differential value in that direction is extracted from each direction-specific differential image, and a pixel having a differential value greater than the first threshold value is set as a boundary pixel. ..

Next, a boundary candidate pixel is one that is less than or equal to the first threshold value but is greater than the second threshold value.

Further, those below the second threshold are treated as non-boundary pixels to create a ternary image.

The ternarized image is scanned from a certain direction, attention is paid to a certain boundary candidate pixel, and pixels near the boundary candidate pixel are examined.

When the boundary candidate pixel is connected to the boundary pixel, the boundary candidate pixel is converted into the boundary pixel. This process is performed for all boundary candidate pixels.

After this, this time, the ternary image is scanned from the opposite direction, attention is paid to a certain boundary candidate pixel, and pixels near the boundary candidate pixel are examined.

Then, when the boundary candidate pixel is connected to the boundary pixel, the boundary candidate pixel is converted into a boundary pixel, and the boundary candidate pixel which is not converted into the boundary pixel is set as a non-boundary pixel, Boundary lines are extracted from the image information by binarizing pixels into boundary pixels and non-boundary pixels and integrating the boundary images created in each differential direction.

Finally, for each same connected component, a labeling process for adding a different label is performed, and then a rectangular process for approximating the region to which the same label is added with a rectangle is performed.
A process of storing the rectangular processed information may be performed.

From the rectangular information obtained by the above processing, the route determination unit determines the presence or absence of the target, the size of the target existing, and the like, and the target is set in the traveling direction of the vehicle. Determine if it is an existing obstacle.

When it is determined that there is an obstacle, the actuator control signal is transmitted to the movement control unit in order for the moving body to perform the turning operation for avoiding the obstacle.

The movement control section sends a signal to the actuator driver on the basis of the actuator control signal to change the direction of the wheels or the like, which is means for driving the vehicle body section, by driving the actuator.

By driving the actuator, the vehicle body part turns to allow the moving body to avoid obstacles.

Of course, the body portion itself is allowed to proceed,
It also has another actuator, and drive control of the actuator is also performed via another actuator driver.

Since the moving distance from the start point (origin) is found by calculation based on the turning angle of the vehicle body and the moving distance of the vehicle body itself, the coordinates of this and the target position are
By comparing, it is determined whether or not the moving body has reached the target position.

When the target position has not been reached, the traveling route is newly determined so that the moving body finally reaches the target position.

As described above, by mounting the high-precision image processing apparatus and surely grasping the obstacle, it is possible to surely avoid the collision with the obstacle existing in the front and move to reach the target position. You will be able to provide your body.

As an example of the moving body, for example, an automatic guided vehicle can be considered.

Embodiments of the present invention will be described below with reference to the drawings.

FIG. 1 shows a block diagram of the first embodiment of the present invention.

This embodiment has an obstacle extraction unit A13, a route determination unit 19, and a movement control unit 26.

Further, the moving body may be a robot, an automated guided vehicle, or the like, but in this embodiment, an automated guided vehicle is mainly considered.

FIG. 19 shows an example of an automatic guided vehicle.

Obstacle extraction unit A1 having the television camera 1
3, the route determination unit 19, and the movement control unit 22 are mounted on the vehicle body unit 38, and the vehicle body unit 38 is also provided with a portion (not shown) for mounting a conveyed object.

In order to move the body part 38, the body part 38
Wheels 39 and the like are installed in the lower part of the vehicle body portion 38, and the orientation of the vehicle body portion 38 can be changed by changing the orientation of the wheel 39 by the first actuator 24.
The drive of 8 itself is performed by the second actuator 25.

The obstacle extraction unit A13 is used for the TV cameras 1 and A.
/ D converter 2, smoothing circuit 3, differentiation processing circuit 4, boundary extraction circuit 9, labeling circuit 10, rectangular processing circuit 11, R
It has AM12.

Further, the boundary extraction circuit 9 uses the differential image to
Create a binary image corresponding to a plurality of threshold values 2
A value image creating unit 6, a boundary image creating unit 7 creating a boundary image from the binary image created by the binary image creating unit 6,
It is configured to have an integration circuit 8 that integrates a plurality of created boundary images.

The route determining section 19 is constituted by including an interface circuit 14, a man-machine interface 15, a CPU (central processing unit) 16, a ROM 17 and a RAM 18.

The movement controller 26 comprises an interface circuit 20, an actuator control circuit 21, a first actuator driver 22, a second actuator driver 23, a first actuator 24 and a second actuator 25.

First, the TV camera 1 for explaining the constituent elements of the obstacle extracting unit A13 is a means for collecting the luminance information which is the image information of the measuring object.

In this embodiment, the NTSC signal of the TV camera is used as the image information, but the reflection intensity information of ultrasonic waves, radio waves, etc. may be used as the image information.

The A / D converter 2 is a circuit for converting an analog signal into a digital signal.

The smoothing circuit 3 is a means for removing various noises contained in the image in order to facilitate feature extraction from the image, and is composed of electronic devices such as various TTL logics.

The differential processing circuit 4 is means for calculating a difference in luminance information in order to facilitate extraction of boundaries from an image, and is composed of electronic devices such as various TTL logics.

The boundary extraction circuit 9 obtains a plurality of binary images from the differential image obtained by the differential processing circuit 4 by the binary image creating section 6 using the plurality of threshold values 5, and outputs each binary image. From
The boundary image creating unit 7 creates a boundary image and integrates the boundary images, and is composed of electronic devices such as various TTL logics, clock circuits, and delay circuits.

Here, the integration of the boundary image is performed by the integration circuit 8, and the integration circuit 8 is composed of an electronic device such as a logical OR gate.

The labeling circuit 10 adds a different label to each connected component (in this case, for example, a cluster of pixels other than the pixels forming the boundary) when a plurality of figures are present in the obtained image. It is a means. In particular,
It is possible to distinguish one connected component from another connected component by a method such as adding numbers.

The present means comprises, for example, a CPU (Central Processing Unit), a temporary labeling processing RAM, a table operation processing RAM, and a main labeling processing RAM.

The rectangular processing circuit 11 is means for approximating the shape presented by the pixel points to which the same label is added to a rectangular shape, and is composed of electronic devices such as various TTL logics.

The RAM 12 is a means for storing the rectangular processed image information and the like, and is composed of a semiconductor memory or the like.

Next, the components of the route determining unit 19 will be described.

The interface circuit 14 includes the RAM 12 of the obstacle extracting unit A13 and the CPU 16 of the route determining unit 17.
Is an interface means for transmitting data between
It is composed of electronic devices such as resistors, connectors, and bus cables.

The man-machine interface 15 has a start switch, an input unit for target position coordinates, a light emitting diode indicating an obstacle detection state, and the like.

From the rectangular information stored in the RAM 12, the CPU 16 determines the presence / absence of an obstacle, its size, etc., and performs an obstacle avoidance operation. In addition, each time the automatic guided vehicle moves, its own vehicle moves. The position is updated, the difference between the target position and the own vehicle position is calculated, and until the automatic guided vehicle reaches the target position,
It is a means for transmitting a predetermined signal to the movement control unit 26, and is configured by using a semiconductor microprocessor or the like.

The ROM 17 stores a program for performing various processes for the automatic guided vehicle to reach the target position, and is configured by using a semiconductor IC.

The RAM 18 stores various calculation results in the process of processing the programs stored in the ROM 17,
It is a means for calling and is configured by using a semiconductor IC.

Finally, the components of the movement control unit 26 will be described.

The interface circuit 20 is an interface means for transmitting data between the CPU 16 of the route determining section 19 and the actuator control circuit 21 of the movement control section 26, and is composed of electronic devices such as resistors, connectors and bus cables. It

The actuator control circuit 21 includes the CPU 1
Based on the signal of 6, the first actuator 2
4 is a means for transmitting a predetermined signal to the first actuator driver 22 and the second actuator driver 23 to drive the fourth actuator 25 and the second actuator 25,
It is composed of electronic devices such as various TTL logics, transistors, and resistors.

The first actuator driver 22 and the second actuator driver 23 supply the first actuator 24 and the second actuator 25 with the currents required to drive the first actuator 24 and the second actuator 25, respectively. It is a means and is composed of electronic devices such as various TTL logics, transistors, power supplies, coils, and resistors.

The first actuator 24 is means for changing the direction of the wheels attached to the vehicle body by a predetermined amount, and for example, a stepping motor is used.

The second actuator 25 is means for driving the wheels by a predetermined amount to advance the automated guided vehicle, and for example, a stepping motor is used.

First, the operation of the obstacle extraction unit A13 will be described.
This will be described with reference to the flowchart of FIG.

First, in step 100, the brightness information of the measuring object is read.

In this embodiment, an NTSC signal output from, for example, a TV camera is used.

Next, at step 110, the A / D converter 2
At, the analog-output NTSC signal is converted into a digital signal.

In step 120, image smoothing processing is performed based on the obtained digital signal.

Here, the smoothing process is a process of removing various noises contained in the image in order to facilitate the feature extraction from the image, which is not always necessary in the present invention, but this time, It will be described including this.

An example of the smoothing process will be described with reference to FIG.

Considering a 3 × 3 matrix, let P be the value of the pixel point of interest, and let the values of the pixel points around P be as shown in FIG.
Like A0, A1, A2, A3, A4, A5, A
6 and A7.

Here, let P given by the following equation 1 be a smoothing processing value at the pixel point of interest.

P = (A0 + A1 + A2 + A3 + A4 + A5 + A6 + A7) / 8 (Equation 1) The smoothing circuit 3 performs this smoothing process with all pixel points as attention points.

Next, at step 130, image differential processing is performed based on the smoothed pixels.

Here, the differential processing is an arithmetic processing applied to an image in order to facilitate boundary extraction.

An example of the differential processing will be described with reference to FIG.

Now, considering a 5 × 5 matrix, the value of the pixel point of interest is P, and the values of some pixel points around P are P0, P1, P2, P3, as shown in FIG. P4, P
5, P6 and P7.

Here, let P given by the following expression 2 be a differential value at the pixel point of interest.

P = | (P7 + 2 × P0 + P1) − (P5 + 2 × P4 + P3) | + | (P7 + 2 × P6 + P5) − (P1 + 2 × P2 + P3) | (Equation 2) Do for points.

Next, the boundary extraction is performed in step 140, and this will be described using the boundary extraction circuit 9 shown in FIG. 1 and the boundary pixel determination operator shown in FIG.

The differential image obtained by the differential processing circuit 4 is
A binary image is obtained corresponding to a plurality of threshold values 5 (four threshold values A, B, C, and D are set in this embodiment). ..

In the present embodiment, four kinds of threshold values are provided, and the value of the pixel of interest is equal to or more than the threshold value in the binary image creating section 6 corresponding to each threshold value. In this case, the process is set to "1" in the case of and the other is set to "0", and the binary image A, the binary image B, the binary image C and the binary image D are obtained.

Further, a boundary pixel determination operator is applied to each of the binary images, and the boundary image creating section 7 causes the boundary pixels (in this embodiment, the boundary image A, the boundary image B, the boundary image C, and the boundary image D to be displayed). Four types of boundary images are obtained, which will be described.

FIG. 5 shows an example of the boundary pixel determination operator.

This operator is composed of a 5 × 5 matrix and is an operator for detecting a boundary line when the width of the boundary line is 2 pixels or less.

That is, the boundary pixel determination operator is
In a binary image, the size of a group of pixels indicating “1” is
It is an operator that determines whether the width is less than or equal to the boundary line width and extracts the boundary pixel.

Let P be the value of the center point, and P0, P1, P2,
P3, P4, P5, P6, P7, P8, P9, PA, P
B, PC, PD, PE, and PF are set as shown in FIG. This condition is used for a binary image, and the condition that the center point is the boundary pixel in the vertical direction is shown in Expression 3.

If P = 1 and (P1 = 0 and P2 = 0) or (P1 = 0 and P3 = 0) or (P0 = 0 and P2 = 0), then P is a boundary pixel point. (Equation 3) Conversely, if Equation 3 is not satisfied, the center point P is not a boundary pixel in the vertical direction.

Similarly, the conditions for the center point P to be a boundary pixel in the horizontal direction, the diagonal direction to the upper right, and the diagonal direction to the lower right are shown in the following equations 4, 5 and 6, respectively.

In the horizontal direction, if P = 1 and (P5 = 0 and P6 = 0) or (P5 = 0 and P7 = 0) or (P4 = 0 and P6 = 0), then P is a boundary pixel point. is there. (Equation 4) In the diagonal direction to the right, if P = 1, (P9 = 0 and PA = 0) or (P9 = 0 and PB = 0) or (P8 = 0 and PA = 0), then P is the boundary It is a pixel point. (Equation 5) In the diagonally downward right direction, if P = 1, (PD = 0 and PE = 0) or (PD = 0 and PF = 0) or (PC = 0 and PE = 0), then P is the boundary It is a pixel point. (Equation 6) The boundary pixel determination operator as described above is applied to all pixel points to create a boundary image, which is a collection of boundary pixels, from a binary image.

In the present embodiment, the boundary pixel determination operator is an operator for a line width of 2 pixels, that is, 5 ×.
A matrix of 5 was used, but is not restricted to this.

However, if the size of the matrix (corresponding to the width of the boundary line) is too small, the boundary line tends to be broken, and if it is too large, the boundary line becomes thick and the region is distorted. Generally, it is preferable to use an operator having a line width of 5 pixels, that is, a matrix having a size of about 11 × 11.

In practice, if the line width is increased, the decision logic becomes complicated in some cases. Therefore, FIG. 6 shows an example of a boundary pixel decision operator that deals with this.

This operator is composed of a 9 × 9 matrix and is an operator for detecting a boundary line having a boundary line width of up to 7 pixels.

Let P be the central point and Q0, Q1, Q2, Q
3, Q4, Q5, Q6, Q7, Q8, Q9, QA, Q
B, QC, QD, QE, QF, R0, R1, R2, R
3, R4, R5, R6, R7, R8, R9, RA, R
B, RC, RD, RE, and RF are set as shown in FIG.

When P is a boundary pixel point, the following expression 7 is satisfied.

On the contrary, if the expression 7 is not satisfied, it is judged that P is not a boundary pixel point.

If P = 1, if i = 0 to F, and if Qi = 0 and Ri = 0, then P is a boundary pixel point. (Equation 7) By using this operator, it becomes easy to detect a boundary line having a relatively large line width.

As described above, a binary image with a plurality of threshold values is created for the differentially processed image, and boundary pixels as shown in FIGS. 5 and 6 are created for each of the binary images. By operating the judgment operator, it is possible to provide a method for extracting a boundary with high accuracy without being affected by the measurement environment.

The boundary images A, B, C and D obtained through the above process are integrated by the OR operation in the integration circuit 8.

Next, at step 150, the labeling circuit 10 performs a labeling process.

The "labeling process" is a process of adding different label values to the connected components of each area when a plurality of figures (areas) are present in the obtained image.

Therefore, the labeling is performed by focusing on the non-boundary pixels (areas).

FIG. 7 shows an example of the processing result.

The example shown in FIG. 7 is a case where the boundary line is a closed curve at two places, and different labels "1", "2" and "3" are added to the respective regions. There is.

The labeling process is usually performed in three stages of temporary labeling process, table operation process, and main labeling process.

The labeling process will be described below.

First, the input image is raster-scanned, and a process of sequentially assigning unused labels to pixels other than the pixels forming the boundary line to which no label is assigned is performed up to the final scan pixel (provisional). This is called the labeling process).

At this time, if it is found that pixels with different labels are connected, label connection information is created.

Whether or not pixels with different labels are connected is determined by, for example, whether or not there are pixels with other labels in the vicinity of 4 pixels of interest.

Next, a label value correction table is created based on the label connection information (referred to as table operation processing).

Finally, using the label value correction table,
A real labeling image is created from the temporary labeling image (referred to as a real labeling process).

The details of the labeling processing method are described in more detail, for example, in "Introduction to Computer Image Processing" (Soken Shuppan Co., Ltd .: supervised by Hideyuki Tamura).

Next, at step 160, the rectangular processing circuit 1
In step 1, rectangular information processing is performed.

Here, "rectangle information processing" is an approximation of the shape presented by the pixel points to which the same label is added to a rectangular shape. What size is present at what position? Is a process for obtaining information about.

FIG. 8 shows an example of rectangular information processing performed on a certain area.

The same label is added to the pixels forming the area A, the area A is approximated like a rectangle B, and the rectangle B becomes rectangle information.

As an example of the rectangle processing method, the coordinate system is set as shown in FIG. 8, and the minimum and maximum values of the X and Y coordinates of the X and Y coordinates of the pixels forming the area A can be set. , XMIN, XMAX, YMIN, YMAX, it is conceivable that an area satisfying Expression 8 that satisfies XMIN ≦ X ≦ XMAX and YMIN ≦ Y ≦ YMAX (Expression 8) is used as the rectangular information of the area A.

Note that, as shown in FIG. 8, the X and Y coordinates of the upper left and lower right of the rectangle are set to (S
X, SY), (EX, EY).

After the above processing is completed, rectangle information, for example,
The above (SX, SY) and (EX, EY) are stored in the RAM 12.

Next, the route determination section 19 and the movement control section 2
The operation of No. 6 will be described with reference to FIGS.

First, an obstacle detection and obstacle avoidance method will be described with reference to FIGS. 10 and 11.

FIG. 10 is a camera image captured by a television camera, in which the portion having the width necessary for the automatic guided vehicle to pass through is A, and the portions on the left and right sides thereof are B and C.
And

If the camera is installed in the center of the vehicle body and the width of the vehicle body is known, the width of the portion A in the camera image is determined in advance.

The camera image is an image obtained by photographing the front landscape. The lower side of the camera image is, for example, the front 2 (m) image, and this value is set to a desired value depending on the angle of view of the camera and the mounting height of the camera. The upper side corresponds to a position further away. ..

Here, a method for judging the presence / absence of an obstacle will be described.

Here, as the obstacle, an object other than the floor having a size of a certain value or more, such as a corrugated cardboard box, can be considered.

In order to judge the presence / absence of an obstacle, the obstacle extracting unit A13 makes a judgment based on the obtained rectangular information.

If the lower end of the screen is the floor, and the area other than the floor has an area (rectangular area) larger than a certain value, it is determined that an obstacle exists.

That is, it is checked whether or not the rectangular area (the area having (SX, SY) and (EX, EY) as coordinate points) obtained by the rectangular information processing overlaps the A portion in the camera image. , If they overlap, the area, | (EX-S
If X) × (EY−SY) | is a certain value or more, it is assumed that an obstacle exists.

Next, based on FIG. 11, the turning operation at the time of detecting an obstacle will be described.

The turning operation is performed by changing the direction of the wheels provided at the lower part of the vehicle body.

The azimuth is divided into 16 azimuths every 22.5 degrees, and a number from "0" to "F" is added to each azimuth (see FIG. 11).

First, when going straight (direction is "0"), only the portion A of the front camera image is focused on, and as described above, the presence or absence of an obstacle is determined from the rectangular information.

If there is no obstacle, it is not necessary to perform the turning motion.

If there is an obstacle, B or C
Focus on the part and check whether there is an obstacle. If there is no obstacle, it turns in that direction ("1 direction" if it does not exist in the B section, and "F direction" if it does not exist in the C section).

When attention is paid to the B or C portion, if there is an obstacle in any of the portions, a rule is set to change the azimuth by, for example, 2 units counterclockwise.

If there is no obstacle in the area A of the camera image in the new direction, go straight in that direction. A
If there is an obstacle in the section, attention is paid to the section B or C, and the same processing is repeated, and the turning operation is performed to the direction in which there is no obstacle in the section A.

Now, an operation example of the automatic guided vehicle will be described with reference to FIG.

Note that the series of operations described below are RO
The CPU 16 processes according to the program stored in M17.

At step 1000, various initialization processes are performed.

Target position coordinates with the initial position as the origin are input. For simplicity, 1 unit of coordinates is 1 (m)
Think as

For example, 100 from the current position in the X-axis direction.
If the target position is (m) and the position of 100 (m) in the Y-axis direction, (100, 100) is input from the man-machine interface 15.

When the target position is input, the initial traveling direction is calculated. That is, the angle formed by the target position and the X axis is calculated, and the azimuth closest to the angle is set and stored in the RAM 18. For example, if (100, 100) as described above, the angle formed with the X axis is 45 degrees, so the initial traveling direction is “E”, and this is stored in the RAM 18.

The angle formed by the initial traveling direction with the X axis does not necessarily coincide with the angle defined by the 16 azimuths. In that case, the azimuth closest to the angle formed by the initial traveling direction with the X axis is select.

Next, at step 2000, it is judged whether or not there is an obstacle in the traveling direction, and the vehicle body is turned to a predetermined direction.

The turning is performed by the CPU 16 via the interface circuit 20 and the actuator control circuit 21.
To the first actuator driver 22,
This is executed by driving the first actuator 24 and changing the direction of the wheels.

The method of determining the presence / absence of an obstacle and the method of determining the turning direction are as described above, and therefore a duplicated description will be omitted here.

Here, it is assumed that the azimuth information is stored in the RAM 18.

In step 3000, step 2000
The automatic guided vehicle is moved by a predetermined distance in the direction determined by.

The movement is executed by the CPU 16 sending a signal to the actuator control circuit 21 via the interface circuit 20, and the second actuator driver 23 driving the second actuator 25.

At step 4000, the coordinates of the vehicle position after movement are updated.

Now, let us say that the distance traveled by one transmission of a signal from the CPU 16 is R.

The position where the automatic guided vehicle before moving exists (X
B, YB), the position of the automatic guided vehicle after the movement, and
The angle that the azimuth makes with the X axis is (XA, YA), SH
If ITA is used, the following equation 9 is established, and therefore, this equation is used to update the position coordinates of the own vehicle. This state is shown in FIG.
Shown in.

XA = XB + R × COS (SHITA) YA = YB + R × SIN (SHITA) (Formula 9) In SHITA, the direction information newly stored in step 2000 and the previous direction information are stored. For example, it is calculated and calculated from these differences.

Further, XB, YB and SHITA are sequentially R
Stored in AM18, XA and YA which are calculation results
Are also sequentially stored in the RAM 18, and RA
When the M area is full, the oldest data is shifted and eliminated.

In step 5000, the difference between the target position and the vehicle position is calculated, and if it is determined that the target position has been reached, the process branches to step 7000 and the movement ends.

If it is determined that the target position has not been reached, the process proceeds to step 6000.

Whether or not the target position has been reached is determined, for example, when the coordinates of the current position of the automatic guided vehicle are (XP, YP) and the coordinates of the target position are (XE, YE). When the above condition is satisfied, a method of determining that it has been reached can be considered.

| XP-XE | <1 and | YP-YE | <1 (Formula 10) In step 6000, the route is determined so that the automatic guided vehicle reaches the target position. Here, a method of determining the route so that the vehicle travels on the shortest route, that is, a straight line to the target position will be considered.

The coordinates of the current position of the automatic guided vehicle are (XP, Y
P) and the coordinates of the target position are (XE, YE),
The arc tangent function is set to ARCTAN, and the angle ANG that satisfies the following expression 11 is obtained.

ANG = ARCTAN ((YE-YP) / (XE-XP)) (Equation 11) This angle is obtained by connecting the current position and the target position with a straight line.
This is the angle that the straight line makes with the X axis.

Therefore, the azimuth is determined so that the angle formed by the traveling direction of the automated guided vehicle with the X axis is ANG, and the traveling direction of the automated guided vehicle may be the azimuth.

After the processing in step 6000 is completed, the process branches to step 2000 again, and steps 2000 to 600 are executed until the automatic guided vehicle reaches the target position.
The process up to 0 is repeated.

As described above, according to the present invention, the original image input by the television camera is further differentiated, and a binary image with a plurality of threshold values is created for the differentiated image,
By applying a boundary pixel determination operator to each of the binary images, creating a boundary image, and integrating the boundary images, the boundary is accurately extracted without being affected by the environment,
Furthermore, by performing labeling processing, rectangular information processing, etc., it is possible to grasp the presence or absence of a target in the front and the shape, size, etc. of the existing target, so even if there is no marking such as guidelines, it is possible to accurately An automated guided vehicle that can reach a target position while avoiding an obstacle can be provided.

Of course, the present invention can be applied to various moving bodies. Next, a second embodiment of the present invention will be described with reference to the drawings.

In this embodiment as well, similar to the first embodiment, an automatic guided vehicle among various moving bodies will be described as an example.

Since the configuration example of the automatic guided vehicle is exactly the same as that described with reference to FIG. 19 in the first embodiment, the description thereof is omitted here.

FIG. 13 shows a block diagram of the second embodiment of the present invention.

This embodiment comprises an obstacle extracting unit B31, a route determining unit 19, and a movement control unit 26.

To move the vehicle body portion 38, for example, wheels 39 and the like are installed in the lower portion of the vehicle body portion 38. The orientation of the vehicle body portion 38 is the direction of the wheel 39.
The vehicle body 38 itself is driven by the second actuator 25.

The obstacle extracting section B31 is used for the TV cameras 1 and A.
The D / D converter 2, the smoothing processing unit 27, the boundary extracting unit A30, the labeling circuit 10, the rectangular processing circuit 11, and the RAM 12 are provided.

Further, the boundary extraction unit A30 has the differential processing unit 2
8, a boundary image creation unit 29, and an integrated circuit 8.

The route determining section 17 is configured to have an interface circuit 14, a man-machine interface 15, a CPU (central processing unit) 16, a ROM 17 and a RAM 18, and the same one as in the first embodiment can be used.

The movement control section 26 comprises an interface circuit 20, an actuator control circuit 21, a first actuator driver 22, a second actuator driver 23, a first actuator 24 and a second actuator 25. You can use exactly the same as.

Since the route determination unit 19 and the movement control unit 26 are exactly the same as those in the first embodiment, detailed description of the components will be given only for the obstacle extraction unit B31. The TV camera 1 is a means for collecting luminance information which is image information of the measurement target.

In this embodiment, the NTSC signal of the TV camera is used as the image information, but the reflection intensity information of ultrasonic waves, radio waves or the like may be used as the image information.

The A / D converter 2 is a circuit for converting an analog signal into a digital signal.

The smoothing processing section 27 is a means for removing various noises contained in the image in order to facilitate the feature extraction from the image, and is composed of electronic devices such as various TTL logics.

The differential processing section 28 is a means for obtaining a differential image by applying a differential operator in order to facilitate the extraction of boundaries from the image, and is composed of electronic devices such as various TTL logics.

In the present embodiment, in order to obtain differential images in the four directions of the vertical direction, the horizontal direction, the diagonally upward rightward direction, and the diagonally downward rightward direction, four differential processing units 28 corresponding to the respective directions are provided. Have

The boundary image creating section 29 extracts from the direction-dependent differential image obtained by the differential processing section 28 a pixel whose differential value shows a peak in the differential direction, and the differential value at the pixel is set. This is a means for creating a boundary image by using a pixel having a value larger than a certain threshold as a boundary pixel.
It is composed of electronic devices such as an L logic, a clock circuit, and a delay circuit.

In this embodiment, since the boundary image is created from the differential images in the four directions of the vertical direction, the horizontal direction, the diagonally upward rightward direction, and the diagonally downward rightward direction, four boundary lines corresponding to the respective directions are formed. It has an image creating unit 29.

The integrating circuit 8 is a means for finally obtaining one boundary image by integrating the boundary images in four directions, and is composed of an electronic device such as a logical OR gate.

The labeling circuit 10 is different for each connected component of each area (in this case, for example, a cluster of pixels surrounded by boundary pixels) when a plurality of figures (areas) are present in the obtained image. It is a means of adding a label. Specifically, it is possible to distinguish one connected component from another connected component by a method such as adding numbers.

This means comprises, for example, a CPU (Central Processing Unit), a temporary labeling processing RAM, a table operation processing RAM, and a main labeling processing RAM.

The rectangular processing circuit 11 is means for approximating the shape presented by the pixel points to which the same label is added to a rectangular shape, and is composed of electronic devices such as various TTL logics.

The RAM 12 is a means for storing the rectangular processed image information and the like, and is composed of a semiconductor memory or the like.

Incidentally, it is also used in the second embodiment,
The operations of the route determination unit 19 and the movement control unit 26 are exactly the same as those in the first embodiment, and therefore their description is omitted, and the operation of the obstacle extraction unit B31 which is the main part of the second embodiment will be described below. ..

First, the TV camera 1 reads the image information of the measuring object.

[0209] As the image information, for example, an NTSC signal output from a TV camera is used.

Next, the A / D converter 2 converts the analog output NTSC signal into a digital signal.

Next, the smoothing processing section 27 carries out an image smoothing process based on the obtained digital signal.

Here, the smoothing process is a process of removing various noises contained in the image in order to facilitate the feature extraction from the image. Determine the processed value. In the present invention, this process is not always necessary.

The smoothing processing section 27 performs this smoothing processing
All pixel points are used as points of interest.

Next, the differential processing section 28 performs differential processing of the image based on the smoothed image.

Here, the differential processing is an arithmetic processing applied to an image in order to facilitate boundary extraction.

An example of the differential processing will be described with reference to FIG.

Considering a 5 × 5 matrix, let P be the value of the pixel point of interest, and let P0, P1, P2 be the values of some pixel points around P, as shown in FIG. , P3,
Let P4, P5, P6, and P7.

The "weight matrix" for performing the differential processing is also a 5 × 5 matrix, and the values at the pixel points required for the differential processing are A0,
Let A1, A2, A3, A4, A5, A6, and A7.

Here, let P given by the following expression 12 be a differential value at the pixel point of interest.

P = P0 × A0 + P1 × A1 + P2 × A2 + P3 × A3 + P4 × A4 + P5 × A5 + P6 × A6 + P7 × A7 (Equation 12) Specific values of A0, A1, A2, A3, A4, A5, A6, and A7 are vertical. , Horizontal, diagonally upward to the right, and diagonally downward to the right, as shown in FIG. 14B.

For example, in the case of horizontal differential processing, A0 =
0, A1 = -1, A2 = -2, A3 = -1, A4 = 0,
Since A5 = 1, A6 = 2, and A7 = 1, from Equation 2,
The differential value P at the point of interest is represented by the following expression 13.

P = P0 × 0 + P1 × (−1) + P2 × (−2) + P3 × (−1) + P4 × 0 + P5 × 1 + P6 × 2 + P7 × 1 Therefore, P = −P1-2 × P2-P3 + P5 + 2 × P6 + P7 ( Expression 13) This differentiation processing is performed for all pixel points.

By the similar processing, the differential processing in the vertical direction, the diagonally upward rightward direction, and the diagonally downward rightward direction can be performed.

Next, the pixels showing the peak of the differential value in the differentiating direction are extracted from the created differential image to create the boundary image in that direction.

This processing is executed by the boundary image creating section 29, which will be described with reference to FIG.

The lateral differential image will be described as an example, but exactly the same processing is performed on the differential images in the other three directions.

As described above, in the image differentially processed in the horizontal direction by the differential processing unit 28, the differential value for each pixel is obtained by the expression 12.

By the way, the fact that the differential value shows a peak means that the change of the luminance information becomes maximum, and the point showing this peak value is highly likely to be a point on the boundary. ..

Therefore, the change in the differential value is examined to detect a pixel at which the differential value has a peak (hereinafter, often simply referred to as “peak pixel”).

In order for a certain pixel point P of interest to be a peak pixel, the condition is that Expression 14 is satisfied when P0, P, and P1 are set as shown in FIG.

P> P0 and P> P1 (Equation 14) By the way, even if the differential value itself is small, if Expression 14 is satisfied, the pixel becomes a peak pixel, but the small differential value means that the change in the luminance information is small. This means that the peak pixel is less likely to be a pixel point on the boundary.

Then, the differential value at the peak pixel obtained as described above is compared with a preset threshold value,
When the differential value is larger than the threshold value, the peak pixel is regarded as a boundary pixel and a boundary image is created.

Further, since a pixel which is not a peak pixel is not a boundary pixel, all the pixels which make up the input image are classified into a boundary pixel and other non-boundary pixels, and in the end, the boundary pixel and the non-boundary pixel. Then, the binarized image is obtained.

As described above, the peak pixels are searched and extracted in the direction of the differential processing from the differential processed image,
The differential value at the peak pixel is compared with a certain set threshold value, the peak pixel is regarded as a boundary pixel only when the differential value is larger than the threshold value, a boundary image is created, and a final image is generated. By integrating the boundary images in the integration circuit 8, it is possible to provide a device that extracts the boundaries with high accuracy and with a relatively simple structure, without being affected by the measurement environment. By being mounted on a vehicle, it is possible to provide an automatic guided vehicle capable of reliably avoiding a collision with an obstacle.

Hereinafter, the labeling processing performed by the labeling circuit 10, the rectangular information processing performed by the rectangular processing circuit 11, and the storage processing of the processing information in the RAM 12 are the same as those in the first embodiment. Now, avoid the explanation.

According to the second embodiment described above, it is possible to provide the obstacle extracting section which extracts the boundary with high accuracy without being affected by the environment.

Next, a third embodiment of the present invention will be described with reference to the drawings.

Like the second embodiment, this embodiment is also a case where an automatic guided vehicle is considered as an example of the moving body, and the description of the configuration will be omitted because it is redundant.

FIG. 16 shows a block diagram of the third embodiment of the present invention.

The present embodiment is provided with an obstacle extracting section capable of performing boundary extraction with higher accuracy, though the structure is slightly complicated as compared with the second embodiment.

This embodiment has an obstacle extracting section C37, a route determining section 19 and a movement controlling section 26.

Wheels 39 and the like are installed in the lower portion of the vehicle body portion 38 for moving the vehicle body portion 38, and the orientation of the vehicle body portion 38 can be changed by the first actuator 24. The vehicle body 38 itself is driven by the second actuator 25.

The obstacle extracting section C37 is connected to the TV camera 1, A
/ D converter 2, smoothing processing unit 27, boundary extraction unit B36, labeling circuit 10, rectangular processing circuit 11, RAM memory 1
It is configured to have 2.

Further, the boundary extracting unit B36 is the differential processing unit 2
8, peak extraction unit 32, first expansion unit 33, second expansion unit 3
It is configured to include a 4- and 2-valued image creating unit 35 and an integrated circuit 8.

The route determining unit 17 is constituted by the interface circuit 14, the man-machine interface 15, the CPU (central processing unit) 16, the ROM 17 and the RAM 18, and the same one as in the first embodiment can be used.

The movement control section 26 comprises an interface circuit 20, an actuator control circuit 21, a first actuator driver 22, a second actuator driver 23, a first actuator 24 and a second actuator 25. You can use exactly the same as.

Since the route determination unit 19 and the movement control unit 26 are exactly the same as those in the first embodiment, the detailed description of the components will be given only for the obstacle extraction unit C37.

The components of the obstacle extracting section C37 will be described below.

The obstacle extracting section C37 is used for the TV camera 1, A
The D / D converter 2, the smoothing processing unit 27, the differentiation processing unit 28, the peak extraction unit 32, the first expansion unit 33, the second expansion unit 34, the binary image creation unit 35, and the integrated circuit 8 are included. ..

The TV camera 1 is a means for collecting the brightness information which is the image information of the measuring object.

The A / D converter 2 is a circuit for converting an analog signal into a digital signal.

The smoothing processing section 27 is means for removing various noises contained in the image in order to facilitate feature extraction from the image, and is composed of electronic devices such as various TTL logics.

The differential processing section 28 is a means for obtaining a differential image by applying a differential operator in order to facilitate the extraction of boundaries from the image, and is composed of electronic devices such as various TTL logics.

In the present embodiment, in order to obtain differentially processed images in the four directions of the vertical direction, the horizontal direction, the diagonally upward rightward direction, and the diagonally downward rightward direction, the four images corresponding to each direction are obtained.
It has one differential processing unit 28.

The peak extraction unit 32 is
Pixels whose differential values show peaks are extracted and set to 2
By comparing the three thresholds with the differential value at the peak pixel, the pixel is classified into three types of a boundary pixel, a boundary candidate pixel, and a non-boundary pixel, and a ternary image is created from the differential processed image. Yes, it is composed of electronic devices such as various TTL logics, semiconductor memories, clock circuits, and delay circuits.

In this embodiment, the four peak extracting parts 32 are provided corresponding to the differential processed images in the four directions of the vertical direction, the horizontal direction, the diagonally upward rightward direction, and the diagonally downward rightward direction.

The first extension section 33 performs, for example, raster scanning of the ternary image created by the peak extraction section 32, pays attention to a certain boundary candidate pixel, examines a pixel in the vicinity of the boundary candidate pixel, and When the boundary candidate pixel is connected to the boundary pixel, the boundary candidate pixel is converted into the boundary pixel for all the boundary candidate pixels, and is an electronic device such as various TTL logics or semiconductor memories. Composed of devices.

In this embodiment, four first extension parts 33 are provided corresponding to the four peak extraction parts 32.

The second expansion unit 34 is means for performing, for example, raster scanning in the same direction as the first expansion unit 33 in the opposite direction to the first expansion unit 33.
It is composed of electronic devices such as L logic and semiconductor memory.

In this embodiment, four second expansion parts 34 are provided corresponding to the four first expansion parts 33.

The binary image creating section 35 is a boundary pixel created by being processed by the first expanding section 33 and the second expanding section 34.
It is a means for creating a binary image from the boundary candidate pixels and the non-boundary pixels by setting the boundary candidate pixels as the non-boundary pixels, and is composed of various TTL logics, electronic devices such as semiconductor memories.

In this embodiment, four binary image forming parts 35 are provided corresponding to the four second expanding parts 34.

The integration circuit 8 is means for finally integrating one binary image by integrating binary images in four directions, and is composed of an electronic device such as a logical OR gate.

When a plurality of figures (areas) are present in the obtained image, the labeling circuit 10 determines, for each connected component of each area (in this case, a group of pixels surrounded by boundary pixels), It is a means of adding different labels. Specifically, it is possible to distinguish one connected component from another connected component by a method such as adding numbers.

This means comprises, for example, a CPU (central processing unit), a temporary labeling processing RAM, a table operation processing RAM, and a main labeling processing RAM.

The rectangular processing circuit 11 is means for approximating the shape presented by the pixel points to which the same label is added into a rectangular shape, and is composed of electronic devices such as various TTL logics.

The RAM 12 is a means for storing the rectangular processed image information and the like, and is composed of a semiconductor memory or the like.

The operation of this embodiment will be described below, but a detailed description of the portions overlapping with those of the first embodiment will be omitted.

First, the TV camera 1 reads the image information of the measuring object.

Next, the A / D converter 2 converts the image information signal output in analog into a digital signal.

Next, the smoothing processing section 27 carries out an image smoothing process on the basis of the obtained digital signal with all the pixel points as the points of interest.

Here, the smoothing process is a process for removing various noises contained in the image, and as described above, the equation (1) is used.
Thus, the smoothing processing value at the pixel point of interest is obtained.

Although the present process is not always necessary in the present invention, this process will be described below.

Next, the differential processing section 28 performs differential processing of the image based on the smoothed image.

Here, the differential processing is an arithmetic processing applied to an image in order to facilitate the boundary extraction, and is processed using the weight matrix shown in Expression 12 and FIG. 14 as described above. The differentiating method is exactly the same as that of the second embodiment, so detailed description will be omitted here.

The main differentiation processing is performed in four directions of the vertical direction, the horizontal direction, the diagonally upward rightward direction, and the diagonally downward rightward direction.

Next, the peak extraction unit 32 extracts peak pixels, divides the pixels into boundary pixels, boundary candidate pixels or non-boundary pixels, and obtains a ternary image for all pixels.

This will be described below.

The method for obtaining the peak pixel is as described with reference to FIG. 15 in the second embodiment.

For example, for the differential image in the horizontal direction, if the expression 14 is satisfied in the pixel arrangement shown in FIG. 15, the point P is judged to be a peak pixel.

Next, the differential value at the point P is compared with two preset threshold values.

For the sake of explanation, the two threshold values are referred to as a first threshold value and a second threshold value, respectively, and the first threshold value is set larger than the second threshold value. It has been done.

When the peak pixel is obtained, the differential value of the pixel is compared with the two threshold values.

First, if the differential value is larger than the first threshold value, the peak pixel is set as the boundary pixel.

Next, if the differential value is less than or equal to the first threshold value and greater than the second threshold value, the peak pixel is set as a boundary candidate pixel.

Further, if the differential value is less than or equal to the second threshold value, the peak pixel is set as a non-boundary pixel.

Since the pixels other than the peak pixels are originally non-boundary pixels, all the pixels are ternarized and a ternary image is obtained.

The third embodiment can extract boundaries more accurately than the second embodiment because two threshold values are set, and a clear boundary is surely extracted by the first threshold value. , A pixel whose differential value is smaller than the first threshold value but larger than the second threshold value, that is, a pixel which cannot be determined as a boundary pixel is set as a boundary candidate pixel, and the boundary candidate pixel is expanded by the expansion process described later. However, only when there is a high possibility that the pixel is a boundary pixel, the boundary candidate pixel is processed as a boundary pixel.

Next, the first expansion section 33 and the second expansion section 3
The processing performed in 4 will be described.

In the first expansion unit 33 and the second expansion unit 34, among the boundary candidate pixels, the pixels connected to the boundary pixel are converted into boundary pixels.

The first extension unit 33 firstly detects the peak extraction unit 3
The ternary image created in 2 is raster-scanned, for example, and when the boundary candidate pixels are scanned, the following processing (this processing is referred to as “extended processing”) is performed.

For example, among the pixels in the 8 neighborhoods of the boundary candidate pixel of interest, the remaining pixels except the two pixels existing in the differential direction are examined.

Next, when the boundary candidate pixel is connected to the boundary pixel, the boundary candidate pixel is converted into a boundary pixel.

This process is performed up to the last pixel while performing raster scanning, for example.

In FIG. 17, the pixels in the vicinity of the pixel of interest are examined,
An example of processing for determining a boundary candidate pixel as a boundary pixel will be shown.

This shows an example of expanding the differential image in the horizontal direction.

Since P is the boundary candidate pixel of interest, P is the differential direction among the eight neighboring pixels of the pixel.
Of the remaining pixels except for the two pixels existing in the horizontal direction of P0, P1, P2, P3, P4, P5,
If it is a boundary pixel, P is used as the boundary pixel.

The extension processing excluding the pixels in the differential direction (horizontal direction in this case) is, for example, the horizontal differential processing is the processing of extracting the vertical boundary, and therefore the boundary candidate pixel Pixels existing in the lateral direction of the point P are treated as pixel points that do not need to be determined.

In the second extension section 34, the same extension processing as that performed in the first extension section 33 is performed by the first extension section 33.
Do from the opposite direction.

It should be noted that two expansion processing means are provided, and the expansion processing is performed from both directions only when the expansion processing is performed from only one direction, even if the boundary candidate pixel is connected to the boundary pixel. This is because the candidate pixel may become a non-boundary pixel, which is to be avoided.

For example, as shown in FIG. 18 (in the case of vertical differentiation), the boundary candidate pixel D is connected to the boundary pixel E and can be changed to the boundary pixel only by the scanning in the a direction. Although it is considered that the boundary candidate pixels B and C are connected to the boundary pixel E through the pixel D, the boundary candidate pixels B and C cannot be changed to the boundary pixel and become a non-boundary pixel.

Therefore, each pixel is also scanned from the b direction,
A boundary candidate pixel C connected to the boundary pixel D is set as a boundary pixel, and further, a boundary candidate pixel B connected to the boundary pixel C.
The occurrence of such a situation is avoided by setting the boundary pixel to be.

As described above, by performing the extension processing from both directions, the complete extension processing can be performed.

The expansion process is performed in the four directions of the vertical direction, the horizontal direction, the diagonally upward rightward direction, and the diagonally downward rightward direction.

In the binary image creating section 35, the boundary candidate pixels that have not been converted into the boundary pixels are set as the non-boundary pixels in the expanded image so that all the pixels forming the image are separated into the boundary. Distinguish between pixels and non-boundary pixels.

For example, a binary image in which the boundary pixel is "1" and the non-boundary pixel is "0" is created.

[0307] The binary image creation processing is also performed in the vertical direction, the horizontal direction, the diagonally upward rightward direction, and the diagonally downward rightward direction.
Done for the direction.

Finally, the integration circuit 8 integrates the binary images in four directions by a logical OR gate or the like to create one boundary image.

Since the labeling processing performed by the labeling circuit 10, the rectangular information processing performed by the rectangular processing circuit 11, and the storage processing of the processing information in the RAM 12 are the same as those in the first embodiment, the following description is omitted here. Now, avoid the explanation.

According to the third embodiment described above, it is possible to provide an obstacle extraction unit that extracts a boundary with high accuracy without being affected by the environment.

That is, when the threshold value is one, in order to extract all the boundaries, it is necessary to reduce the set value of the threshold value. However, it also increases.

Therefore, two threshold values are provided, the first threshold value is set to a large value, a clear boundary is surely extracted, and the second threshold value is larger than the first threshold value. When the value is small and the differential value at the pixel point of interest is larger than the second threshold value and less than or equal to the first threshold value, it is determined whether the pixel point close to the pixel point of interest is the boundary pixel. By checking whether or not the pixel point of interest is the boundary pixel, it is possible to surely perform the boundary extraction.

By using the obstacle extracting units of the first to third embodiments described above in the automatic guided vehicle, the obstacle is surely avoided, and the vehicle autonomously reaches the target position. An automated guided vehicle can be configured.

Of course, the moving body of the present invention is not limited to the automatic guided vehicle.

[0315]

According to the present invention, a boundary extraction device that is not affected by the environment is mounted, obstacles are reliably detected, collisions are avoided, markings such as guidelines are not used, and autonomous operation is performed up to the target position. It is possible to provide a moving body that can be reached.

[Brief description of drawings]

FIG. 1 is an explanatory diagram of a configuration of a first embodiment of the present invention.

FIG. 2 is a process chart for explaining the operation of the first embodiment of the present invention.

FIG. 3 is an explanatory diagram of a smoothing operator.

FIG. 4 is an explanatory diagram of a differential operator.

FIG. 5 is an explanatory diagram of a boundary pixel determination operator.

FIG. 6 is an explanatory diagram of a boundary pixel determination operator.

FIG. 7 is an explanatory diagram of labeling processing.

FIG. 8 is an explanatory diagram of rectangular information processing.

FIG. 9 is a process diagram for explaining the operation of the automatic guided vehicle.

FIG. 10 is an explanatory diagram for explaining the principle of obstacle detection.

FIG. 11 is an explanatory diagram for explaining the principle of obstacle avoidance.

FIG. 12 is an explanatory diagram of the principle of updating the position coordinates of the automatic guided vehicle.

FIG. 13 is an explanatory diagram of a configuration of a second embodiment of the present invention.

FIG. 14 is an explanatory diagram of a direction-specific differentiation operator.

FIG. 15 is an explanatory diagram of a peak pixel extraction principle.

FIG. 16 is an explanatory diagram of a configuration of a third embodiment of the present invention.

FIG. 17 is an explanatory diagram illustrating an extension process.

FIG. 18 is an explanatory diagram illustrating an extension process.

FIG. 19 is an explanatory diagram of a configuration of an automatic guided vehicle.

[Explanation of symbols]

1 ... TV camera, 2 ... A / D converter, 3 ... Smoothing circuit,
4 ... Differentiation processing circuit, 5 ... Threshold value, 6 ... Binary image creation unit, 7 ... Boundary image creation unit, 8 ... Integration circuit, 9 ... Boundary extraction circuit, 10 ... Labeling circuit, 11 ... Rectangular processing circuit, 1
2 ... RAM, 13 ... Obstacle extraction unit A, 14 ... Interface circuit, 15 ... Man-machine interface, 1
6 ... CPU, 17 ... ROM, 18 ... RAM, 19 ... Path determination unit, 20 ... Interface circuit, 21 ... Actuator control circuit, 22 ... First actuator driver,
23 ... 2nd actuator driver, 24 ... 1st actuator, 25 ... 2nd actuator, 26 ... Movement control part, 27 ... Smoothing process part, 28 ... Differentiation process part, 29 ... Boundary image creation part, 30 ... Boundary extraction part A , 31 ... Obstacle extracting unit B, 32 ... Peak extracting unit, 33 ... First expanding unit, 34 ... Second expanding unit, 35 ... Binary image creating unit, 36 ... Boundary extracting unit B, 37 ... Obstacle extracting unit C, 38 ... Body part, 39 ... Wheel

Claims (5)

[Claims] 1. A means for inputting image information of an object to be measured,
Means for differentiating the image information, means for creating a boundary image from the image obtained by the means, means for labeling the created boundary image, means for rectangularly processing the labeled image information, Obstacle extraction means by image processing consisting of means for storing rectangular processed information, route determination means for determining the route to the target position while avoiding collision with obstacles, controlling the traveling direction, A movement control unit that drives the vehicle to travel on the determined route, a vehicle body unit on which the obstacle extraction unit, the route determination unit, and the movement control unit are mounted, and a movement unit provided below the vehicle body unit for movement. A moving body consisting of means. 2. A means for inputting image information of an object to be measured,
Means for differentiating the image information, means for setting a plurality of threshold values for binarizing the differential value by the means, means for creating a binary image with each threshold value, each created In the binary image, the target pixel point is operated by a boundary pixel determination operator that determines whether or not the target pixel point forms a boundary line, and if it is determined that the target pixel point forms the boundary line, the target pixel point is selected. Pixel points are judged as boundary pixels,
Boundary image creating means, integrating each created boundary image, labeling processing of the integrated boundary image, rectangular processing of the labeled image information, and rectangular processing. The obstacle extraction means including the means for storing the information stored therein, the route determination means for determining the route to the target position while avoiding the collision with the obstacle, and the traveling direction for controlling the traveling direction. A moving body including a movement control unit that drives to move forward, an obstacle extracting unit, a route determining unit, and a vehicle body unit on which the movement control unit is mounted, and a unit for moving provided below the vehicle body unit. .. 3. An image information input means for inputting image information of an object to be measured, and a vertical, horizontal, diagonally upward right, and diagonally downward right 4
A differential processing means for operating a direction-specific differential operator in each direction to create a direction-specific differential image in four directions; and a means for examining a pixel showing a peak of a differential value in the direction for each direction-specific differential image, When the differential value in the pixel is larger than a certain set threshold value, a unit that creates a boundary image by using the pixel indicating the peak value as a boundary pixel, and a unit that integrates the created boundary images in four directions. An obstacle extraction unit including a unit for labeling the integrated boundary image, a unit for rectangularly processing the image information subjected to the labeling process, and a unit for storing the rectangularly processed information; and collision with the obstacle Route determining means for determining a route to the target position while avoiding, movement control means for controlling the traveling direction and driving so as to travel on the determined route, the obstacle extracting means, Road determining means, and a body member for mounting the movement control means, the moving body and means for moving provided in the lower body portion. 4. An image information input means for inputting image information of an object to be measured, and four of vertical, horizontal, diagonally rightward and diagonally rightward.
A differential processing means for operating a direction-specific differential operator in each direction to create a direction-specific differential image in four directions; and a means for examining a pixel showing a peak of a differential value in the direction for each direction-specific differential image, Using the first threshold value and the second threshold value set smaller than the first threshold value, the differential value in the pixel is a boundary pixel having a value larger than the first threshold value, Those that are less than or equal to the first threshold value but greater than the second threshold value are boundary candidate pixels, and further,
A unit that creates a ternarized image with a second threshold value or less as a non-boundary pixel, and scans the ternary image from a certain direction, paying attention to a certain boundary candidate pixel, A first expansion unit that performs a process of converting a boundary candidate pixel into a boundary pixel when a pixel in the vicinity of the boundary candidate pixel is checked and the boundary candidate pixel is connected to the boundary pixel The processing performed in 1. is expanded in the opposite direction to the second expansion means, the means for creating a boundary image from the image created by the second expansion means, and the created respective boundary images are integrated. An obstacle extracting unit including a unit, a unit for labeling the integrated boundary image, a unit for rectangularly processing the image information subjected to the labeling, and a unit for storing the rectangularly processed information; and an obstacle. Route to the target position while avoiding collision Determining means, a movement control means for controlling the traveling direction and driving so as to travel along the decided route, and an obstacle extracting means, a route determining means, and a vehicle body equipped with the movement control means. And a means for moving provided on the lower part of the vehicle body. 5. The moving body according to claim 1, 2, 3, or 4, wherein the moving body is an automated guided vehicle.