JPH0465402B2 - - Google Patents

Description

[Detailed Description of the Invention] [Industrial Application Field] The present invention converts image information into edge image information based on changes in brightness of image information captured by an imaging means that captures an image of a working area state in a predetermined range on the forward side in the direction of movement of an aircraft. a differential processing means for performing a Hough transform process on the binary image information; a binarizing means for binarizing the edge image information based on a set threshold value;
The present invention relates to a boundary detection device for an automatically traveling work vehicle, which includes a boundary parameter calculation means for calculating the vehicle body positional relationship with respect to the boundary between an untreated work area and a processed work area based on the Hough transform processing result.

[Conventional technology]

This type of boundary detection device described above takes advantage of the characteristic that the brightness of an untreated work area and a treated work area appears to be different, and captures an image of the working area situation in front of the travel route of the work vehicle. Converting the information into an edge image based on the brightness change, binarizing the portion where the brightness change is large based on a set threshold value, and removing noise components from the binarized image information by performing Hough transform processing, Information corresponding to boundaries is recognized as continuous line segments.

In this way, as a means of combining discontinuous line segments into continuous line segments or erasing isolated line segments,
It is known that Hough transform processing is effective.

[Problems to be Solved by the Invention] However, although the Hough transform processing described above is an effective means for approximating discontinuous line segment information to one continuous line segment information, the calculation required for the processing is However, it is necessary to convert the image information in the orthogonal coordinate system to the polar coordinate system, which requires arithmetic processing with a heavy processing load. Furthermore, since the processing has to be performed over all pixels, the amount of information to be processed increases, making high-speed processing difficult.

By the way, since the automatic traveling work vehicle described above travels while performing various tasks, its travel trajectory, that is, the direction of the boundary between the untreated work area and the treated work area, does not suddenly change. In other words, although the boundary may have some curvature caused by steering of the working vehicle, it can be recognized as a straight line that coincides with the traveling direction of the working vehicle.

Therefore, the above-mentioned actual boundary can be regarded as matching the line segment information included within a relatively narrow specific range of the captured image information, and the Huff in all directions of the captured image information. It can be said that there is no need to convert it.

The present invention has been made in view of the above-mentioned circumstances, and its purpose is to enable the above-mentioned Hough transform processing to be performed easily and at high speed.

[Means for solving problems]

The feature of the boundary detection method for an automatic traveling work vehicle according to the present invention is that the Hough transform means corresponds to the coordinate value of each pixel, and that the boundary detection method corresponds to the coordinate value of each pixel and that A Hough transform data storage means is provided in which Hough transform data within a set angle range narrower than the degree range is tabulated in advance, and the tabulated Hough transform data is directly read out in correspondence with the coordinate values. In addition, there is provided a counting means for counting the readout frequency in order to determine the information with the highest readout frequency as information corresponding to the boundary, and its functions and effects are as follows.

[Effect]

In other words, the angular range of the Hough value for tabulating the Hough transform data calculated corresponding to each pixel of the captured image information is set in advance in the direction of extension of the boundary.
By limiting the angle to a set angle range narrower than the range of 90 degrees to -90 degrees, the amount of Hough transform data for detecting the boundary is kept small. Then, at the same time as the binarized image information is read out, the corresponding Hough transform data is read out, its frequency is counted, and the Hough transform data with the highest frequency is used as detection boundary information.

〔Effect of the invention〕

Therefore, it is possible to reduce the capacity of a storage means such as a memory for storing Hough transform data necessary for Hough transform processing, and since the storage capacity is small, it is possible to significantly shorten the time required to complete Hough transform processing. can. Furthermore, since the Hough value used to obtain boundary information uses only a specific range in the direction of the boundary, Hough transform of unnecessary ranges is not substantially performed, so despite the simplification, , the recognition accuracy is better than when recognition is performed over all pixels.

〔Example〕

DESCRIPTION OF THE PREFERRED EMBODIMENTS An embodiment in which the method of the present invention is applied to a lawn mowing vehicle as an automatically traveling vehicle will be described below with reference to the drawings.

As shown in FIGS. 7 and 8, the lawn mower 2 is vertically movably suspended in the middle of the machine V, which is configured to be able to steer both the front wheels 1F and the rear wheels 1R. A video camera 3 is provided as an image capturing means for capturing an image of the working area in a predetermined range ahead in the direction of travel, and the image information captured by the camera 3 is binarized by a boundary detection device A to be described later. Boundary between untreated work area B and treated work area C in each direction
The positional relationship of the aircraft V with respect to L ₁ and L ₂ is detected, and based on the detection results of the boundaries L ₁ and L ₂ by the boundary detection device A, the travel control device H causes the aircraft V to move along the boundary L ₁ . The vehicle is configured to perform a steering operation to automatically travel, and after completing one stroke, to perform a steering operation and a gear shift operation to automatically travel to the next stroke.

The camera 3 is installed at the tip of a support frame 4 that extends toward the upper front of the aircraft V so as to take an image of a predetermined range of work area on the front side of the aircraft from diagonally upward to downward. In a state where V is along the boundary L ₁ in the width direction, this boundary L ₁ is located at the center of the imaging field of the camera 3 in the vertical direction.

When detecting the boundary L ₁ in the width direction of the aircraft V, the detection boundary L _{1 is determined with respect to a reference line L 0 that} vertically traverses the center of the imaging field of the camera 3 in the vertical direction, with the lower end of the imaging field of the camera 3 as a reference. The positional deviation β is taken as the positional deviation information in the width direction of the aircraft V, and the inclination α of the detection boundary L 1 with respect to the reference line L ₀ that vertically traverses the center of the imaging field of view of the camera 3 in the vertical direction is defined as the inclination α of the detection boundary L ₁ of the aircraft V.
Detected as direction deviation information.

On the other hand, when detecting the boundary L ₂ in the longitudinal direction of the aircraft V, the vertical center of the imaging field of the camera 3 is The deviation β with respect to the reference line L that runs vertically is the distance information between the aircraft V and the boundary _L2 , and the inclination α with respect to the reference line L that runs vertically across the center of the imaging field of the camera 3 in the vertical direction is:
Aircraft V with respect to boundary L ₂ in the longitudinal direction of the aircraft V
The slope is In addition, the boundary in the front and rear direction of this aircraft V
When detecting L ₂ , the value of the detection deviation β does not immediately become the position information of the end of the stroke, so
The value of the detection deviation β and the body V of the camera 3
The distance from the lower end of the imaging field of view to the aircraft V is set in advance based on the mounting distance and the angle of the imaging direction, and the boundary L ₂ is set based on this set distance information.
The actual distance between this and the aircraft V is calculated.

By the way, since the image captured by the camera 3 is binarized based on the brightness difference between adjacent pixels, it is necessary to remove the influence of local brightness changes and average it. A soft focus filter 8 is provided in front of the camera 3 to blur the captured image.

Furthermore, since the camera 3 looks down diagonally from above the aircraft V, its imaging field of view becomes a trapezoid that expands from the near side to the far side, and the further away the image becomes, the more detailed the image becomes. Therefore, if the image information S ₀ captured by the camera 3 is sampled as is, the closer the image information is to the near side, the more local changes may be emphasized and the nozzle component may increase, so the entire captured image will not be uniformly averaged. As shown in FIG.

Further, as a means for eliminating the influence of large brightness changes such as shadows of untreated grass caused by natural light, a strobe device 9 is provided which emits light in synchronization with the image taking by the camera 3.

As shown in FIG. 9, the driving force from the engine E is transmitted to each of the front wheels 1F and rear wheels 1R via the transmission 4, and the shift position detected by the shift position detection potentiometer _R3 is The motor 5 is driven so that the vehicle travels at a predetermined speed so as to reach a predetermined position.

The front wheels 1F and the rear wheels 1R are configured to be power-steering operated by hydraulic cylinders 6F and 6R, respectively, and are controlled by steering angle detection potentiometers P ₁ and R ₂ that are linked to the steering operation of the wheels. an electromagnetic valve 7F that operates the hydraulic cylinders 6F and 6R so that the detected steering angle matches the target steering angle;
It is designed to drive 7R. When correcting the tilt α of the aircraft V in the longitudinal direction with respect to the boundary L ₁ in the aircraft longitudinal direction, the front wheels 1F and the rear wheels 1R are steered in relatively opposite directions in order to change the aircraft V direction. When performing turning steering and correcting the deviation β in the width direction of the aircraft V with respect to the boundary L ₁ , in order to move the aircraft parallel in parallel without changing the orientation of the aircraft V, turn the steering so that the front wheels 1F and rear wheels 1R face the same direction. By performing parallel steering operations, the aircraft V is efficiently controlled to follow the boundary _L1 .

The configuration and operation of the boundary detection device A will be described below.

As shown in FIG. 1, the boundary detection device A quantizes the image information _S0 captured by the camera 3 with an 8-bit resolution and converts it into a digital value.
D conversion unit 10, image memory 1 that converts the digitized image information by 90 degrees in coordinates x and y, samples it as image information with a number of constituent pixels of 32×32, and stores the sampled image information;
1. Image information S ₂ stored in this image memory 11
and image information output from the A/D converter 10.
S ₁ (However, the number of constituent pixels is processed as 32 x 32)
an image switching device 12 as an input format switching means for switching which image information is to be processed;
Image signal F ₁ output from this switch 12
is differentiated based on the brightness change in the aircraft width direction (x-coordinate direction) and converted into edge image data _F2 corresponding to the directionality and magnitude of the brightness change; Based on the differential sign (positive, negative) of _the edge image data F ₂ that has been differentially processed by Binarize based on
A binarization processing unit 30 extracts image parts with large brightness changes, and the two binarized by this binarization processing unit 30
Approximate the digitized image data _F3 as a continuous straight line,
A Hough transform unit 40 that identifies boundaries L ₁ and L ₂ on the image, and the following equation approximated as a straight line representing the positional relationship of detection boundaries L ₁ and L ₂ with respect to the aircraft V based on information from this Hough transform unit 40 i, a control section 60 that controls the operation of each processing section, an ITV controller 13 that controls light emission of the strobe 9 and imaging of the camera 3, the differential processing section 20, and binarization. Monitor television 1 that displays images processed by the processing unit 30
The CRT controller 14 controls the operation of the CRT controller 5.

y=ax+b...(i) However, a: Inclination of the boundaries L ₁ and L 2 with respect to the reference line L ₀ in the image coordinate system, b: Inclination of the boundaries L ₁ and _{L 2 with} respect to the reference line L ₀ in the image coordinate system Lateral deviation, x: Coordinate value of a pixel in the width direction of the aircraft V; y: Coordinate value of a pixel in the longitudinal direction of the aircraft V.

The overall operation will be described below based on the flowchart shown in FIG.

That is, an image captured by averaging the entire image using the blurring filter 8 is captured, the captured image signal _S0 is A/D converted, and an orthogonal coordinate system x consisting of 32 x 32 pixels per screen is obtained. , y into a digitized original image signal _F1 .

Next, detect the boundary L ₁ in the width direction of the aircraft in the middle of the journey, or the boundary in the longitudinal direction of the aircraft at the end of the journey.
If _{the boundary L 2 at} the end of the stroke is to be detected, the image memory 11
By converting the address coordinates of image signal S ₁ by 90 degrees and giving the image information S ₂ stored by converting the coordinates of image signal S 1 by 90 degrees, when detecting the boundary L ₁ in the middle of the journey, use the original image signal Image signal in the same coordinate system as S ₀
Using _S1 , the differential processing section 20 performs differential processing on the image data, and the binarization processing section 30 binarizes only the differential sign whose direction is positive or negative.

This selection of whether the differential sign is positive or negative is to be binarized is made as explained below.
The setting is made based on whether the untreated work area B exists on either the left or the right side. That is, for example, if we explain the case where the work method is circular mowing, in which the direction is turned 90 degrees on each side of the outer periphery of the work area and the machine moves counterclockwise toward the inner periphery, in this case, the machine V is on the right side. The vehicle is now traveling adjacent to the treated work area C. In other words, when the brightness change is scanned from the left side to the right side of the image, a large positive change from dark to bright occurs at the boundary _L1 . When the change between adjacent pixels is differentiated, the sign of the differential value is positive. The (+) one corresponds to a certain directionality of the boundary _L1 when looking at the brightness change from the untreated work area B side to the treated work area C side, and the negative (-)
This can be considered as noise and removed.

Next, this differentially processed image data is binarized, and based on the following formula (), the orthogonal coordinate system is converted to a polar coordinate system and Hough transform is performed. At each of the polar coordinates ρ, θ, the same Hough transform data ρ take 2
The frequency of the digitized image data is counted as a two-dimensional histogram and its maximum value (Dmax) is determined.

ρ＝xcosθ＋ysinθ……() however, 60 degrees≦θ＜120 degrees x: Coordinate value of the pixel in the horizontal direction of the aircraft V y: Coordinate value of a pixel in the longitudinal direction of the aircraft V It is.

Then, from the value of the Hough transform data ρ of the frequency D that is the maximum value (Dmax), the above equation (i), which is a boundary parameter corresponding to one boundary information, is determined, and the coefficient of this equation (i) is determined. slope a and deviation b
Therefore, in the traveling control device H, the actual inclination α of the aircraft V with respect to the boundary L ₁ and the deviation β in the width direction
The front wheel 1F and the rear wheel 1R are controlled so that the front wheel 1F and the rear wheel 1R are steered so that the tilt α and the deviation β become zero, respectively, so that the aircraft V automatically travels along the boundary _L1 . .

In addition, in the above formula (), the range of angle θ for Hough transformation is limited to 60 degrees ≦ θ < 120 degrees because
In other words, the reason why the setting angle range is narrower than the range of +90 degrees to -90 degrees with respect to the extending direction of the boundary is because the steering of the work vehicle is controlled.
This is because the range in which L ₁ exists in the captured image information does not deviate from the angular range limited above, and therefore there is no need to perform Hough transform processing outside the angular range limited above.

By the way, when detecting the boundary L ₁ in the width direction of the aircraft, the image information captured by the camera 3 is directly input to the differential processing 20 and processed, and when detecting the boundary L ₂ in the longitudinal direction of the aircraft, the original image information The vertical direction y is the horizontal direction x, and the horizontal direction x is the vertical direction y.
The coordinates x, y of the imaging information are converted by 90 degrees by being converted and stored in the image memory 11, and read out with the original coordinate system x, y unchanged, and then input to the differential processing section 20. Since the processing is performed, each processing section after the differential processing section 20 can be used as is to detect boundaries L ₁ and L ₂ in different directions with respect to the aircraft V.

When detecting the boundary L ₂ in the longitudinal direction of the aircraft, if the maximum value (Dmax) of the frequency matching the same Hough transform data ρ is not greater than the set threshold (Dref), the aircraft V is still at the end of the stroke. It can be determined that the area near the boundary _L2 has not been reached. On the other hand, if the maximum value (Dmax) is greater than or equal to the set threshold (Dref), the distance from the aircraft V to By finding the distance to the end boundary _L2 , the turning point can be determined accurately.

By the way, when detecting the boundary L ₂ in the longitudinal direction of the aircraft, even if the same process is used in which the angular range for Hough transform is limited to a narrow range in the above formula (), the boundary L ₂ in the longitudinal direction of the aircraft The direction of the end of the travel process is only 90 degrees different from the aircraft V direction, that is, the boundary L ₁ in the aircraft width direction, and it is impossible for the range of existence on the image information to be extremely different. , even if the angular range to be subjected to Hough transform is limited, this does not have any effect.

Hereinafter, the operation of each part will be explained based on the drawings shown in FIGS. 3 to 6.

First, the configuration and operation of the control section 60 will be explained based on the block diagram shown in FIG.

The entire operation of the control section 60 is performed in synchronization with the clock signal CL generated by the clock generator 61a, and the CPUs 1 and 62 function as control processors that control the operations of each section.
a and CPU2,62 as a processor for numerical calculations
Two processors (b) are provided to enable high-speed processing. The calculation results of each control signal and data are exchanged between each processing section via a bus buffer 63. Similarly, data is exchanged with the travel control device H through the serial interface SIO port 6.
4a and a communication interface 64b connected to this SIO port 64a, and offline via a switch interface 64c for offline and a PIO port 64d for parallel interface. It is also possible to start A.

Furthermore, data exchange between the processors CPU1, 62a and CPU2, 62b, data exchange via the bus buffer 63, and control of their operations are performed by an input/output controller 65, and data from the respective ports 64a, 64d are controlled. Control of data exchange is also performed via the CTC controller 66 using control signals from the input/output controller 65. In addition, in Figure 3, 61
b is SIO port 64a and CTC controller 6
ROM 67 is a memory in which the operation program of boundary detection device A is stored, RAM 68 is a memory used to temporarily store each data or as a buffer for calculation data, LUT 69 is the calculation data for high-speed conversion from the orthogonal coordinate values x, y of each pixel of the image information used in the Hough transform unit 15 to Hough transform data ρ in the polar coordinate system, that is, the coordinates x,
This memory serves as a Hough transform data storage means in which Hough transform data ρ is stored in advance as a table so that the Hough transform data ρ can be directly obtained from the value of y.

As shown in FIG. 4, the LUT 69 calculates the angle θ (however, 60
Hough transform data ρ for each angle is calculated in advance by dividing the angle (degree ≦ θ < 120 degrees) into 42 equal parts, and
y, that is, 42 (2A in hexadecimal notation) Hough transform data ρ for each pixel is stored in ROM, and as shown in Figure 5, the coordinates of each given pixel are A pair of x registers 69a and 6 that generate address information for reading out the stored Hough transform data ρ based on the values x and y.
9b and y register 69c, 42 θ for each pixel
A θ counter 69d that generates address information, the registers 69a, 69b, 69c, and a Hough transform data memory 69d that stores the Hough transform data ρ based on the address information generated by the θ counter 69d. It consists of an address decoder 69e that generates address information. Then, 42 pieces of Hough transform data ρ for each given pixel coordinate value x, y are transferred to the θ counter 69d.
The configuration is such that it is directly output to the Hough transform section 40 as a Hough transform result together with the information on the angle θ generated in .

Next, the operation of the differential processing section 20 will be briefly explained.

The video signal _S0 , which is the original image information from the camera 3, is transmitted directly through the A/D converter 10 consisting of a video amplifier 10a and an A/D converter 10b, or after 90 degree coordinate transformation, the video signal S0 is converted into the image. As image information stored in the memory 11, 32 x 32 pixels, 8 pixels per pixel, are input via the input format switch 12.
The data is input to the differential processing section 20 as digital image data _F1 expressed in bit length.

Then, one raster (all 32 pixels of all x coordinates for one y coordinate) of image data F ₁ is sequentially obtained from left to right with the upper left of the imaging field of camera 3 as the origin.
While importing 32 rasters (y coordinates of 32 elements), the process of calculating the differential value for each pixel is performed. This differential processing calculates the differential value in the left-right direction (x-axis direction) for each pixel based on the brightness of the pixel, and calculates the directionality and magnitude of the change in brightness of all image information. , it becomes possible to extract the edges of the change from dark to bright in the image.

Next, based on the block diagram shown in FIG. 6, a binarization processing unit 30 that binarizes the image information converted into 8-bit/pixel edge image data _F2 by the differential processing unit 20, and a Hough transform part 40, and
The configuration and operation of the boundary parameter calculation section 50 will be explained.

That is, the entire operation is controlled by the input/output controller 42 so that the entire operation is performed in synchronization with the operation of the differential processing section 20 based on the control signal from the control section 60 inputted via the bus buffer 41. It is configured so that

The edge image data _F2 is input to the comparator 31 of the binarization processing unit 30 via the data buffer 43a, and is compared with a set threshold value (Fref) input via the buffer 32, and portions with large brightness changes are identified. Binarized. This binary image data
F ₃ is input to the comparator 51 of the boundary parameter calculation section 50 via a data buffer 43b connected to a data bus (BUS ₃ ), and is also stored in the binarized image data memory 33a.

In the Hough transform unit 40, the value of the Hough transform data ρ given from the LUT 69 via the data buffer 43c is the frequency number D of angles θ at which the values are the same.
is counted by a frequency counter 44, and the result is stored in a two-dimensional histogram frequency memory 45, thereby forming a counting means.

The frequency D counted by the frequency counter 44
is added to the contents of the same address position in the frequency memory 45 via the data buffer 43d, and a boundary parameter calculation unit 50 specifies the boundary by detecting its maximum value (Dmax).
The value is transferred to the maximum value register 52a, and compared with the value stored in the maximum value register 52a by the comparator 51, and the larger frequency is re-stored as the new maximum value (Dmax). The address of the frequency memory 45 for the frequency D that is the maximum value (Dmax) is stored in the maximum value address register 52.
b at the same time, and after completing the Hough transform for all 32×32 pixels, the coefficients a and b of the above formula (i) are calculated from the Hough transform data ρ and angle θ that have reached the maximum value (Dma).
I'm trying to find out. Also, in Figure 6, 33b
33c is an image memory that stores the digitized image data _F1 , 33c is an image memory that stores the edge image data _F2 , and the video RAM 34 and
Images in each processing state can be displayed on the monitor television 15 via the CRT controller 14.

The coefficients a and b of the equation (i) obtained are the input/output controller 42 and the bus buffer 41.
is sent to the control unit 60 via the boundaries L ₁ , L ₂
It is used as data for determining the presence or absence of a substance and for subsequent processing.

[Another example]

In the above embodiment, the boundary L ₂ in the longitudinal direction of the aircraft V
The differential processing unit 20
The coordinates of the input image information are converted by 90 degrees and 90
However, each time one screen's worth of image information is processed, the coordinates of the input image are converted 90 degrees, and the boundary _L1 in the width direction of the aircraft V is detected. Detection of the boundary _L2 in the V front and rear directions may be repeated alternately. In that case, if you alternately input the coordinates transformed and the coordinates not transformed for each field of the image captured by the camera 3, the necessary information can be obtained for each frame at the same time, and the imaging processing for one screen can be performed. Image information for detecting boundaries L ₁ and L ₂ in different directions between the two can be obtained.

Alternatively, the aircraft V is provided with means for detecting the travel distance information, and based on the detected travel distance information and the scheduled travel distance information for one stroke, the aircraft V is adjusted in the longitudinal direction depending on whether or not it has reached the vicinity of the end of the stroke. boundary of
It is also possible to switch to _L2 detection processing.

In addition, in the above embodiment, the formula for Hough transform processing ()
In , the angle change is processed between 60 degrees ≦ θ < 10 degrees, but due to the positional relationship between the boundaries L ₁ and L ₂ and the aircraft V, the directions of the boundaries L ₁ and L ₂ are significantly different from the aircraft V traveling direction. Therefore, by limiting the angular range in which the Hough transform is performed to a narrower range than the above-mentioned 60 degrees to 120 degrees, the resolution of the Hough transform processing can be increased without reducing the Hough transform processing speed. By increasing the accuracy or processing only a narrower specific range, the processing speed can be further improved and the influence of noise can be effectively removed.

In addition, in the above embodiment, the captured image information is 32×32
It was sampled into pixels, but if necessary, it can be made even more finely.
Alternatively, it may be roughly sampled.

In addition, to determine the positional relationship between the boundaries L ₁ and L ₂ and the aircraft V, in addition to using the reference line L ₀ that vertically traverses the imaging field of view as exemplified in the above embodiment, the lower and upper ends of the imaging field of view are used as a reference. Any reference may be used, such as the center, the center, or the coordinate origin position of the image information.

[Brief explanation of the drawing]

The drawings show an embodiment of the boundary detection device for an automatic traveling work vehicle according to the present invention, and FIG. 1 is a block diagram showing the configuration of the boundary detection device, FIG. 2 is a flowchart showing its overall operation, and FIG. FIG. 3 is a block diagram showing the configuration of the control section, FIG. 4 is an explanatory diagram of a table storing data for Hough transformation, FIG. 5 is a block diagram showing the configuration of a data memory for Hough transformation, and FIG. A block diagram showing the configuration of the conversion section, FIG. 7 is a schematic plan view of the lawn mowing vehicle, and FIG. 8 is a side view thereof.
FIG. 9 is a block diagram showing the overall configuration of the control system for the lawn mowing vehicle. 3... Imaging means, 20... Differential processing means, 30
...Binarization means, 40...Hough transformation means, 50...
... Boundary parameter calculation means, 69 ... Hough transform data storage means, S ₀ ... Captured image information, F ₂ ...
Edge image information, F ₃ ...Binarized image information, B...
...Untreated working area, C... Treated working area, L ₁ , L ₂
...boundary, x, y...coordinates, ρ...data for Hough transformation, D...frequency.

Claims (1)

[Claims] 1 Image information (S _p ) captured by the imaging means 3 that captures images of the working area state in a predetermined range on the forward side in the direction of movement of the aircraft
a differential processing means 20 that converts the edge image information (F ₂ ) into edge image information (F 2 ) based on a change in brightness; a binarization means 30 that binarizes the edge image information (F ₂ ) based on a set threshold; and a binarized image thereof. A Hough transform means 40 that processes the information F ₃ through Hough transform, and calculates the positional relationship of the vehicle body V with respect to the boundaries L ₁ and L ₂ between the unprocessed work area B and the processed work area C based on the Hough transform processing result. A boundary detection device for an automatic traveling work vehicle is provided with a boundary parameter calculating means 50, and the Hough transform means 40 is configured to correspond to the coordinate values X and Y of each pixel, and which corresponds to the boundary L ₁ , _L2 , Hough transformation data ρ within a set angle range narrower than the range of +90 degrees to -90 degrees with respect to the extension direction of L2 is provided. Directly reading out the tabulated Hough transform data ρ corresponding to the value of Y, and determining the data with the highest reading frequency D as the information corresponding to the boundaries L ₁ and L ₂ . A boundary detection device for an automatic traveling work vehicle, which is provided with a counting means for counting the read frequency D.