JPH11248431A - Three-dimensional model generation device and computer-readable recording medium storing three-dimensional model generation program - Google Patents

Abstract

PROBLEM TO BE SOLVED: To easily extract feature points from a two-dimensional image taken by a camera and generate an accurate three-dimensional model without a plurality of cameras, by acquiring depth information corresponding to a two-dimensional dot array drawn by an operator on a device coordinate system. SOLUTION: Feature points of an object shown on a display 5 are traced by a pen on a digitizer every line segment to send coordinates corresponding to designated pixels in the designating order to a generator 4 from a designator 3, camera parameters are sent from a digital camera to the generator 4, the topology of the two-dimensional segments is extracted, based on the received coordinates, coordinates of the intersection of the same segments are sampled in a memory 6, and the depth information corresponding to the sampling coordinates is obtained from a configuration chart and processed to obtain normalized coordinates which are converted in modeling coordinates. Drawing the contour line of a three-dimensional body 6 to be extracted from a two-dimensional image taken by the camera facilitates extracting feature points and also forming a three-dimensional model.

Description

DETAILED DESCRIPTION OF THE INVENTION

[0001]

BACKGROUND OF THE INVENTION 1. Field of the Invention The present invention relates to a three-dimensional model generating apparatus for generating a three-dimensional model of an object based on an image having depth information. The present invention relates to a three-dimensional model generation device that interactively generates a three-dimensional model of the object.

[0002]

2. Description of the Related Art Conventionally, there has been known a method of generating a three-dimensional model in a non-contact manner by processing a two-dimensional image obtained by capturing an object with a digital camera or the like, and is often used in computer vision research. In particular, the stereo method is based on the principle of triangulation and is a method of measuring a target object from a plurality of original parallax images obtained by imaging the target object from different positions. This method requires a process (matching) of extracting a feature point such as a contour of a target object from a certain original image to find a corresponding position in another original image.

Further, a three-dimensional image measuring apparatus capable of determining corresponding points of a plurality of original parallax images at a time without performing feature point extraction processing is disclosed in Japanese Patent Application Laid-Open No. Hei 5-272943. This three-dimensional image measurement apparatus creates a continuous stereo image of an object from a plurality of original parallax images obtained by imaging the object from different positions, and performs only a Fourier transform and filtering of a gradient component in a frequency space. By performing the processing and the inverse Fourier transform for extracting an image of only a certain depth, three-dimensional voxel data is configured.

In addition, while an image of an object is taken by a CCD camera, the object is irradiated with a laser beam, and the reflected light of the object is converted to C light.
A three-dimensional measuring device that obtains depth information of an object based on the principle of triangulation by receiving light with a CD camera is commercially available.
According to the three-dimensional measuring device, depth information can be obtained for each pixel of the CCD camera.

[0005]

However, the extraction of feature points in the conventional stereo method is a process performed to simplify the determination of corresponding points in another parallax original image.
It may be difficult to extract an appropriate feature point due to the brightness and complexity of the original image.

Further, in matching, it is difficult to find an appropriate correspondence between the original parallax images depending on a captured image such as a case where a change in contrast is small or a case where an object has a curved surface. In such a case, since a three-dimensional model may be generated by measuring an object at an incorrect corresponding point, a three-dimensional model cannot be reliably generated. In addition, even if feature points can be extracted and matched, they can be obtained as a set of point data in a three-dimensional space. Therefore, when generating a three-dimensional model using lines, the three-dimensional topology of line segments (which points and which points) However, it is difficult to determine the relationship between the two.

In the three-dimensional image measuring apparatus disclosed in Japanese Patent Laid-Open No. 5-272943, a plurality of parallax original images are required, and it is necessary to prepare the same number of cameras as the required number of parallax original images. . This increases costs. In addition, a plurality of original parallax images can be captured by moving one camera, but in this case, since the optical axis of the camera had to always move on a straight line in a state perpendicular to the moving direction, the control was performed. There is a drawback that it is difficult.

In a commercially available three-dimensional measuring device, a method of measuring the size of an object obtained from a two-dimensional image picked up by a CCD camera and depth information of the object obtained for each pixel of the CCD camera Therefore, it has been difficult to generate a three-dimensional model whose scale is matched. This three-dimensional measuring device will be described with reference to FIGS.

FIG. 7 is a diagram showing a state in which an image of an object captured by a digital camera is displayed on a liquid crystal display. FIG. 8 shows depth information for each pixel of a CCD camera measured using reflected light of a laser beam. Here, the number of pixels of the CCD camera and the number of pixels of the liquid crystal display are the same. From the image shown in FIG. 7 and FIG. 8, the line segment AB (L1) has six pixels, the line segment AC (L2) has six pixels, and the line segment AD (L5) has three pixels. The depth information is obtained for each pixel as a value normalized within the range of 0 to 1 as shown in FIG. 8, where point A is 0.5, point B is 0.5, point C is 0.5, and point C is 0.5. D is obtained as 0.8.
This indicates that points A, B, and C are at the same distance from the CCD camera and are in the same plane. Further, since the depth information of all points on the line segment AB and the line segment AC is 0.5 and the same, they exist on the same plane perpendicular to the line of sight. This means that the line segment AB and the line segment AC exist on the same plane perpendicular to the line of sight and have the same number of pixels, so that it can be determined that they have the same length.

However, since the depth information of the point D is 0.8, how large the line segment AD is is
I can't tell if it's longer or shorter. This is because the scale differs between the depth information and the length on the plane shown in FIG.

[0011]

SUMMARY OF THE INVENTION The present invention has been made to solve the above-mentioned problems, and has as its object to easily generate a three-dimensional model using feature points extracted from a two-dimensional image. And

Another object of the present invention is to generate an accurate three-dimensional model in which the scale for each dimension is matched.

Another object of the present invention is to easily extract feature points from a two-dimensional image captured by one camera without using a plurality of cameras.

Another object of the present invention is to accurately determine the topology of a three-dimensional sequence of points.

According to an aspect of the present invention, there is provided a three-dimensional model generating apparatus for generating a three-dimensional model by measuring an object in a non-contact manner. A three-dimensional model is generated from the drawn two-dimensional point sequence and depth information corresponding to the two-dimensional point sequence.

According to the present invention, it is possible to provide a three-dimensional model generating apparatus capable of easily generating a three-dimensional model using feature points extracted from a two-dimensional image.

More preferably, the three-dimensional model is generated by first calculating means for calculating normalized coordinates of a point sequence from a two-dimensional point sequence and depth information corresponding to the two-dimensional point sequence, And a second calculating means for calculating modeling coordinates from the converted coordinates.

According to the present invention, it is possible to provide a three-dimensional model generating apparatus capable of generating an accurate three-dimensional model in which the scale for each dimension is matched.

[0019] More preferably, the three-dimensional model generating device includes: an image pickup unit for picking up an object of the three-dimensional model; a display unit for displaying an image picked up by the image pickup unit on a device coordinate system; The image processing apparatus further includes an instructing unit for instructing a two-dimensional point sequence with respect to the image displayed in the device coordinate system, and a depth information acquiring unit for acquiring depth information corresponding to the instructed two-dimensional point sequence.

According to the present invention, it is possible to provide a three-dimensional model generation apparatus capable of easily extracting feature points from a two-dimensional image picked up by one camera without using a plurality of cameras. Become.

[0021] More preferably, the three-dimensional model generating device extracts a topology of a two-dimensional point sequence, and extracts a topology of the three-dimensional point sequence based on the extracted topology of the two-dimensional point sequence. A second extraction unit.

According to the present invention, it is possible to provide a three-dimensional model generation device that can further accurately determine the topology of a three-dimensional point sequence.

According to another aspect of the present invention, a step of inputting a two-dimensional point sequence drawn by an operator into the device coordinate system, a step of inputting depth information corresponding to the two-dimensional point sequence, Generating a three-dimensional model from the columns and the depth information.

According to the present invention, it is possible to provide a recording medium which records a program capable of easily generating a three-dimensional model by a computer using feature points extracted from a two-dimensional image.

According to another aspect of the present invention, a step of inputting a two-dimensional point sequence drawn by an operator into the device coordinate system, a step of inputting depth information corresponding to the two-dimensional point sequence, Extracting a column topology, calculating modeling coordinates from the two-dimensional point sequence and depth information, extracting a three-dimensional point sequence topology based on the extracted two-dimensional point sequence topology, and calculating Generating a three-dimensional model from the obtained modeling coordinates and the topology of the extracted three-dimensional point sequence.

According to the present invention, a program is recorded which enables a computer to easily generate a three-dimensional model in which the topology of a three-dimensional point sequence is accurate using feature points extracted from a two-dimensional image. It is possible to provide a recording medium.

[0027]

FIG. 1 is a block diagram showing a configuration of a three-dimensional model generating apparatus according to one embodiment of the present invention. Referring to the figure, a three-dimensional model generation device includes an imaging unit 1 including a digital camera, a depth information acquisition unit 2 that acquires depth information of an object for each pixel of the imaging unit 1, and a feature point coordinate. An instructing unit 3 for instructing, a generating unit 4 for generating a three-dimensional model from feature point coordinates and corresponding depth information, a display unit 5 for displaying an image captured by the imaging unit 1, and a storage unit 6. Be composed.

FIG. 2 is a flowchart showing a process of generating a three-dimensional model performed by the three-dimensional model generating device of FIG. Referring to the figure, an image having depth information is input in step s0. In step s1, a two-dimensional line segment is input. In step s2, the camera parameters output from the imaging unit 1 are input to the generation unit 4. Steps
At 3, the topology of the two-dimensional line segment input by the instruction unit 3 is extracted. In step s4, two-dimensional line segments are sampled. In step s5, the value of Zs for the two-dimensional coordinates is obtained. In step s6, a three-dimensional line segment is generated. Next, the processing performed in each step of FIG. 2 will be described in detail.

[Step s0] The three-dimensional model is generated by
First, an image having depth information is input. The image having the depth information is obtained from a two-dimensional image obtained by imaging the object to be generated in the three-dimensional model by the imaging unit 1 and the depth information acquired for each pixel of the imaging unit 1 by the depth information acquisition unit 2. Become.

The depth information is acquired by the principle of triangulation by irradiating the object with a laser beam, receiving the reflected light by the imaging unit 1 and processing it by the depth information acquisition unit 2. This depth information sets the position of the frontmost (imaging unit side) surface (front surface) at which the imaging unit 1 can image to 0.0, in order to cope with the difference in the imaging environment such as the imaging distance and the focal length. The position of the rearmost direction (rear surface) was set to 1.0. It is a real number normalized to the range of 0.0 to 1.0.

FIG. 3 shows an array of depth information. The depth information Z _ij (0 ≦ i ≦ n, 0 ≦ j ≦ m) of the n × m array corresponds to the array of pixels of the imaging unit 1. Note that the depth information does not need to be acquired for each pixel of the imaging unit 1, and rough processing may be performed such that a plurality of neighboring pixels are collectively collected to acquire one piece of depth information.

The two-dimensional image picked up by the image pickup unit 1 and the depth information obtained by the depth information obtaining unit 2 are sent to the generation unit 4, and the two-dimensional image is displayed on the display unit 5.

[Step s1] Next, input of a two-dimensional line segment is performed by the instruction unit 3. This corresponds to an operation in which the operator looks at the two-dimensional image displayed on the display unit 5 and inputs a feature point. The instruction unit 3 includes a digitizer made of a transparent member provided on the display unit 5 and a pointing device. When the operator designates a desired position on the digitizer with the pointing device, the position of the pixel on the display unit 5 corresponding to the designated position is output to the generation unit 4 as designated coordinates in the device coordinate system. When entering a line,
When the pointing device is designated on the digitizer, a start point signal is output to the generation unit. While the pointing device is moved on the digitizer, the position of the pixel of the two-dimensional image corresponding to the designated position is designated by the designated coordinates in the device coordinate system. And an end point signal is output when the pointing device is separated from the digitizer. As a result, the generation unit 4 recognizes a set of designated coordinates received between the reception of the start point signal and the reception of the end point signal as a two-dimensional point sequence. And which coordinates are connected). Therefore, the line is recognized as a set of designated coordinates (two-dimensional point sequence).

FIG. 4 shows the relationship between the line segment recognized by the output of the instruction unit 3 and the coordinates forming the line segment. The number of line segments is s, and L1, L2, L3, and Ls represent names of straight lines (group). P1 indicates the designated coordinates of the start point, Pr indicates the designated coordinates of the end point, and P2 indicates the designated coordinates between them, and the topology between the designated coordinates can be known from the order of the designated coordinates. In the device coordinate system, the origin is at the lower left, the X coordinate is at the right, and the positive direction is Y at the top. Each device coordinate has one-to-one correspondence with n × m pixels of the imaging unit 1. Therefore, X is an integer value of 1 to m, and Y is 1
It is an integer value not less than n and not more than n.

Although the instructing unit 3 is composed of a digitizer and a pointing device, the mouse pointer is moved to the display unit 5 by operating the mouse, so that a desired image on the two-dimensional image displayed on the display unit 5 is displayed. By clicking the position of the pixel with a mouse, the designated coordinates in the device coordinate system may be output to the generation unit 4. In this case, if the input of the line segment is such that the start point signal is output at the start of the drag and the end signal is output at the end of the drag, the group is generated by the generation unit 4 in the same manner as in the case where the pointing device and the digitizer are used. Can be recognized.

[Step s2] Next, the camera parameters output from the imaging unit 1 are input to the generation unit 4. Here, the camera parameters will be described with reference to FIG.

The Xv axis, the Yv axis, and the Zv axis indicate a modeling coordinate system. The imaging unit 1 is placed at its origin in the positive direction of the Zv axis. The camera parameters are set in the imaging unit 1
Are the actual measurement values when the image is taken at
Zv value f of rear surface 12, projection surface (same surface as front surface) 1
1 is a height h from the Zv axis. Here, the front surface refers to the forefront (imaging unit side) surface that can be imaged by the imaging unit 1, the rear surface refers to the rearmost surface, and the projection surface refers to the front surface and the rear surface. It refers to the surface on which the intermediate object is projected as an image. Here, the position of the projection surface is set to be the same as the front surface for the sake of simplicity.

In the three-dimensional model generating apparatus according to the present embodiment, the steps from step s0 to step s2 are omitted, and the processing of these steps is performed by another apparatus. To input depth information and camera parameters. In this case, the apparatus can be configured by omitting the imaging unit 1, the depth information acquisition unit 2, the instruction unit 3, and the display unit 5 shown in FIG.

[Step s3] When the camera parameters are input to the generation unit 4, the topology of the two-dimensional line segment input by the instruction unit 3 is extracted. The topology of a two-dimensional line segment refers to a relationship in which one two-dimensional line segment is connected to another two-dimensional line segment, and coordinates at which the two-dimensional line segments intersect are obtained by extracting the topology.

The s two-dimensional line segments shown in FIG.
Extraction of topology between two-dimensional line segments when input
Will be described. The line segments (L1 to L
The same coordinates are extracted from the coordinates that constitute s), and are described.
It is stored in the storage unit 6. The extracted coordinates intersect the line segment
Indicates the coordinates. For example, the coordinates (X
₁₁, Y₁₁) And the coordinates (X₃₂, Y₃₂)When
Are the same coordinates (5,287), (5,28
7) is stored in the storage unit 6.

In the same manner, all the coordinates constituting the line segment (L1 to Ls) are checked for the identity, and the same coordinates are stored in the storage unit 6.

The result of extracting the topology of the two-dimensional line segment is
This is used for sampling a two-dimensional line segment described below.

[Step s4] After the topology of the two-dimensional line segment is extracted, sampling of the two-dimensional line segment is performed. The sampling of the two-dimensional line segment is a process of thinning out the coordinates constituting the two-dimensional line segment input by the instruction unit 3. The number of coordinates constituting the two-dimensional line segment can be reduced by the sampling, and the calculation load of the subsequent processing can be reduced. This is particularly effective when the two-dimensional line segment is a straight line. Of course, this processing may not be performed.

The sampling of the two-dimensional line segment is performed based on the coordinates of the start point and the end point of the coordinates constituting the two-dimensional line segment input by the instruction unit 3 and the coordinates stored in the storage unit 6. Are sampled with priority. The coordinates stored in the storage unit 6 indicate coordinates where two-dimensional line segments intersect. As for other coordinates, coordinates outside the range of the sampling width from the sampled coordinates are sampled. For example, for the 2-dimensional line segment L1, first the start point coordinates P1 (X _11, Y ₁₁₎ are sampled and separated following coordinates P2 (X _12, Y ₁₂₎ is much the coordinates P1 (X _11, Y ₁₁₎ Is determined. If the sampling width is 2 in both the vertical and horizontal directions, the coordinate P1
If (X ₁₁ , Y ₁₁ ) and coordinates P2 (X ₁₂ , Y ₁₂ ) are separated by 2 or more in both the vertical and horizontal directions, (| X ₁₂ −X ₁₁ | ≧ 2
AND | Y ₁₂ −Y ₁₁ | ≧ 2), coordinates P2 (X ₁₂ ,
Y ₁₂ ) is sampled, and the next coordinate P3 (X ₁₃ , Y
₁₃₎ how far the coordinates P2 (X _12, Y ₁₂₎ is determined.

The coordinates P1 (X ₁₁ , Y ₁₁ ) and the coordinates P2
If (X ₁₂ , Y ₁₂ ) is not separated by 2 or more in both the vertical and horizontal directions, (| X ₁₂ −X ₁₁ | <2 OR | Y ₁₂ −Y ₁₁ |
<2), the coordinates P2 (X _12, Y ₁₂₎ is not sampled, the next coordinates P3 (X _13, Y ₁₃₎ are the coordinates P1 (X _11, Y
_It is judged how far away from ₁₁ ).

This process is repeated up to the end point coordinates Pr (X _1r , Y _1r ). However, the coordinates and the end point coordinates stored in the storage unit 6 are always sampled regardless of whether they are out of the range of the sampling width. Hereinafter, it is assumed that all coordinates are sampled for the sake of simplicity.

[Step s5] Next, the value of Zs for the two-dimensional coordinates is determined. The depth information Zs of the image corresponding to the coordinates sampled in the sampling of the two-dimensional line segment (step s4) is obtained from the array of depth information (FIG. 3). For example, if the sampled coordinates are (i, j)
Zs is the Z _ij where is.

[Step s6] Next, a three-dimensional line segment is generated. The generation of a three-dimensional line segment includes a process of obtaining normalized coordinates from coordinates forming a two-dimensional line segment and depth information of an image, and a process of converting the normalized coordinates into modeling coordinates. In the process of obtaining the normalized coordinates, the X and Y coordinates of the coordinates (X _d , Y _d ) constituting the two-dimensional line segment are normalized to a range of −1.0 or more and 1.0 or less. The coordinates (Xs, Ys, Zs) are obtained. Normalized coordinates Xs coordinate X _d in the following equation (1), the normalized coordinates Ys coordinate Y _d is determined by the following equation (2). Where X _dmax and Y
_dmax refers to the maximum value that X _d and Y _d can take. In the case of the present embodiment, since it is an array of n × m pixels, X _dmax =
m, Y _dmax = n. The range of Zn is shown by equation (3).

[0049]

(Equation 1)

Next, a process of converting the normalized coordinates into the modeling coordinates is performed. The following equations (4), (5), and (6) are derived from the relationship between the normalized coordinates and the modeling coordinates.

[0051]

(Equation 2)

The following equations are obtained by modifying the equations (4), (5) and (6).

[0053]

(Equation 3)

From the equations (7), (8) and (9), the normalized coordinates (Xs, Ys, Zs) are converted into the modeling coordinates (Xv, Yv,
Zv). Here, d, f, and h are the camera parameters described above. In order for the expressions (7), (8), and (9) to hold, the front surface 11 and the rear surface 12 are not on the same plane (d 平面 f) and do not include the origin of the modeling coordinates (d (≠ 0 AND f ≠ 0) is a condition.

If the process of obtaining the normalized coordinates and the process of converting the coordinates into the modeling coordinates are performed for all the coordinates sampled in the sampling of the two-dimensional line (step s4), as shown in FIG. The three-dimensional coordinates constituting each line segment and the topology between the three-dimensional coordinates are obtained. Then, the result of the processing is stored in the storage unit 6.

Next, a specific example of the above processing will be described. FIG. 7 shows a case where an object imaged by a digital camera is displayed on a liquid crystal display. FIG. 8 shows an array of depth information acquired by the depth information acquisition unit, and each frame corresponds to a pixel. A transparent digitizer is provided on the liquid crystal display, and when an instruction is given with a pen, it is possible to know which pixel of the liquid crystal display has been designated. FIG. 9 shows a case where the operator traces a feature point of an object displayed on the display with a pen. L1
L9 indicates a line segment that is a feature of the object. In this embodiment, since the pen traces the digitizer for each line segment, the starting point signal and the designated coordinates are set when the pen is hit on the digitizer, the designated coordinates are set when the pen is moved, and the end point signal is set when the pen is released. Coordinates are given for each line segment. Thus, the coordinates corresponding to the pixel designated by the pen from the digitizer are sent from the designation unit 3 to the generation unit 4 in the designated order.

Next, the camera parameters are sent from the digital camera to the generator 4. Here, the camera parameters are d = 10.0, f = 20.0, and h = 5.0.

The generation unit 4 extracts the topology of the two-dimensional line segment based on the received coordinates, stores the same coordinates, that is, the coordinates where the line segments intersect, in the storage unit 6, and then performs sampling. . Here, the sampling width is set to 2 in both the vertical and horizontal directions. FIG. 10 shows the relationship between sample coordinates sampled as a result of sampling and line segments.

FIG. 11 shows identification points C1 to C16 of the sampled coordinates at which point the sampled coordinates are located in the device coordinates. Further, FIG. 12 shows the X-coordinate X _d and Y-coordinate Y _d are denoted by the identification number C1~C16 the sampled coordinates.

Next, depth information Zs corresponding to the sampling coordinates is obtained from the array of depth information (FIG. 8). Then, processing for obtaining the normalized coordinates is performed. The device coordinates (X _d , Y _d ) of the sampled coordinates shown in FIG. 12 are normalized by the equations (1) and (2) to obtain the normalized coordinates (Xs, Ys, Zs) shown in FIG. Here, since the pixel array is 10 × 10, X _dmax = 10 and Y _dmax = 10.

Then, the normalized coordinates are expressed by (7), (8) and (9).
Convert to modeling coordinates by formula. The result is shown in FIG.
Shown in The relationship between the obtained modeling coordinates (C1 to C16) and the line segments (L1 to L9) is as shown in FIG.

By drawing the outline of the three-dimensional object to be extracted from the two-dimensional image captured by the camera as described above,
The feature points can be easily extracted, and a three-dimensional model can be easily created from the extracted feature points and depth information.

In the present embodiment, the case where a line segment is input by the instruction unit 3 has been described.
Needless to say, the same can be applied to the case where the information is input as dimensional information.

Further, in the present embodiment, the three-dimensional model generating apparatus having the configuration shown in FIG. 1 is used. However, a program capable of causing a computer to execute the processing shown in FIG. 2 is recorded on a recording medium (CD-ROM, (A floppy disk or the like), and may be executed by a computer.

[Brief description of the drawings]

FIG. 1 is a block diagram illustrating a functional configuration of a three-dimensional model generation device according to an embodiment of the present invention.

FIG. 2 is a flowchart showing a flow of processing of generating a three-dimensional model according to one of the embodiments of the present invention.

FIG. 3 is a diagram showing an array of depth information according to one of the embodiments of the present invention.

FIG. 4 is a diagram showing a relationship between a two-dimensional line segment and coordinates forming the line segment according to one of the embodiments of the present invention.

FIG. 5 is a diagram for explaining a relationship between a modeling coordinate system and camera parameters according to one embodiment of the present invention.

FIG. 6 is a diagram illustrating a relationship between a three-dimensional line segment and coordinates forming the line segment according to one of the embodiments of the present invention.

FIG. 7 is a diagram showing a state in which a captured image is displayed on a liquid crystal display according to one of the embodiments of the present invention.

FIG. 8 is a diagram for explaining a relationship between an array of depth information and a designated line segment according to one of the embodiments of the present invention.

FIG. 9 is a diagram illustrating a state in which a feature point is designated with a pen according to one of the embodiments of the present invention.

FIG. 10 is a diagram showing a relationship between a line segment and sampling coordinates according to one embodiment of the present invention.

FIG. 11 is a diagram showing positions of sampling coordinates in device coordinates according to one of the embodiments of the present invention.

FIG. 12 is a diagram showing sampling coordinates according to one of the embodiments of the present invention.

FIG. 13 is a diagram showing normalized coordinates according to one of the embodiments of the present invention.

FIG. 14 is a diagram illustrating a result of conversion into modeling coordinates according to one of the embodiments of the present invention.

FIG. 15 is a diagram showing a relationship between a line segment and modeling coordinates according to one of the embodiments of the present invention.

[Explanation of symbols]

 REFERENCE SIGNS LIST 1 imaging unit 2 depth information acquisition unit 3 instruction unit 4 generation unit 5 display unit 6 storage unit 11 front surface, projection surface 12 rear surface

Claims (6)

[Claims] An apparatus for generating a three-dimensional model by measuring an object in a non-contact manner, comprising: a two-dimensional point sequence drawn by an operator in a device coordinate system; A three-dimensional model generation device for generating a three-dimensional model from corresponding depth information. 2. The generation of the three-dimensional model includes: first calculating means for calculating normalized coordinates of the point sequence from the two-dimensional point sequence and depth information corresponding to the two-dimensional point sequence; 2. The method according to claim 1, wherein the second calculation unit calculates modeling coordinates from the normalized coordinates.
Dimensional model generator. 3. An image pickup unit for picking up an object of a three-dimensional model, a display unit for displaying an image picked up by the image pickup unit on a device coordinate system, and an operator displayed on the device coordinate system. 3. The apparatus according to claim 1, further comprising: an instruction unit configured to instruct a two-dimensional point sequence with respect to the image; and a depth information acquisition unit configured to acquire depth information corresponding to the designated two-dimensional point sequence. 3D model generation device. 4. A first extracting means for extracting a topology of the two-dimensional point sequence, and a second extracting means for extracting a topology of a three-dimensional point sequence based on the extracted topology of the two-dimensional point sequence. The three-dimensional model generation device according to any one of claims 1 to 3, further comprising: 5. A step of inputting a two-dimensional point sequence drawn by an operator into a device coordinate system; a step of inputting depth information corresponding to the two-dimensional point sequence; the two-dimensional point sequence and the depth information And a step of generating a three-dimensional model from the above. 6. A step of inputting a two-dimensional point sequence drawn by an operator into a device coordinate system; a step of inputting depth information corresponding to the two-dimensional point sequence; and extracting a topology of the two-dimensional point sequence. Calculating the modeling coordinates from the two-dimensional point sequence and the depth information; extracting the three-dimensional point sequence topology based on the extracted two-dimensional point sequence topology; A computer-readable recording medium storing a program for causing a computer to execute a step of generating a three-dimensional model from the modeling coordinates and the topology of the extracted three-dimensional point sequence.