JP2005251122A - Image processor and image processing method - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To solve the problem that the accuracy of ranging in an equiluminous line stereo method is apt to deteriorate according as a distance to a target object is made longer. <P>SOLUTION: An image acquiring part 204 acquires a reference image and a comparison image obtained by picking up the image of an object from different angles. An equiluminous line extracting part 212 extracts an equiluminous line from the comparison image. An epipolar line extracting part 214 extracts an epipolar line from the comparison image in accordance with a predetermined reference pixel in the reference image. A corresponding pixel specifying part 222 specifies a corresponding pixel corresponding to reference pixel from the comparison image based on the intersection of the equiluminous line corresponding to the luminance value in the reference pixel and the epipolar line. A corresponding point specifying part 224 specifies the coordinates of the corresponding point having a luminance value which is almost equivalent to that of the reference pixel based on the luminance value in the corresponding pixel. A ranging part 208 measures a distance to the object based on the coordinates of the reference pixel and the coordinates of the corresponding point. <P>COPYRIGHT: (C)2005,JPO&NCIPI

Description

  The present invention relates to a three-dimensional measurement technique using a stereo image, and more particularly to a technique for three-dimensional measurement based on luminance information of an image.

  The ground for handling three-dimensional digital contents is getting better with the improvement of computer image expression and broadband network. In such an era background, there is a demand for a technique for converting external information sensed by vision into three-dimensional image data. For this purpose, it is important to establish a technique for accurately measuring a target object in three dimensions.

  Three-dimensional measurement technology, which is a technology for measuring the distance to the target object and its shape, is roughly classified into an active type and a passive type. An active type three-dimensional measurement apparatus projects a pattern or the like onto a target object and measures a distance to the target object (hereinafter simply referred to as “distance measurement”). As a typical example, a bright spot formed by projecting a laser beam onto a target object is captured by a camera from different angles, a spot light projection method for obtaining the three-dimensional position of the spot, slit light is projected onto the target object, There are a slit light projection method for measuring the depth on the projection line, a spatially coded pattern light projection method for projecting a plurality of pattern lights onto a target object, and characterizing the pattern by a combination of patterns.

  On the other hand, the passive type three-dimensional measuring device measures the distance by specifying the position of each predetermined point on the target object in the captured image obtained by imaging the target object from different angles. That is, the passive type three-dimensional measurement apparatus does not project a design pattern or the like that should be a mark for distance measurement onto the target object. Therefore, the passive type has an advantage that the color information of the target object surface can be acquired more accurately than the active type. On the other hand, in the passive type, processing for specifying the position of the predetermined point on the captured image by analyzing the captured image is necessary. One of the three-dimensional measurement techniques classified as passive is a method based on the detection of isoluminance lines (hereinafter referred to as “isoluminance line stereo method”).

In the equiluminance line stereo method, each pixel of a captured image is classified into a quantized luminance range according to its luminance value. The boundary line for each luminance range is extracted as an isoluminance line. With respect to a predetermined point on the surface of the target object, it is considered that the luminance values of the two points captured on the reference image and the comparative image obtained by capturing the target object from different angles are usually equal. The three-dimensional measuring apparatus based on the isoluminance line stereo method uses the isoluminance line information to specify the position where the predetermined point is imaged. The isoluminance stereo method is a three-dimensional measurement technology that demonstrates its superiority in the distance measurement of a target object whose luminance changes smoothly, such as human skin where features for distance measurement are difficult to extract (patented) Reference 1).
JP-A-5-34117

  The conventional isoluminance line stereo method extracts isoluminance lines based on the luminance value of each pixel. Therefore, the distance measurement accuracy depends on the resolution of the captured image. For this reason, the conventional isoluminance line stereo method has a problem that the distance measurement accuracy tends to deteriorate as the distance to the target object increases.

  The present invention has been made in view of such problems, and an object of the present invention is to provide a three-dimensional measurement technique for accurately measuring the distance to the target object based on the isoluminance line stereo method. is there.

  In order to solve the above problems, an image processing apparatus according to an aspect of the present invention first acquires a reference image and a comparative image obtained by imaging an object from different angles. This apparatus extracts isoluminance lines from the comparison image, and extracts epipolar lines from the comparison image corresponding to predetermined reference pixels in the reference image. Then, the corresponding pixel corresponding to the reference pixel is identified from the comparison image based on the intersection of the isoluminance line corresponding to the luminance value in the reference pixel and the epipolar line. Furthermore, the coordinates of the corresponding point having a luminance value substantially equal to the luminance value of the reference pixel is specified based on the luminance value in the corresponding pixel. This apparatus measures the distance to the object based on the coordinates of the reference pixel and the coordinates of the corresponding point.

  According to the present invention, three-dimensional measurement can be performed more accurately based on the isoluminance line stereo method.

  First, the principle of three-dimensional measurement by the isoluminance line stereo method will be briefly described. Then, after describing the problems included in the isoluminance line stereo method, this embodiment will be described.

  FIG. 1 is a diagram for explaining the principle of distance measurement of the target object 100 based on the principle of triangulation. The point P is a point (hereinafter referred to as “target point”) that is a distance measurement target existing on the surface of the target object 100. This target point P is imaged from different angles. The reference image 102 and the comparison image 104 are the captured image planes. This figure is a diagram showing a mode in which a camera (not shown) images the target object 100 from above. The imaging focus position 106 is a position where the focus of the camera that captures the reference image 102 and the comparison image 104 exists. These cameras are arranged horizontally with respect to the target object 100. Further, the optical axis 108 and the optical axis 110 of each camera are parallel. f is a distance from the reference image 102 and the comparative image 104 to the imaging focal position 106.

The point P _L is a position where the target point P is imaged in the reference image 102. Hereinafter referred to as "reference image sensing point" that such points as the point P _L. The point O _L is a camera for capturing a reference image 102 (hereinafter, referred to as "reference image camera") is the focus of. The point P _R is the position where the object point P is imaged in the comparison image 104. Hereinafter referred to as "comparative image pickup point" that such points as the point P _R. Point O _R is a focus of the camera that captured the comparison image 104 (hereinafter, referred to as "comparative image camera").

That is, a straight line connecting the reference imaging point P _L and the focus O _L, the intersection of the straight line connecting the comparison imaging point P _R and the focus O _R interest point P. Reference image camera and the comparative image camera the distance between the optical axes of 2a, and the reference imaging point P _L parallax comparison imaging point P _R when is D, the distance Z to the object point P on the object 100,
(Equation 1)
Z = 2af / D
It is obtained as Hereinafter, comparison imaging point P _R is that it is the corresponding point of the reference imaging point P _L. Alternatively, the reference imaging point P _L is referred to as a corresponding point of comparison imaging point P _R. By measuring the distance on each point on the surface of the target object 100, the distance and shape to the target object 100 can be obtained. Here, in order to accurately measure the distance Z, it is necessary to accurately specify the corresponding point in the comparison image 104 of the reference imaging point in the reference image 102.

FIG. 2 is a schematic diagram for explaining the principle of identifying corresponding points using isoluminance lines. The figure shows a case of obtaining the comparison imaging point P _R is the corresponding point in the comparison image 104 of the reference imaging point P _L that is captured object point P of the reference image 102. Since the reference image 102 comparative image 104 is left-right horizontal epipolar lines 112 for the reference imaging point P _L is present on the same scanning line as the reference imaging point P _L. Comparative imaging point P _R is present either on the epipolar line 112. Here, the luminance value of each pixel in the reference image 102 and the comparison image 104 is classified into 256 gradations from 0 to 255. A luminance value of 0 corresponds to black, and a luminance value of 255 corresponds to white.

Pixel reference imaging point P _L is located in the drawing (hereinafter, referred to as "reference pixels") luminance value is "100". At this time, the comparison image 104 is separated into an area having a luminance value larger than “100” and an area smaller than “100”. In the figure, a region 132 is a region formed by a set of pixels having a luminance value greater than “100”. On the other hand, the region 118 is a region formed by a set of pixels having a luminance value smaller than “100”. The isoluminance line 114 is an isoluminance line with respect to the luminance value “100” that is a boundary line between the region 132 and the isoluminance line 114.

Luminance value of the comparison imaging point P _R related to the target point P is the luminance value of the reference imaging point P _L is considered equal to "100". Comparative imaging point P _R is on the equi-luminance line 114 and the epipolar line 112, i.e., considered to be on the intersection of both lines. Thus, the identified comparison image point P _R. In the reference image 102 and the comparison image 104, the optical characteristics of the respective cameras and the illumination environment at the time of imaging are not always the same. In this case, the luminance value of each pixel in both images may be adjusted so that the same luminance value is obtained for the same brightness using a gray scale test pattern. The above is the outline of the principle of the isoluminance line stereo method.

  In FIG. 1, the two cameras are arranged horizontally on the left and right with respect to the target object 100, and the optical axes of the cameras are parallel to each other. There is no need for such a camera arrangement.

Figure 3 is a schematic view showing an enlarged compared imaging point near P _R in the comparison image 104. Each square in the figure represents each pixel of the comparative image 104. The numerical value described in each pixel indicates the luminance value of that pixel. The epipolar pixel line 116 is a set of pixels in which the epipolar line 112 exists. The epipolar line 112 is a line, but is a line having a finite width represented by a set of pixels in the comparative image 104.

  In the figure, the region is divided by a set of pixels having a luminance value of “100” or more and a set of pixels smaller than “100”. This boundary line is an isoluminance line related to the luminance value “100”. Pixels indicated by diagonal lines are pixels that serve as boundaries between these two regions. The isoluminance line is theoretically a line, but is represented by a set of pixels in the comparative image 104. Hereinafter, when expressing an equiluminance line represented by a set of pixels indicated by such diagonal lines, it is particularly referred to as an “isoluminance pixel line”. In the figure, the right side of the equal luminance pixel line is a set of pixels having a luminance value of “100” or more, and the left side is a set of pixels having a luminance value smaller than “100”.

The luminance value of the pixels included in the equiluminance pixel line is not necessarily “100”. The equal luminance pixel line is a set of pixels located at the boundary between a set of pixels having a luminance value of “100” or more and a set of pixels having a luminance value smaller than “100”. In isoluminance line stereo method, a pixel located at the intersection of the equi-luminance pixel lines and epipolar pixel line 116 is specified as the corresponding point of the reference imaging point P _L. Hereinafter, the pixels specified in this way are referred to as “corresponding pixels”. In the figure, the corresponding pixel 120 corresponds to this. Then, based on the reference imaging point P _L in each of the coordinates of the corresponding pixel 120, and distance measurement target point P. However, since the luminance value of a corresponding pixel 120 is "101", the corresponding pixel 120 is likely to have occurred a drawing to their close Kano deviation from the position of the true corresponding point of the reference imaging point P _L.

FIG. 4 is a schematic diagram for explaining a state in which ranging accuracy is lowered in the isoluminance line stereo method. Luminance values of the reference pixels based imaging point P _L is present is "100". Comparative imaging point P _R is the true corresponding point of the reference imaging point P _L. That is, the comparison imaging point P _R is the corresponding point to be specified relative to the reference imaging point P _L. Luminance value of the comparison imaging point _{P R} is "100". The distance Z to the object point P is accurately measured by comparing the imaging point P _R as a reference imaging point P _L.

Point _{P R} 'corresponds to the position of a corresponding pixel 120 in FIG. The luminance value of the point _{P R} 'is "101". Standard imaging point P _L and the point P _{R 'target} point specified by the P' is. In other words, _'is calculated based on, not the distance Z to the object point P, Z' standard imaging point P _L and the point P _R so that is calculated. In this case, a true distance Z and a distance error E occur. Even small difference error d is about 1 pixel comparison imaging point P _R and the point P _{R 'in} the comparison image 104, when the distance from the imaging focal point position 106 to the object 100 is large, the distance error E growing. That is, a minute error in specifying the corresponding point in the comparison image 104 may greatly deteriorate the distance measurement accuracy. The present invention has been made to solve such problems.

FIG. 5 is a schematic diagram for explaining processing for identifying corresponding points in the present invention. The figure is a schematic view showing an enlarged compared imaging point near P _R in the comparison image 104. Also in the figure, the luminance value of the reference pixel is “100”. First, the corresponding pixel 120 that is a pixel included in both the epipolar pixel line 116 and the equiluminance pixel line is specified. Since the luminance value of the corresponding pixel 120 is “101”, it does not match the luminance value of the reference pixel. In this case, the luminance values of the pixels 124 and 122 adjacent to the corresponding pixel 120 among the pixels included in the epipolar pixel line 116 are also acquired.

  The luminance value of the pixel 124 is “96”, and the luminance value of the pixel 122 is “103”. Therefore, it is considered that a true corresponding point that matches the luminance value “100” of the reference pixel exists on a line segment connecting the points 126 and 128. A point 126 is the center point of the corresponding pixel 120. A point 128 is the center point of the pixel 124. The luminance value increases by “5” from “96” to “101” between the point 128 and the point 126. Therefore, the true corresponding point with the luminance value “100” is a point 130 obtained by moving the line segment from the point 128 to the point 126 toward the point 128 by 1/5 from the point 126 as shown in FIG. Presumed to be a true comparative imaging point. In other words, the luminance value at the point 130 is estimated to be “100”. Then, ranging to the target point is executed based on the reference imaging point and the point 130.

  In the above, the true corresponding point is estimated by the method based on the linear interpolation based on the luminance values of the two pixels of the corresponding pixel 120 and the pixel 124. However, the true corresponding point is based on the non-linear interpolation using the luminance value of three pixels or more. Other methods may be used.

  In the isoluminance line stereo method, distance measurement is usually performed based on the coordinates of the reference imaging point and the point 126. On the other hand, in this embodiment, distance measurement is performed using the point 130 that is not a pixel unit as a comparative imaging point. As described with reference to FIG. 4, even if the difference between the point 126 and the point 130 is small, the distance measurement accuracy can be improved by obtaining the comparative imaging point in this way. Hereinafter, details for realizing the present invention will be described.

  FIG. 6 is a functional block diagram of the image processing apparatus 200. Each block shown here can be realized in hardware by an element such as a CPU of a computer or a mechanical device, and in software it is realized by a computer program or the like. Draw functional blocks. Therefore, those skilled in the art will understand that these functional blocks can be realized in various forms by a combination of hardware and software.

  The image processing apparatus 200 includes a user interface processing unit 202, an image acquisition unit 204, a reference pixel extraction unit 206, a distance measurement unit 208, a control unit 210, an equiluminance line extraction unit 212, an epipolar line extraction unit 214, a coordinate specification unit 220, and A data storage unit 230 is included. The data storage unit 230 stores various data necessary for ranging the target object 100. The data storage unit 230 includes a captured image storage unit 232 and a distance information storage unit 234. The captured image storage unit 232 stores the reference image and comparison image of the target object 100 as a pair of stereo images. The distance information storage unit 234 stores distance information that is a result of distance measurement for each target point on the surface of the target object 100. Based on this distance information, the target object 100 may be reproduced as a three-dimensional image by computer graphics by a known method.

  The user interface processing unit 202 acquires an operation input from the user and displays various information to the user. The control unit 210 comprehensively controls each functional block of the image processing apparatus 200 according to an instruction from the user interface processing unit 202 or the like. The image acquisition unit 204 acquires, from the camera, a stereo image composed of a pair of a reference image and a comparison image obtained by capturing the target object 100 from different angles. The image acquisition unit 204 stores these acquired captured images in the captured image storage unit 232 in association with the shooting position and angle with respect to the target object 100. The reference pixel extraction unit 206 appropriately extracts each pixel on the reference image, and the control unit 210 controls the ranging process for each pixel.

  The isoluminance line extraction unit 212 extracts the boundary lines of the regions classified according to the luminance from the reference image or the comparison image as isoluminance lines. However, the isoluminance lines referred to here are strictly the equiluminance pixel lines described with reference to FIG. The isoluminance line extraction unit 212 extracts isoluminance pixel lines from the reference image and the comparison image by a known method disclosed in Patent Document 1. The epipolar line extraction unit 214 extracts the epipolar line 112 from the comparison image corresponding to a predetermined reference pixel. However, as described with reference to FIG. 3, the epipolar line 112 extracted by the epipolar line extraction unit 214 is strictly an epipolar pixel line 116.

  The coordinate specifying unit 220 specifies corresponding points for the reference pixel from the comparative image based on the equiluminance pixel line and the epipolar pixel line 116. The coordinate specifying unit 220 includes a corresponding pixel specifying unit 222 and a corresponding point specifying unit 224. The corresponding pixel specifying unit 222 specifies the corresponding pixel based on the luminance value of the reference pixel. As described with reference to FIG. 3, the corresponding pixel specifying unit 222 specifies a corresponding pixel from pixels included in both the equiluminance pixel line and the epipolar pixel line 116. When there are several candidates for corresponding pixels, the corresponding pixels are identified by a known method such as based on the similarity to the luminance values of the pixels around the reference pixel.

  The corresponding point specifying unit 224 specifies the coordinates of the corresponding point having a luminance value substantially equal to the luminance value of the reference pixel based on the luminance value of the corresponding pixel. On the epipolar pixel line 116, the corresponding point specifying unit 224 determines the corresponding point assumed to have the same luminance value as the luminance value of the reference pixel based on the luminance value of the pixel adjacent to the corresponding pixel and the luminance value of the corresponding pixel. Specify coordinates. That is, the corresponding point specifying unit 224 first acquires the luminance value of a pixel adjacent to the specified corresponding pixel among the pixels included in the epipolar pixel line 116. Then, as described with reference to FIG. 5, the corresponding points are specified based on these luminance values. The distance measuring unit 208 measures the distance of the target object 100 to the target point based on the coordinates of the reference pixel and the coordinates of the corresponding point. The distance measuring unit 208 stores the coordinates of the reference pixel and the corresponding point and the distance to the target point of the target object 100 in the distance information storage unit 234 in association with each other.

  FIG. 7 is a flowchart illustrating a process in which the image processing apparatus 200 measures the target object 100. First, the image acquisition unit 204 acquires the reference image 102 obtained by capturing the target object 100 from the camera and stores it in the captured image storage unit 232 (S10). The image acquisition unit 204 acquires the comparison image 104 obtained by imaging the target object 100 from another angle from the camera, and stores it in the captured image storage unit 232 (S12). The equiluminance line extraction unit 212 extracts equiluminance pixel lines from the reference image 102 and the comparison image 104 (S14). The reference pixel extraction unit 206 acquires a predetermined pixel from the reference image 102 as a reference pixel (S16). At this time, the reference pixel extraction unit 206 appropriately selects and acquires a pixel included in the equiluminance pixel line of the reference image 102 as a reference pixel as shown in Patent Document 1. The reference pixel extraction unit 206 acquires the luminance value of the reference pixel (S18).

  Based on the position and luminance value of the reference pixel in the reference image 102, the coordinate specifying unit 220 acquires a corresponding point in the comparison image. The distance measuring unit 208 measures the distance to the target point based on the coordinates of the reference pixel and the acquired corresponding point. The distance measuring unit 208 stores the distance information acquired by the distance measuring process in the distance information storage unit 234. If the above processing has been completed for all pixels to be measured as reference pixels in the reference image 102 (Y in S24), the processing ends. If not completed (N in S24), the process returns to S16, and the reference pixel extraction unit 206 acquires the next reference pixel.

  FIG. 8 is a flowchart showing in detail the process of S20 of FIG. The epipolar line extraction unit 214 extracts the epipolar line 112 from the comparison image 104 based on the coordinates of the reference pixel (S30). However, the epipolar line 112 extracted by the epipolar line extraction unit 214 is an epipolar pixel line 116 that is a set of pixels including the epipolar line. The corresponding pixel specifying unit 222 specifies the corresponding pixel from the pixels included in both the equiluminance pixel line and the epipolar pixel line 116 extracted in S14 of FIG. 7 (S32). The corresponding pixel specifying unit 222 acquires the luminance value of the specified corresponding pixel (S34). If the luminance value of the reference pixel matches the luminance value of the corresponding pixel (Y in S36), the process ends with the coordinates of the corresponding pixel being a corresponding point. If they do not match (N in S36), the corresponding pixel specifying unit 222 acquires the luminance value of the pixel adjacent to the corresponding pixel among the pixels included in the epipolar pixel line 116 (S38). Then, as described with reference to FIG. 5, the corresponding point specifying unit 224 specifies the corresponding point based on the luminance value of the neighboring pixels (S40).

  According to the embodiment described above, the image processing apparatus 200 can more accurately measure the distance to the target object 100 based on the isoluminance line stereo method. The image processing apparatus 200 in the present embodiment does not obtain corresponding points in units of pixels. Therefore, ranging accuracy for measuring an object three-dimensionally is improved.

  In the above, this invention was demonstrated based on the Example. The present invention is not limited to this embodiment, and various modifications thereof are also effective as aspects of the present invention.

  For example, the image processing apparatus of the above embodiment is characterized in that the distance to the target object can be accurately measured by estimating the corresponding point of the stereo image in units of sub-pixels. However, as described in the above embodiment, A high-definition image may be generated by estimating corresponding points using a method. Alternatively, application to extraction of an object motion vector is also conceivable.

  Further, in the above embodiment, the distance is measured by obtaining a corresponding point that is not a pixel unit from the corresponding pixel, but such sub-pixelization can be applied not only to the corresponding pixel but also to the reference pixel. For example, the distance may be measured by obtaining a point that is not a pixel unit having a certain luminance value from both the reference pixel and the corresponding pixel. As a result, accurate isoluminance lines are obtained, and the three-dimensional shape thereof is also accurate.

It is a figure for demonstrating the principle which measures a target object by the principle of a triangulation. It is a schematic diagram for demonstrating the principle which identifies a corresponding point using an isoluminance line. Is a schematic view showing an enlarged compared imaging point near P _R in the comparative image. It is a schematic diagram for demonstrating the state where ranging accuracy falls in the isoluminance line stereo method. It is a schematic diagram for demonstrating the process which specifies a corresponding point in this invention. It is a functional block diagram of an image processing apparatus. It is a flowchart which shows the process in which an image processing apparatus measures a target object. It is a flowchart which shows the process of S20 of FIG. 7 in detail.

Explanation of symbols

  100 target object, 102 reference image, 104 comparison image, 112 epipolar line, 114 isoluminance line, 116 epipolar pixel line, 200 image processing device, 202 user interface processing unit, 204 image acquisition unit, 206 reference pixel extraction unit, 208 measurement Distance unit, 210 control unit, 212 isoluminance line extraction unit, 214 epipolar line extraction unit, 220 coordinate identification unit, 222 corresponding pixel identification unit, 224 corresponding point identification unit, 230 data storage unit, 232 captured image storage unit, 234 distance Information storage unit.

Claims (5)

An image acquisition unit that acquires a reference image and a comparison image obtained by imaging an object from different angles;
An isoluminance line extraction unit that extracts boundary lines of regions classified according to luminance from the comparison image as isoluminance lines;
An epipolar line extraction unit that extracts an epipolar line from the comparison image corresponding to a predetermined reference pixel in the reference image;
A corresponding pixel specifying unit for specifying a corresponding pixel corresponding to the reference pixel from the comparison image, based on an intersection of the isoluminance line corresponding to the luminance value in the reference pixel and the epipolar line;
A corresponding point specifying unit that specifies the coordinates of the corresponding point having a luminance value substantially equal to the luminance value of the reference pixel, based on the luminance value in the corresponding pixel;
A distance measuring unit that measures the distance to the object based on the coordinates of the reference pixel and the coordinates of the corresponding points;
An image processing apparatus comprising: An image acquisition unit that acquires a reference image and a comparison image obtained by imaging an object from different angles;
An isoluminance line extraction unit that extracts boundary lines of regions classified according to luminance from the comparison image as isoluminance lines;
An epipolar line extraction unit that extracts an epipolar line from the comparison image corresponding to a predetermined reference pixel in the reference image;
A corresponding pixel specifying unit for specifying a corresponding pixel corresponding to the reference pixel from the comparison image, based on an intersection of the isoluminance line corresponding to the luminance value in the reference pixel and the epipolar line;
A corresponding point specifying unit that specifies the coordinates of the corresponding point having a luminance value substantially equal to the luminance value of the reference pixel, based on the luminance value in the corresponding pixel;
An image processing apparatus comprising:   The corresponding point specifying unit is a coordinate of a corresponding point having a luminance value substantially equal to the luminance value of the reference pixel based on the luminance value of the pixel adjacent to the corresponding pixel and the luminance value of the corresponding pixel on the epipolar line. The image processing apparatus according to claim 1, wherein the image processing apparatus is specified. Obtaining a reference image and a comparative image obtained by imaging an object from different angles;
Extracting boundary lines of regions classified according to luminance from the comparison image as isoluminous lines;
Extracting an epipolar line from the comparison image corresponding to a predetermined reference pixel in the reference image;
Identifying a corresponding pixel corresponding to the reference pixel from the comparison image based on the intersection of the isoluminance line corresponding to the luminance value in the reference pixel and the epipolar line;
Identifying coordinates of corresponding points having a luminance value substantially equal to the luminance value of the reference pixel based on the luminance value in the corresponding pixel;
Measuring the distance to the object based on the coordinates of the reference pixel and the coordinates of the corresponding points;
An image processing method comprising: A function for acquiring a reference image and a comparative image obtained by imaging an object from different angles;
A function of extracting boundary lines of regions classified according to luminance from the comparison image as equal luminance lines;
A function of extracting an epipolar line from the comparison image corresponding to a predetermined reference pixel in the reference image;
A function of identifying a corresponding pixel corresponding to the reference pixel from the comparison image based on an intersection of the isoluminance line corresponding to the luminance value in the reference pixel and the epipolar line;
A function for specifying coordinates of corresponding points having a luminance value substantially equal to the luminance value of the reference pixel based on the luminance value in the corresponding pixel;
A function of measuring the distance to the object based on the coordinates of the reference pixel and the coordinates of the corresponding point;
An image processing program for causing a computer to exhibit the above.

Images