JP2010128622A - Stereo matching processing apparatus, stereo matching processing method and program - Google Patents

Abstract

<P>PROBLEM TO BE SOLVED: To improve the speed and precision of stereo matching processing. <P>SOLUTION: An image data input part 10 acquires the image data of a plurality of images obtained by photographing a prescribed region from a plurality of different positions. A reference parallax setting part 12 sets a reference parallax according to the plurality of images. A retrieval range setting part 13 sets a prescribed range which is smaller than the range of an image to the retrieval range of stereo matching by using the point of an image giving the reference parallax set by the reference parallax setting part 12 as a reference. For an optional point in one image of the plurality of images, a stereo matching part 11 retrieves a point corresponding to the other image in the retrieval range set by the retrieval range setting part 13 by using the point of the other image giving the reference parallax set by the reference parallax setting part 12 as a reference. <P>COPYRIGHT: (C)2010,JPO&INPIT

Description

  The present invention relates to a stereo matching processing device, a stereo matching processing method, and a program. More specifically, the present invention relates to a method for automatically generating three-dimensional data from a stereo image.

  As a method for automatically generating three-dimensional data from a stereo image, there is a wide variety of methods for generating three-dimensional data [DSM (Digital Surface Model) data] indicating terrain by stereo matching based on an image obtained from an artificial satellite or an aircraft. Has been done. Here, for two images taken from a different viewpoint from the stereo matching process, so-called stereo images, corresponding points in each image capturing the same point are obtained, and the parallax is used to determine the corresponding points according to the principle of triangulation Finding the depth and shape to the target.

  Various methods have already been proposed for this stereo matching process. For example, Patent Document 1 discloses a method using an area correlation method that is generally widely used. This area correlation method sets a correlation window in the left image as a template, moves the search window in the right image to calculate the cross-correlation coefficient with the template, This is a method of obtaining corresponding points by searching.

  In the above method, in order to reduce the amount of processing, by limiting the moving range of the search window to the epipolar line direction in the image, for each point in the left image, the corresponding point in the right image in the x direction A displacement amount, that is, a parallax can be obtained. Here, the epipolar line is a straight line that can be drawn as an existing range of a point corresponding to the point in one image in a stereo image. Epipolar lines are described in “Image Analysis Handbook” (supervised by Mikio Takagi and Yoshihisa Shimoda, published by the University of Tokyo Press, January 1991, pages 597-599).

  Usually, the epipolar line direction is different from the scanning line direction of the image. However, by performing coordinate conversion, the epipolar line direction can be matched with the scanning line direction of the image, and rearrangement can be performed. This coordinate transformation method is described in the above “Image Analysis Handbook”. In the stereo image that has been rearranged as described above, the movement range of the search window for the corresponding points can be limited to the scanning line, so that the parallax is obtained as the difference between the x coordinates of the corresponding points in the left and right images. .

  Each stereo image has a portion (occlusion region) that becomes a shadow of the object. There has been proposed a matching method that gives an accurate correspondence by not providing a stereo matching correspondence to this occlusion region (see Patent Document 2).

  Patent Document 3 describes a technology of a stereo image processing apparatus that automatically obtains three-dimensional data from a satellite stereo image or an aerial stereo image for a complex object without using an operator. In the technique of Patent Document 3, erroneous data such as noise and loss in the three-dimensional data obtained by the stereo processing means is automatically used by using outline information such as buildings obtained from the map data of the map data storage means. To correct. The map data storage means provides map data such as the external shape of the building to the DSM data automatic correction means.

Japanese Patent Laid-Open No. 3-167678 JP-A-4-299474 JP 2002-157576 A

  When searching for a point in one image and a corresponding point in the other image in a set of images for which stereo matching processing is performed, the search is performed over the entire scanning line (epipolar line) of the image. Processing takes time, and the probability of mismatching increases.

  The present invention has been made in view of the above circumstances, and an object thereof is to improve the speed and accuracy of stereo matching processing.

The stereo matching processing device according to the first aspect of the present invention provides:
Image data acquisition means for acquiring image data of a plurality of images obtained by photographing a predetermined region from a plurality of different positions;
Reference parallax setting means for setting a reference parallax corresponding to the plurality of images;
Search range setting means for setting a predetermined range smaller than the range of the image as a search range for stereo matching with reference to the point of the image giving the reference parallax set by the reference parallax setting means;
A search range set by the search range setting unit with respect to an arbitrary point in one image of the plurality of images based on a point of another image that gives a reference parallax set by the reference parallax setting unit. Search means for searching for corresponding points in the other image;
It is characterized by providing.

The stereo matching processing method according to the second aspect of the present invention is:
An image data acquisition step of acquiring image data of a plurality of images obtained by photographing a predetermined region from a plurality of different positions;
A reference parallax setting step for setting a reference parallax corresponding to the plurality of images;
A search range setting step for setting a predetermined range smaller than the range of the image data as a search range for stereo matching based on the point of the image giving the reference parallax set in the reference parallax setting step;
With respect to an arbitrary point in one image of the plurality of images, the search range set in the search range setting step based on a point of another image that gives the reference parallax set in the reference parallax setting step. A search step for searching for a corresponding point in the other image;
It is characterized by providing.

The program according to the third aspect of the present invention is:
Computer
Image data acquisition means for acquiring image data of a plurality of images obtained by photographing a predetermined region from a plurality of different positions;
Reference parallax setting means for setting a reference parallax corresponding to the plurality of images;
Search range setting means for setting a predetermined range smaller than the range of the image as a search range for stereo matching with reference to the point of the image giving the reference parallax set by the reference parallax setting means;
A search range set by the search range setting unit with respect to an arbitrary point in one image of the plurality of images based on a point of another image that gives a reference parallax set by the reference parallax setting unit. It is made to function as a search means for searching for a corresponding point in the other image.

  According to the present invention, the speed and accuracy of stereo matching processing can be improved in a method for automatically generating three-dimensional data from a stereo image.

  Hereinafter, embodiments of the present invention will be described in detail with reference to the drawings. In the drawings, the same or corresponding parts are denoted by the same reference numerals.

(Embodiment 1)
FIG. 1 is a block diagram showing a configuration example of a stereo image processing apparatus according to Embodiment 1 of the present invention. The stereo image processing apparatus 1 includes an image data input unit 10, a stereo matching unit 11, a reference parallax setting unit 12, and a search range setting unit 13. The stereo image processing apparatus 1 is connected to the height calculation unit 2.

  The image data input unit 10 has a function of inputting image data, and inputs a plurality of image data used for stereo matching processing. The image data is, for example, an aerial photograph image converted into a digital image. The image data includes the position where the image was captured, the direction in which the image was captured, the angle of view, and the like.

  FIG. 2 schematically shows an example of an aerial photograph converted into image data. The aerial photograph shown in FIG. 2 is composed of an aerial photograph 101A and an aerial photograph 101B continuously taken from an aircraft flying over the sky. The aerial photograph 101A and the aerial photograph 101B are taken with 60% overlap in the traveling direction of the aircraft. The overlap portion is an image obtained by photographing the same region from different positions.

  The image in the present embodiment is an image generated by digitally converting an aerial photograph taking the aerial photograph 101A and the aerial photograph 101B as an example. The image used in the present invention is not limited to an aerial image, but it scans a digital satellite image, a digital image taken with a general digital camera, or an analog photo taken with a general analog camera. It may be a digital image or the like digitized by.

  The stereo matching unit 11 in FIG. 1 detects a position in an image that captures the same point with respect to a plurality of image data obtained by photographing the same region from different positions. That is, a set of points corresponding to the same point in a plurality of images is detected. A set of points corresponding to the same point is usually detected from the position where the correlation coefficient is maximized in the two adjacent images and the correlation coefficient of the corresponding small area is maximized.

  Note that there are various methods for performing stereo matching processing, such as a method for obtaining a general feature value to be associated, and a method for obtaining a correlation between left and right images, and the stereo matching processing in the present embodiment. There are no restrictions on the method used. For example, a stereo matching process described in Japanese Patent Publication No. 8-16930 may be used.

  The height calculation unit 2 generates DSM data based on the principle of triangulation from the parallax of the corresponding points obtained by the stereo matching process. For example, between the pair of aerial photographs 101A and aerial photographs 101B, the position of the corresponding feature has a predetermined positional deviation (parallax), and therefore, the stereo matching processing is performed by measuring this positional deviation. The height of the surface layer of the feature including the elevation value and the horizontal coordinate, that is, three-dimensional data are obtained.

  FIG. 3 is a schematic diagram illustrating an example of a ground state in the real world. FIG. 3 shows a cross section of a part of the real world, and features exist on the undulating terrain.

  FIG. 4 is a schematic diagram showing DSM data generated by stereo matching processing from an image obtained by photographing a part of the real world shown in FIG. Since the DSM data represents the height data of the outermost surface, the ground surface hidden by the roof or the like represents the height of the roof including the altitude value.

  The reference parallax setting unit 12 in FIG. 1 sets a parallax that gives a reference parallax for searching for corresponding points in two images. For example, the parallax that gives the reference height of the range to be searched by stereo matching in the real space is set as a reference. The search range setting unit 13 sets a range in which the stereo matching unit 11 searches for a corresponding point based on the image point that gives the reference parallax set by the reference parallax setting unit 12. Normally, a predetermined range smaller than the image range is set as the search range for stereo matching.

  FIG. 4 conceptually shows the reference altitude and the height corresponding to the search range. For example, for the undulating ground surface as shown in FIG. 3, a plane represented by a line SL having a predetermined height H from the height G of the altitude of the aircraft is set as the reference altitude. Then, with reference to the surface of the line SL, a range between the line BL and the line UL is set as a height SH corresponding to the search range in the real space.

  FIG. 5 shows a search plane for explaining the search range. FIG. 5 shows the scanning line (epipolar line) A of the image obtained by converting the aerial photograph 101A and the scanning line (epipolar line) B corresponding to the scanning line A of the image obtained by converting the aerial photograph 101B arranged vertically. is there. A plane constituted by the axis AB is generally called a search plane. The center positions of the blocks on A and B are represented by vertical lines and horizontal lines, respectively, and one correspondence between the two images is represented by the intersection of the vertical lines and horizontal lines. The stereo matching unit 11 searches for the corresponding points of the two images on the scanning lines A and B. A line with an angle of 45 degrees in the search plane indicates a constant parallax, that is, a constant height in the two images.

  In FIG. 5, a line gl is, for example, a parallax line corresponding to the reference height of the ground, and represents the origin of the altitude of the aircraft. The line sp is a height that gives the reference parallax and corresponds to the line SL in FIG. The width SP corresponds to the height H in FIG. The line u in FIG. 5 corresponds to the line UL in FIG. 4, and the line l corresponds to the line BL in FIG. The range of the width R surrounded by the line u and the line l indicates the search range.

  For example, the stereo matching unit 11 searches for a corresponding combination between AB between the line u and the line l in FIG. A point of the scanning line B corresponding to a certain point on the scanning line A is searched for in a portion between the vertical line u and the line l passing through the point of the scanning line A. When the point of the scanning line B is determined and the corresponding point of the scanning line A is searched, the search is performed in a portion between the horizontal line passing through the point of the scanning line B and the line u and the line l.

  FIG. 6 shows an example of the search range. When the difference in level of the undulations on the ground is known, it is possible to determine a range for searching for the feature having the maximum height including that. In FIG. 6, the parallax corresponding to the undulations is represented by a line ls. The search range is indicated by a line u and a line l in the range R including the height difference of the undulation, with reference to the parallax sp obtained by adding the assumed average height of the feature to the average undulation height.

  When the altitude of the ground surface is known, the stereo matching process can be performed quickly by setting a search range including the height difference and the height of the assumed feature. In addition, since the search range is limited, the possibility of erroneous recognition of corresponding points between two images is reduced.

  FIG. 7 is a flowchart showing an example of the operation of the height orientation processing according to the first embodiment. The image data input unit 10 inputs a plurality of images to be subjected to stereo matching processing (step S11). For example, the reference parallax setting unit 12 sets the reference parallax from the height of the feature that is assumed to be the average altitude of the region (step S12). The search range setting unit 13 sets a search range with respect to the reference parallax from the elevation difference of the region and the height of the feature (step S13).

  The stereo matching unit 11 searches for the corresponding point of the other image within the set search range based on the point of the other image giving the reference parallax with respect to the point of one image (step S14). The height calculator 2 calculates the height corresponding to the point and the coordinates of the point on the map from the position in the image of each point associated with the plurality of images (step S15).

  According to the stereo image processing apparatus 1 of the first embodiment, the stereo matching process can be performed quickly by setting the reference parallax and the search range including the height of the feature that is assumed to be a height difference. . In addition, since the search range is limited, the possibility of erroneous recognition of corresponding points between two images is reduced.

(Embodiment 2)
FIG. 8 is a block diagram showing a configuration example of the stereo image processing apparatus 1 according to Embodiment 2 of the present invention. In the second embodiment, the reference parallax and the search range are set based on the altitude data of the map data.

  The stereo image processing apparatus 1 of FIG. 8 includes a map data input unit 14 and an area dividing unit 15 in addition to the configuration of the first embodiment. The map data input unit 14 inputs map data of a target area of the input image data. The map data includes elevation data at each point of the map mesh.

  The area dividing unit 15 divides the input image data according to the altitude data. If the difference in elevation data is small, the entire image may be divided into one area without being divided. If the height difference in the map data of the image range exceeds a predetermined range, the image is divided into a plurality of regions.

  The reference parallax setting unit 12 sets the reference parallax for each region divided by the region dividing unit 15 based on the altitude data. The search range setting unit 13 also sets a search range for each divided region in consideration of the height difference of the altitude data and the assumed feature height.

  The stereo matching unit 11 searches for corresponding points in a plurality of images in accordance with the reference parallax set for each divided region and the search range, and extracts a set of corresponding points. The height calculation unit 2 generates DSM data based on the principle of triangulation from the parallax of the corresponding points obtained by the stereo matching process.

  FIG. 9 shows an example of a search plane for setting a reference parallax and a search range for each divided area. In the example of FIG. 9, it is divided into four regions according to the undulations ls of the ground surface. In each region, the reference parallax is sp1, sp2, sp3, sp4. In the first region, the range of the width R1 with u1 and l1 as the boundary is set as the search range. Hereinafter, the range of width R2 with u2 and l2 as boundaries, the range of width R3 with u3 and l3 as boundaries, and the range of width R4 with u4 and l4 as boundaries are set as search ranges.

  As shown in FIG. 9, the search range is smaller than that in FIG. When there is a difference in level of undulations, the search range can be limited to a range where the corresponding points exist by dividing the image range into a plurality of regions and setting the search range for each divided region. As a result, the stereo matching process can be performed quickly and accurately.

  The region division can be set so that the height difference in the region is equal to or less than a predetermined value. Alternatively, the number of divisions may be determined according to the height difference of the image range.

  FIG. 10 is a flowchart illustrating an example of the operation of the height orientation processing according to the second embodiment. When the image data input unit 10 inputs a plurality of images to be subjected to stereo matching processing (step S21), the map data input unit 14 inputs map data of the target area (step S22). The area dividing unit 15 divides the image into areas based on the altitude data included in the map data (step S23).

  The reference parallax setting unit 12 sets a reference parallax for each divided area based on the altitude data and the divided areas (step S24). The search range setting unit 13 sets a search range for each region according to the height difference of the divided regions (step S25).

  The stereo matching unit 11 searches for a corresponding point of another image in a search range set for each region based on the point of the other image giving the reference parallax with respect to the point of one image (step). S26). The height calculator 2 calculates the height corresponding to the point and the coordinates of the point on the map from the position in the image of each point associated with the plurality of images (step S27).

  According to the stereo image processing apparatus 1 of the second embodiment, the search range can be limited to a range where corresponding points exist according to the altitude data of the map data. As a result, the stereo matching process can be performed quickly and accurately.

(Embodiment 3)
FIG. 11 is a block diagram illustrating a configuration example of the stereo image processing apparatus 1 according to the third embodiment. The stereo image processing apparatus 1 according to the third embodiment includes a reference point setting unit 16 in addition to the configuration of the first embodiment.

  The reference point setting unit 16 selects a reference point for setting a reference parallax by a predetermined method from the images input by the image data input unit 10. For example, as the reference point, a number of points corresponding to the size and scale of the image are randomly selected. Alternatively, a point with a predetermined distribution may be selected.

  The reference point setting unit 16 extracts a set of corresponding points in the plurality of images by the stereo matching unit 11 for the selected point. In addition, the three-dimensional data of the selected point is calculated. Then, the three-dimensional data of the selected point is sent to the reference parallax setting unit 12.

  The reference parallax setting unit 12 sets the reference parallax from the three-dimensional data received from the reference point setting unit 16 by a predetermined method. For example, the average or median height of the three-dimensional data is set as the reference elevation, and the parallax corresponding to the reference elevation is set as the reference parallax. Alternatively, the average parallax may be set for each predetermined divided area, and the reference parallax may be set for each area.

  The search range setting unit 13 sets the search range according to the reference parallax. For example, the search range can be set in consideration of the distribution of the height of the three-dimensional data at the selected point. In addition, when the range of the image is divided into a plurality of areas, a search range may be set for each of the divided areas.

  The stereo matching unit 11 searches for corresponding points in a plurality of images in accordance with the set reference parallax search range, and extracts a set of corresponding points. When a reference parallax and a search range are set for each divided area, a corresponding point is searched in the search range. The height calculation unit 2 generates DSM data based on the principle of triangulation from the parallax of the corresponding points obtained by the stereo matching process.

  FIG. 12 is a flowchart showing an example of the operation of the height orientation processing according to the third embodiment. When the image data input unit 10 inputs a plurality of images to be subjected to stereo matching processing (step S31), the reference point setting unit 16 selects a reference point in the image by a predetermined method (step S32). The stereo matching unit 11 performs a stereo matching process on the selected reference point, and extracts a pair corresponding to the plurality of images (step S33).

  The reference point setting unit 16 calculates the height of the reference point from the set corresponding to the selected point (step S34). The reference parallax setting unit 12 sets a reference parallax based on the height of the reference point (step S35). Here, the reference parallax setting unit 12 may set the reference parallax based on the pair of the selected points (the reference point setting unit 16 may not calculate the height of the reference point). The search range setting unit 13 sets a search range according to the reference parallax (step S36).

  The stereo matching unit 11 searches for a corresponding point of another image in a search range set for each region based on the point of the other image giving the reference parallax with respect to the point of one image (step). S37). The height calculation unit 2 calculates the height corresponding to the point and the coordinates of the point on the map from the position in the image of each point associated with the plurality of images (step S38).

  According to the stereo image processing apparatus 1 of the third embodiment, even when there is no map data, the search range can be limited to a range in which corresponding points exist so as to match the image. As a result, the stereo matching process can be performed quickly and accurately.

(Embodiment 4)
FIG. 13 is a block diagram illustrating a configuration example of the stereo image processing apparatus 1 according to the fourth embodiment. The stereo image processing apparatus 1 according to the fourth embodiment inputs the reference point according to the third embodiment from the outside. The stereo image processing apparatus 1 of FIG. 13 includes a reference point input unit 17 in addition to the configuration of the third embodiment.

  The reference point input unit 17 inputs data indicating the position of the reference point in the image. For example, image data may be displayed on a display device (not shown), and a point selected on the screen may be input. Further, the coordinates in the image may be input as data.

  The operations of the reference point setting unit 16, the reference parallax setting unit 12, the search range setting unit 13, and the stereo matching unit 11 are the same as those in the third embodiment.

In the fourth embodiment, it is possible to set a reference point considered appropriate from the input image. For example, it is possible to select points that are considered appropriate for the standard altitude, such as aerial beacon lights such as high-rise buildings, feature points of steel towers, and feature points of artificial features such as buildings, and that can perform stereo matching processing accurately. .

  FIG. 14 is a flowchart illustrating an example of the height locating process according to the fourth embodiment. When the image data input unit 10 inputs a plurality of images to be subjected to stereo matching processing (step S41), the reference point input unit 17 inputs data indicating the position of the reference point in the image (step S42). There may be a plurality of reference points to be selected.

  The reference point setting unit 16 sends the position of the input point to the stereo matching unit 11, and the stereo matching unit 11 performs a stereo matching process on the selected reference point to extract a pair corresponding to a plurality of images. (Step S43). The reference point setting unit 16 calculates the height of the reference point from the set corresponding to the selected point (step S44). Thereafter, the calculation of the corresponding height (step S48) from the reference parallax setting (step S45) is the same as steps S35 to S38 in FIG.

  According to the stereo image processing apparatus 1 of the fourth embodiment, in addition to the third embodiment, it is possible to select a point where the stereo matching process can be accurately performed with an appropriate reference parallax according to the image. As a result, the stereo matching process can be performed quickly and accurately.

(Embodiment 5)
FIG. 15 is a block diagram illustrating a configuration example of the stereo image processing apparatus 1 according to the fifth embodiment. The stereo image processing apparatus 1 according to the fifth embodiment inputs a set corresponding to the reference point according to the third embodiment and the stereo matching from the outside. The stereo image processing apparatus 1 of FIG. 15 includes a reference corresponding point input unit 18 instead of the reference point input unit 17 and the reference point setting unit 16 of the third embodiment.

  The reference corresponding point input unit 18 inputs data indicating the position of the reference point in the image and the position of the point in another image corresponding to the stereo matching. For example, two pieces of image data may be displayed on a display device (not shown), and a set of corresponding points selected on the screen may be input. Further, the coordinates of a set of corresponding points in the two images may be input as data.

  The operations of the reference parallax setting unit 12, the search range setting unit 13, and the stereo matching unit 11 are the same as those in the first embodiment.

In the fifth embodiment, it is possible to set a reference corresponding point that is considered appropriate from the input image. For example, it is possible to select corresponding points that are considered to be appropriate for the reference altitude and are stereo-matched, such as aerial beacon lights such as high-rise buildings, feature points of steel towers, and feature points of artificial features such as buildings.

  FIG. 16 is a flowchart illustrating an example of the operation of the height orientation processing according to the fifth embodiment. When the image data input unit 10 inputs a plurality of images to be subjected to the stereo matching process (step S51), the reference corresponding point input unit 18 indicates the positions of the reference corresponding points corresponding to the stereo matching in two of the images. Data is input (step S52). There may be a plurality of reference points to be selected.

  Thereafter, the reference height setting (step S53) to the corresponding height calculation (step S56) are the same as steps S35 to S38 in FIG.

  According to the stereo image processing device 1 of the fifth embodiment, the reference parallax and the search range are set by selecting the corresponding reference that is stereo-matching with the reference parallax appropriate for the image. Can do. As a result, the stereo matching process can be performed quickly and accurately.

  FIG. 17 is a block diagram illustrating an example of a physical configuration when the stereo image processing apparatus 1 is mounted on a computer. The stereo image processing apparatus 1 according to the present embodiment can be realized by a hardware configuration similar to a general computer apparatus. As shown in FIG. 17, the stereo image processing apparatus 1 includes a control unit 21, a main storage unit 22, an external storage unit 23, an operation unit 24, a display unit 25, and an input / output unit 26. The main storage unit 22, the external storage unit 23, the operation unit 24, the display unit 25, and the input / output unit 26 are all connected to the control unit 21 via the internal bus 20.

  The control unit 21 includes a CPU (Central Processing Unit) and the like, and executes stereo matching processing according to a control program 30 stored in the external storage unit 23.

  The main storage unit 22 is constituted by a RAM (Random-Access Memory) or the like, loads a control program 30 stored in the external storage unit 23, and is used as a work area of the control unit 21.

  The external storage unit 23 includes a non-volatile memory such as a flash memory, a hard disk, a DVD-RAM (Digital Versatile Disc Random-Access Memory), a DVD-RW (Digital Versatile Disc ReWritable), etc. A control program 30 to be executed is stored in advance, and data stored in the control program 30 is supplied to the control unit 21 in accordance with an instruction from the control unit 21, and the data supplied from the control unit 21 is stored.

  The operation unit 24 includes a pointing device such as a keyboard and mouse, and an interface device that connects the keyboard and pointing device to the internal bus 20. Through the operation unit 24, input of image data, instructions such as transmission / reception, designation of an image to be displayed, a position in the image of a reference point for setting a reference altitude, and the like are input and supplied to the control unit 21.

  The display unit 25 is composed of a CRT (Cathode Ray Tube), an LCD (Liquid Crystal Display), or the like, and displays an image or a result of stereo matching processing.

  The input / output unit 26 includes a wireless transceiver, a wireless modem or network termination device, and a serial interface or a LAN (Local Area Network) interface connected thereto. The image data can be received and the calculated result can be transmitted via the input / output unit 26.

  The image data input unit 10, the stereo matching unit 11, the reference parallax setting unit 12, the search range setting unit 13, the map data input unit 14, and the region dividing unit of the stereo image processing apparatus 1 shown in FIG. 15, the reference point setting unit 16, the reference point input unit 17, and the reference corresponding point input unit 18 are processed by the control program 30, the control unit 21, the main storage unit 22, the external storage unit 23, the operation unit 24, and the display unit 25. The processing is executed by using the input / output unit 26 as a resource.

  Other suitable modifications of the present invention include the following configurations.

About the stereo matching processing device according to the first aspect of the present invention,
Preferably, the reference parallax setting unit divides the plurality of images into two or more corresponding areas, and sets the reference parallax in each area,
The search range setting means sets a predetermined range smaller than the range of the image as a search range for stereo matching based on the point of the image that gives the reference parallax set in each of the regions.
It is characterized by that.

Preferably, comprising map data acquisition means for acquiring elevation data of a map corresponding to the plurality of images,
The reference parallax setting unit sets the reference parallax based on the altitude data acquired by the map data acquisition unit.

  Alternatively, the reference parallax setting unit may calculate a parallax by stereo matching for a point selected from the plurality of images by a predetermined method, and set the reference parallax based on the calculated parallax.

Furthermore, a reference point input means for acquiring a position in the image of a point for which parallax is obtained among the plurality of images is provided,
The reference parallax setting unit may calculate a parallax by stereo matching for the point acquired by the reference point input unit, and set the reference parallax based on the calculated parallax.

Alternatively, it comprises corresponding point input means for inputting a set of points corresponding to stereo matching from the plurality of images.
The reference parallax setting unit may set the reference parallax based on a parallax given by a set of corresponding points input by the corresponding point input unit.

About the stereo matching processing method according to the second aspect of the present invention,
Preferably, the reference parallax setting step divides a set of images to be subjected to the stereo matching process into two or more corresponding areas, and sets the reference parallax in each area,
The search range setting step sets a predetermined range smaller than the range of the image as a search range for stereo matching based on the point of the image that gives the reference parallax set in the respective regions.
It is characterized by that.

Preferably, a map data acquisition step of acquiring map elevation data corresponding to the plurality of images is provided,
In the reference parallax setting step, the reference parallax is set based on the altitude data acquired in the map data acquisition step.

  Alternatively, the reference parallax setting step may calculate a parallax by stereo matching for a point selected from the plurality of images by a predetermined method, and set the reference parallax based on the calculated parallax.

And a reference point input step of acquiring a position in the image of the point for which parallax is to be obtained among the plurality of images.
In the reference parallax setting step, parallax may be calculated by stereo matching for the points acquired in the reference point input step, and the reference parallax may be set based on the calculated parallax.

Alternatively, a corresponding point input step of inputting a set of points corresponding to stereo matching from the plurality of images,
The reference parallax setting step may set the reference parallax based on the parallax given by the set of corresponding points input in the corresponding point input step.

  In addition, the hardware configuration and the flowchart described above are merely examples, and can be arbitrarily changed and modified.

  The central part that performs processing of the stereo image processing apparatus 1 including the control unit 21, the main storage unit 22, the external storage unit 23, the operation unit 24, the input / output unit 26, the internal bus 20, and the like is a dedicated system. Regardless, it can be realized using a normal computer system. For example, a computer program for executing the above operation is stored and distributed in a computer-readable recording medium (flexible disk, CD-ROM, DVD-ROM, etc.), and the computer program is installed in the computer. Thus, the stereo image processing apparatus 1 that executes the above-described processing may be configured. In addition, the stereo image processing apparatus 1 may be configured by storing the computer program in a storage device included in a server device on a communication network such as the Internet and downloading it by a normal computer system.

  Further, when the functions of the stereo image processing apparatus 1 are realized by sharing of an OS (operating system) and an application program, or by cooperation between the OS and the application program, only the application program portion is stored in a recording medium or a storage device. It may be stored.

  It is also possible to superimpose a computer program on a carrier wave and distribute it via a communication network. For example, the computer program may be posted on a bulletin board (BBS, Bulletin Board System) on a communication network, and the computer program distributed via the network. The computer program may be started and executed in the same manner as other application programs under the control of the OS, so that the above-described processing may be executed.

It is a block diagram which shows the structural example of the stereo image processing apparatus which concerns on Embodiment 1 of this invention. It is a figure which shows typically an example of the aerial photograph converted into image data. It is a schematic diagram which shows an example of the ground state of the real world. It is a schematic diagram which shows the DSM data produced | generated by the stereo matching process from the image which image | photographed a part of real world shown in FIG. It is a figure which shows the search plane explaining a search range. It is a figure which shows an example of a search range. 6 is a flowchart illustrating an example of an operation of a height orientation process according to the first embodiment. It is a block diagram which shows the structural example of the stereo image processing apparatus which concerns on Embodiment 2 of this invention. It is a figure which shows the example of the search plane which sets a reference | standard altitude and a search range for every divided | segmented area | region. 10 is a flowchart illustrating an example of an operation of a height orientation process according to the second embodiment. 10 is a block diagram illustrating a configuration example of a stereo image processing apparatus 1 according to Embodiment 3. FIG. 10 is a flowchart illustrating an example of an operation of height orientation processing according to the third embodiment. FIG. 10 is a block diagram illustrating a configuration example of a stereo image processing apparatus 1 according to a fourth embodiment. 10 is a flowchart illustrating an example of an operation of a height orientation process according to the fourth embodiment. FIG. 10 is a block diagram illustrating a configuration example of a stereo image processing apparatus 1 according to a fifth embodiment. 10 is a flowchart illustrating an example of an operation of height orientation processing according to the fifth embodiment. It is a block diagram which shows an example of a physical structure in the case of mounting the stereo image processing apparatus 1 in a computer.

Explanation of symbols

DESCRIPTION OF SYMBOLS 1 Stereo image processing apparatus 2 Height calculation part 10 Image data input part 11 Stereo matching part 12 Reference parallax setting part 13 Search range setting part 14 Map data input part 15 Area division part 16 Reference point setting part 17 Reference point input part 18 Reference | standard Corresponding point input unit 21 Control unit 22 Main storage unit 23 External storage unit 24 Operation unit 25 Display unit 26 Input / output unit 30 Control program

Claims (13)

Image data acquisition means for acquiring image data of a plurality of images obtained by photographing a predetermined region from a plurality of different positions;
Reference parallax setting means for setting a reference parallax corresponding to the plurality of images;
Search range setting means for setting a predetermined range smaller than the range of the image as a search range for stereo matching with reference to the point of the image giving the reference parallax set by the reference parallax setting means;
A search range set by the search range setting unit with respect to an arbitrary point in one image of the plurality of images based on a point of another image that gives a reference parallax set by the reference parallax setting unit. Search means for searching for corresponding points in the other image;
A stereo matching processing device comprising: The reference parallax setting means divides the plurality of images into two or more corresponding areas, and sets the reference parallax in each area;
The search range setting means sets a predetermined range smaller than the range of the image as a search range for stereo matching based on the point of the image that gives the reference parallax set in each of the regions.
The stereo matching processing device according to claim 1. Comprising map data acquisition means for acquiring elevation data of a map corresponding to the plurality of images,
3. The stereo matching processing device according to claim 1, wherein the reference parallax setting unit sets the reference parallax based on elevation data acquired by the map data acquisition unit.   The reference parallax setting unit calculates a parallax by stereo matching for a point selected from the plurality of images by a predetermined method, and sets the reference parallax based on the calculated parallax. Item 3. The stereo matching processing device according to Item 1 or 2. Reference point input means for acquiring the position in the image of the point for which parallax is to be obtained among the plurality of images,
5. The reference parallax setting unit calculates a parallax by stereo matching for the point acquired by the reference point input unit, and sets the reference parallax based on the calculated parallax. The stereo matching processing device described. Corresponding point input means for inputting a set of points corresponding to stereo matching from the plurality of images,
The reference parallax setting means sets the reference parallax based on a parallax given by a set of corresponding points input by the corresponding point input means;
The stereo matching processing device according to claim 1, wherein An image data acquisition step of acquiring image data of a plurality of images obtained by photographing a predetermined region from a plurality of different positions;
A reference parallax setting step for setting a reference parallax corresponding to the plurality of images;
A search range setting step for setting a predetermined range smaller than the range of the image data as a search range for stereo matching based on the point of the image giving the reference parallax set in the reference parallax setting step;
With respect to an arbitrary point in one image of the plurality of images, the search range set in the search range setting step based on a point of another image that gives the reference parallax set in the reference parallax setting step. A search step for searching for a corresponding point in the other image;
A stereo matching processing method comprising: The reference parallax setting step divides a set of images to be subjected to the stereo matching process into two or more corresponding areas, sets the reference parallax in each area,
The search range setting step sets a predetermined range smaller than the range of the image as a search range for stereo matching based on the point of the image that gives the reference parallax set in the respective regions.
The stereo matching processing method according to claim 7. A map data acquisition step of acquiring altitude data of a map corresponding to the plurality of images,
The stereo matching processing method according to claim 7 or 8, wherein the reference parallax setting step sets the reference parallax based on the altitude data acquired in the map data acquisition step.   The reference parallax setting step calculates parallax by stereo matching for a point selected from the plurality of images by a predetermined method, and sets the reference parallax based on the calculated parallax. Item 9. The stereo matching processing method according to Item 7 or 8. A reference point input step for obtaining a position in the image of the point for which parallax is obtained among the plurality of images,
11. The reference parallax setting step calculates parallax by stereo matching for the point acquired in the reference point input step, and sets the reference parallax based on the calculated parallax. The stereo matching processing method described. A corresponding point input step of inputting a set of points corresponding to stereo matching from the plurality of images;
The reference parallax setting step sets the reference parallax based on the parallax given by the set of corresponding points input in the corresponding point input step;
The stereo matching processing method according to claim 7 or 8, wherein Computer
Image data acquisition means for acquiring image data of a plurality of images obtained by photographing a predetermined region from a plurality of different positions;
Reference parallax setting means for setting a reference parallax corresponding to the plurality of images;
Search range setting means for setting a predetermined range smaller than the range of the image as a search range for stereo matching with reference to the point of the image giving the reference parallax set by the reference parallax setting means;
A search range set by the search range setting unit with respect to an arbitrary point in one image of the plurality of images based on a point of another image that gives a reference parallax set by the reference parallax setting unit. A program that functions as search means for searching for a corresponding point in the other image.

Images