CN113808070A - Binocular digital speckle image related parallax measurement method - Google Patents
Binocular digital speckle image related parallax measurement method Download PDFInfo
- Publication number
- CN113808070A CN113808070A CN202110847673.0A CN202110847673A CN113808070A CN 113808070 A CN113808070 A CN 113808070A CN 202110847673 A CN202110847673 A CN 202110847673A CN 113808070 A CN113808070 A CN 113808070A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- parallax
- matching
- camera
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000691 measurement method Methods 0.000 title claims abstract description 19
- 238000000034 method Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 35
- 239000007787 solid Substances 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000012937 correction Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 230000000007 visual effect Effects 0.000 abstract description 2
- 238000005259 measurement Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 5
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000000399 optical microscopy Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/97—Determining parameters from multiple pictures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention provides a binocular digital speckle image related parallax measurement method. Firstly, calibrating by adopting a Zhangzhen calibration method to obtain internal parameters and external parameters of a left camera and a right camera; projecting the speckle images with controllable distribution density to the surface of a measured object; the left camera and the right camera synchronously acquire a left image and a right image; processing the speckle images to reduce the range to be matched from a two-dimensional image to a one-dimensional polar line; selecting a window to be matched with a certain shape and size in the right image, adopting an improved normalized cross-correlation matching algorithm based on a gray image, searching for an optimal matching window of the window to be matched in the left image, and calculating a parallax value; changing the number of intervals between pixel matrixes on two sides and a central pixel point in a window to be matched, and calculating a plurality of parallax values; and finally, carrying out weighted average on the parallax according to the reciprocal of the interval number to obtain the final parallax value of the speckle images under two different visual angles.
Description
Technical Field
The invention belongs to the technology of computational optical microscopy imaging, and particularly relates to a binocular digital speckle image related parallax measurement method.
Background
Binocular stereoscopic vision is an important branch of computer vision, and has application value in many fields, such as pose detection and control of a micro-operation system, robot navigation and aerial survey, three-dimensional metrology, virtual reality and the like. The binocular stereopsis measurement system is similar to the human eyes, and two cameras are used for recording images of the same object under different visual angles. In order to facilitate binocular matching between camera images of different viewing angles, epipolar rectification of the photographed binocular images is required. The binocular stereo vision measurement method has the advantages of high sensitivity, high measurement precision, simple system structure, low cost, non-contact property and the like, and is increasingly paid attention to by people.
The speckle projection is to increase the characteristic information of the object surface by projecting random speckle images on the object surface, which is helpful to improve the effect of binocular matching. After the shot image is subjected to limit correction, the speckle image is calculated by using the similarity function, and the matching relation of the speckle image is obtained. The structured light technology of random speckles can be realized by using a single speckle image, and is also one of important means of dynamic measurement.
The stereo matching algorithm may be classified into a local stereo matching algorithm and a global stereo matching algorithm according to a difference in the optimization theory method. The basic principle of the local stereo matching algorithm is that a certain point on one image is given, a sub-window in the neighborhood of the pixel point is selected, a sub-image most similar to the sub-window image is searched in a region in the other image according to a certain similarity judgment basis, and the corresponding pixel point in the matched sub-image is the matching point of the pixel.
Disclosure of Invention
The invention aims to provide a parallax measurement method with high precision and high speed, in particular to a parallax measurement method based on digital speckle image correlation under a binocular measurement system.
The technical scheme of the invention is as follows: a binocular digital speckle image related parallax measurement method comprises the following steps:
building a binocular stereo vision measuring system, wherein the binocular stereo vision measuring system consists of a left camera, a right camera and a projection device, so that the left camera and the right camera are placed in parallel;
calibrating the left camera and the right camera by adopting a solid circular array calibration plate to respectively obtain the internal parameters and the external parameters of the left camera and the right camera;
acquiring a speckle image with controllable distribution density, and setting the resolution of the speckle image, a speckle distribution constraint window, the size of speckles and the like;
projecting a single speckle image to the surface of a measured object, and synchronously acquiring a left image and a right image by using a left camera and a right camera;
a point P on the space is imaged by the left camera and the right camera to be P1、P2，P2Must be in relation to P1On the polar line of (A); carrying out limit correction on the left image and the right image so as to reduce the matching range of the characteristic points from the two-dimensional image to a one-dimensional polar line;
taking the right image as a basic module and taking the pixel point as a center, and selecting a window to be matched with a certain shape and size; performing pixel-by-pixel matching in a certain range on the epipolar line of the left image, and searching in windows with the same shape and size; obtaining an optimal matching point corresponding to a pixel in a right image in a left image by adopting an improved normalized cross-correlation algorithm based on a gray image;
and seventhly, under the pixel coordinate, optimally matching the pixel coordinate u in the horizontal direction of the pixel point in the left image according to the optimal matching relation of the pixel pointsLThe pixel coordinate u of the pixel point to be matched in the right image in the horizontal directionRThe difference between them is the parallax, i.e. d ═ uL-uR；
Under the condition that other conditions are not changed, taking a plurality of interval numbers K to form a plurality of groups of windows to be matched; repeating the sixth step and the seventh step to calculate the parallax value corresponding to the interval K
And carrying out weighted average on all the parallax values according to the reciprocal of the interval number to obtain the final parallax D, wherein the unit is pixel.
Preferably, the left and right cameras and the projection device are located on the same horizontal line in the step one.
Preferably, a solid circle array calibration plate is adopted in the second step, a Zhang-Yongyou calibration method is adopted in the calibration process, and the coordinates of the feature points in the pixel coordinate system and the world coordinate system have the following mapping relationship:
wherein (u, v) is the coordinate of the characteristic point in the pixel coordinate system, s is the proportionality coefficient of any scale, M is the internal reference matrix, r is1、r2The first two columns of the rotation matrix, respectively, t is the translation matrix, (x)W，yW) And H is a homography matrix.
Preferably, the selection of the matching window in the sixth step takes a pixel point in the right image as a center, K pixels are spaced at two sides of the pixel point, and the aspect ratio is selected to be (2M + 1): two rectangular blocks of N form a matching window, and the data matrix on the left of the pixel point is R1The right data matrix is R2。
Preferably, an improved normalized cross-correlation algorithm based on gray level images is adopted for matching in the sixth step, and corresponding matching points in the left image and the right image are finally determined;
the matching process is implemented by searching for optimal matching in the same line and performing parallel processing, and adopts the following formula:
wherein, CNCCTo normalize the cross-correlation coefficient, the larger the normalized cross-correlation coefficient and closer to 1, the higher the correlation, which can be considered as an optimal match,
L1and L2A matrix of pixel values for both sides of the corresponding point in the left image,
and
are respectively the transposing of the two,
defining matrix norm | · | non conducting lightcIf there is a matrix
Then
Preferably, the pixel value matrix in step six has the following form:
where f (v, u) is the corresponding pixel value at point (v, u) in the pixel coordinate system, and where the pixel value has been converted to a grayscale range of 0-255.
Preferably, the method for calculating the parallax in the step seven comprises: starting from the position of the left image, which is the same as the window to be matched, only searching on the epipolar line is needed to determine the optimal matching point, and the u of the optimal matching point in the left image can be obtained under the pixel coordinateLU of pixel to be matched in right imageRI.e. the parallax d ═ uL-uR。
Preferably, the final parallax calculation method in the step eight is as follows: under the condition that other conditions are not changed, taking a plurality of interval numbers K to form a plurality of groups of windows to be matched; repeating the sixth step and the seventh step, and calculating the parallax value corresponding to the interval number K
Weighted average is carried out on each parallax value according to the reciprocal of the corresponding interval number, as shown in the following formula,
the final parallax D is obtained.
The invention has the beneficial effects that: compared with the prior art, the method can obviously improve the precision and speed of parallax measurement.
Drawings
Fig. 1 is a schematic flow chart of a binocular speckle digital image correlation parallax measurement method according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a hardware structure of the binocular measuring system according to the embodiment of the present invention.
Fig. 3 is a schematic diagram of selecting a part of a data matrix in a right image as a window to be matched according to an embodiment of the present invention.
FIG. 4 is a diagram illustrating an improved matching process of a normalized cross-correlation algorithm according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
The invention aims to provide a binocular digital speckle image related parallax measurement method, which improves the precision and speed of parallax measurement. In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments.
The embodiment is a binocular digital speckle image-related parallax measurement method, and as shown in the flow diagram of fig. 1, the specific steps are as follows.
Step one, a binocular stereo vision measuring system is built, so that a left camera and a right camera are placed in parallel, the binocular stereo vision measuring system is composed of the left camera, the right camera and a projection device, the relative positions of the left camera and the right camera are fixed, and a schematic diagram of a hardware structure is shown in fig. 2.
Firstly, calibrating a left camera and a right camera by adopting a solid circular array calibration plate to respectively obtain internal parameters and external parameters of the left camera and the right camera, and specifically, calibrating by the following steps.
And 2.1, under the environment with proper light, enabling the circle center calibration plate to be positioned at different positions in the image, and enabling the interested area to be positioned in the image all the time. The left camera and the right camera are simultaneously used for collecting, and the number of the obtained calibration images is preferably 10-20.
And 2.2, processing the acquired image, and extracting the pixel coordinates (u, v) of the characteristic points in the region of interest. Assuming a plane corresponding to the calibration image as z in the world coordinate systemwA plane of 0, the world coordinates (x) of the feature points are extractedw，yw). A Zhang Zhengyou calibration method is adopted in the calibration process, and the coordinates under the pixel coordinate system and the world coordinate system have the following mapping relation:
wherein s is a proportional coefficient of any scale, M is an internal reference matrix, r1、r2The first two columns of the rotation matrix are respectively, t is a translation matrix, and H is a homography matrix.
And thirdly, acquiring the speckle images with controllable distribution density, and setting the resolution of the speckle images, the speckle distribution constraint window, the sizes of the speckles and the like.
And step four, projecting the single speckle image to the surface of the measured object, and synchronously acquiring the left image and the right image by the left camera and the right camera.
Step five, a point P on the space is imaged by the left camera and the right camera to be P1 and P2, and P2 is necessarily on an epipolar line relative to P1; and carrying out limit correction on the left image and the right image so that the matching range of the characteristic points is reduced from the two-dimensional image to a one-dimensional polar line.
And sixthly, matching pixel by adopting an improved normalized cross-correlation algorithm based on the gray level image.
And 6.1, selecting a window with a certain shape and size by taking the right image as a basic module. On the right image, the selection situation of the window to be matched is shown in fig. 3, and the image on the right side of fig. 3 is an enlarged image of the window to be matched. R1For the pixel matrix to the left of the pixel to be matched, R2Is a matrix of pixels to the right of the pixel to be matched.
Step 6.2, in a certain range on the epipolar line of the left image, searching is carried out by windows with the same shape and size, and the matching process of calculating the normalized cross-correlation coefficient by adopting the improved normalized cross-correlation algorithm based on the gray level image is shown in figure 4. The following formula is specifically adopted:
wherein, CNCCTo normalize the cross-correlation coefficient, the larger the normalized cross-correlation coefficient and closer to 1, the higher the correlation, and thus may be considered an optimal match. L1 and L2 are matrices of pixel values across corresponding points in the left image,
and
respectively, are transposed thereto.
To trace the corresponding matrix.
Defining matrix norm | · | non conducting lightcIf there is a matrix
Then
Here, the
Wherein the selection of the matrix of pixel values can be expressed as the following equation,
wherein, (2M +1) is the height of the selected pixel matrix, N is the width of the selected pixel matrix, and K is the number of pixels between the left and right pixel matrices and the pixel points to be matched. Where f (v, u) is the corresponding pixel value at point (v, u) in the pixel coordinate system, and where the pixel value has been converted to a grayscale range of 0-255.
Step seven, for the selection of the window to be matched, a plurality of groups of different interval numbers K (K1, 2.., 100) are selected, and pixel matrixes under different interval numbers are obtained
And
because the selection of the windows to be matched is different, the normalized cross correlation coefficient at the moment can be calculated
Therefore, the optimal matching pixel point of the pixel point to be matched in the right image in the left image can be known.
Step eight, under the pixel coordinates, the pixel coordinates in the horizontal direction of the pixel points in the left image are optimally matched
The pixel coordinate in the horizontal direction of the pixel point to be matched in the right image
The difference between, dK, i.e. parallax
All the disparity values (d)1，d2，...，d100) The weighted average is performed according to the reciprocal of the interval number K, and the calculation formula is as follows:
the final parallax D is obtained.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (8)
1. A binocular digital speckle image related parallax measurement method is characterized by comprising the following steps:
building a binocular stereo vision measuring system, wherein the binocular stereo vision measuring system consists of a left camera, a right camera and a projection device, so that the left camera and the right camera are placed in parallel;
calibrating the left camera and the right camera by adopting a solid circular array calibration plate to respectively obtain the internal parameters and the external parameters of the left camera and the right camera;
acquiring a speckle image with controllable distribution density, and setting the resolution of the speckle image, a speckle distribution constraint window, the size of speckles and the like;
projecting a single speckle image to the surface of a measured object, and synchronously acquiring a left image and a right image by using a left camera and a right camera;
a point P on the space is imaged by the left camera and the right camera to be P1、P2，P2Must be in relation to P1On the polar line of (A); carrying out limit correction on the left image and the right image so as to reduce the matching range of the characteristic points from the two-dimensional image to a one-dimensional polar line;
taking the right image as a basic module and taking the pixel point as a center, and selecting a window to be matched with a certain shape and size; performing pixel-by-pixel matching in a certain range on the epipolar line of the left image, and searching in windows with the same shape and size; obtaining an optimal matching point corresponding to a pixel in a right image in a left image by adopting an improved normalized cross-correlation algorithm based on a gray image;
and seventhly, under the pixel coordinate, optimally matching the pixel coordinate u in the horizontal direction of the pixel point in the left image according to the optimal matching relation of the pixel pointsLThe pixel coordinate u of the pixel point to be matched in the right image in the horizontal directionRThe difference between them is the parallax, i.e. d ═ uL-uR；
Under the condition that other conditions are not changed, taking a plurality of interval numbers K to form a plurality of groups of windows to be matched; repeating the sixth step and the seventh step to calculate the parallax value corresponding to the interval K
And carrying out weighted average on all the parallax values according to the reciprocal of the interval number to obtain the final parallax D, wherein the unit is pixel.
2. The binocular digital speckle image-correlated parallax measurement method of claim 1, wherein in the first step, the left and right cameras and the projection device are positioned on the same horizontal line.
3. The binocular digital speckle image-related parallax measurement method according to claim 1, wherein in the second step, a solid circular array calibration plate is adopted, a Zhang-Yongyou calibration method is adopted in the calibration process, and the coordinates of the feature points in the pixel coordinate system and the world coordinate system have the following mapping relationship:
wherein (u, v) is the coordinate of the characteristic point in the pixel coordinate system, s is the proportionality coefficient of any scale, M is the internal reference matrix, r is1、r2The first two columns of the rotation matrix, respectively, t is the translation matrix, (x)W，yW) And H is a homography matrix.
4. The binocular digital speckle image-related parallax measurement method according to claim 1, wherein the selection of the matching window in the sixth step is performed by taking a pixel point in the right image as a center, spacing K pixels on both sides thereof, and selecting a ratio of height to width of (2M + 1): two rectangular blocks of N form a matching window, and the data matrix on the left of the pixel point is R1The right data matrix is R2。
5. The binocular digital speckle image-related parallax measurement method according to claim 1, wherein in step six, an improved normalized cross-correlation algorithm based on gray level images is adopted for matching, and finally corresponding matching points in the left and right images are determined;
the matching process is implemented by searching for optimal matching in the same line and performing parallel processing, and adopts the following formula:
wherein, CNCCTo normalize the cross-correlation coefficient, the larger the normalized cross-correlation coefficient and closer to 1, the higher the correlation, which can be considered as an optimal match,
L1and L2A matrix of pixel values for both sides of the corresponding point in the left image,
and
are respectively the transposing of the two,
defining matrix norm | · | non conducting lightcIf there is a matrix
Then
6. The binocular digital speckle image-related parallax measurement method according to claim 5, wherein the pixel value matrix in the sixth step has the following form:
where f (v, u) is the corresponding pixel value at point (v, u) in the pixel coordinate system, and where the pixel value has been converted to a grayscale range of 0-255.
7. The binocular digital speckle image-related parallax measurement method according to claim 1, wherein the parallax calculation method in the seventh step is: starting from the position of the left image, which is the same as the window to be matched, only searching on the epipolar line is needed to determine the optimal matching point, and the u of the optimal matching point in the left image can be obtained under the pixel coordinateLU of pixel to be matched in right imageRI.e. the parallax d ═ uL-uR。
8. The binocular digital speckle image-related parallax measurement method according to claim 1, wherein the final parallax calculation method in the step eight is: under the condition that other conditions are not changed, taking a plurality of interval numbers K to form a plurality of groups of windows to be matched; repeating the sixth step and the seventh step, and calculating the parallax value corresponding to the interval number K
Weighted average is carried out on each parallax value according to the reciprocal of the corresponding interval number, as shown in the following formula,
the final parallax D is obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110847673.0A CN113808070B (en) | 2021-07-26 | 2021-07-26 | Binocular digital speckle image related parallax measurement method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110847673.0A CN113808070B (en) | 2021-07-26 | 2021-07-26 | Binocular digital speckle image related parallax measurement method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113808070A true CN113808070A (en) | 2021-12-17 |
| CN113808070B CN113808070B (en) | 2024-06-07 |
Family
ID=78893187
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110847673.0A Active CN113808070B (en) | 2021-07-26 | 2021-07-26 | Binocular digital speckle image related parallax measurement method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113808070B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332373A (en) * | 2021-12-29 | 2022-04-12 | 华侨大学 | Magnetic circuit fall detection method and system for overcoming light reflection of metal surface of relay |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106595528A (en) * | 2016-11-10 | 2017-04-26 | 华中科技大学 | Digital speckle-based telecentric microscopic binocular stereoscopic vision measurement method |
| US20170154436A1 (en) * | 2015-05-27 | 2017-06-01 | Zhuhai Ritech Technology Co. Ltd. | Stereoscopic vision three dimensional measurement method and system for calculating laser speckle as texture |
| CN111145342A (en) * | 2019-12-27 | 2020-05-12 | 山东中科先进技术研究院有限公司 | Binocular speckle structured light three-dimensional reconstruction method and system |
| WO2021138993A1 (en) * | 2020-01-10 | 2021-07-15 | 大连理工大学 | Parallax image fusion method for multi-band stereo camera |
-
2021
- 2021-07-26 CN CN202110847673.0A patent/CN113808070B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20170154436A1 (en) * | 2015-05-27 | 2017-06-01 | Zhuhai Ritech Technology Co. Ltd. | Stereoscopic vision three dimensional measurement method and system for calculating laser speckle as texture |
| CN106595528A (en) * | 2016-11-10 | 2017-04-26 | 华中科技大学 | Digital speckle-based telecentric microscopic binocular stereoscopic vision measurement method |
| CN111145342A (en) * | 2019-12-27 | 2020-05-12 | 山东中科先进技术研究院有限公司 | Binocular speckle structured light three-dimensional reconstruction method and system |
| WO2021138993A1 (en) * | 2020-01-10 | 2021-07-15 | 大连理工大学 | Parallax image fusion method for multi-band stereo camera |
Non-Patent Citations (1)
| Title |
|---|
| 钟锦鑫;尹维;冯世杰;陈钱;左超;: "基于深度学习的散斑投影轮廓术", 红外与激光工程, no. 06, 25 June 2020 (2020-06-25) * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332373A (en) * | 2021-12-29 | 2022-04-12 | 华侨大学 | Magnetic circuit fall detection method and system for overcoming light reflection of metal surface of relay |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113808070B (en) | 2024-06-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109919911B (en) | Mobile three-dimensional reconstruction method based on multi-view photometric stereo | |
| CN110070598B (en) | Mobile terminal for 3D scanning reconstruction and 3D scanning reconstruction method thereof | |
| CN104537707B (en) | Image space type stereoscopic vision moves real-time measurement system online | |
| CN111667536A (en) | Parameter calibration method based on zoom camera depth estimation | |
| CN110728671A (en) | Dense reconstruction method of texture-free scene based on vision | |
| CN111192235A (en) | Image measuring method based on monocular vision model and perspective transformation | |
| CN110517211B (en) | Image fusion method based on gradient domain mapping | |
| CN110910456B (en) | Three-dimensional camera dynamic calibration method based on Harris angular point mutual information matching | |
| WO2018032841A1 (en) | Method, device and system for drawing three-dimensional image | |
| CN111709985A (en) | Underwater target ranging method based on binocular vision | |
| CN116129037B (en) | Visual touch sensor, three-dimensional reconstruction method, system, equipment and storage medium thereof | |
| Eichhardt et al. | Affine correspondences between central cameras for rapid relative pose estimation | |
| CN107679542B (en) | Double-camera stereoscopic vision identification method and system | |
| CN111951339A (en) | Image processing method for performing parallax calculation by using heterogeneous binocular cameras | |
| CN113808070B (en) | Binocular digital speckle image related parallax measurement method | |
| CN111429571B (en) | Rapid stereo matching method based on spatio-temporal image information joint correlation | |
| CN116630423A (en) | ORB (object oriented analysis) feature-based multi-target binocular positioning method and system for micro robot | |
| CN108090930A (en) | Barrier vision detection system and method based on binocular solid camera | |
| CN107103620B (en) | Depth extraction method of multi-optical coding camera based on spatial sampling under independent camera view angle | |
| Wang et al. | Facilitating PTZ camera auto-calibration to be noise resilient with two images | |
| CN112950727B (en) | Large-view-field multi-target simultaneous ranging method based on bionic curved compound eye | |
| CN114511631A (en) | Method and device for measuring height of visual object of camera and computer readable storage medium | |
| JP2018133064A (en) | Image processing apparatus, imaging apparatus, image processing method, and image processing program | |
| JP2018081378A (en) | Image processing apparatus, imaging device, image processing method, and image processing program | |
| CN113971629A (en) | Image restoration method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant |