CN111476836B - Parallax optimization method and device based on image segmentation - Google Patents
Parallax optimization method and device based on image segmentation Download PDFInfo
- Publication number
- CN111476836B CN111476836B CN202010600271.6A CN202010600271A CN111476836B CN 111476836 B CN111476836 B CN 111476836B CN 202010600271 A CN202010600271 A CN 202010600271A CN 111476836 B CN111476836 B CN 111476836B
- Authority
- CN
- China
- Prior art keywords
- block
- image
- parallax
- color
- disparity
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000005457 optimization Methods 0.000 title claims abstract description 37
- 238000003709 image segmentation Methods 0.000 title claims abstract description 16
- 230000006835 compression Effects 0.000 claims abstract description 16
- 238000007906 compression Methods 0.000 claims abstract description 16
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000000638 solvent extraction Methods 0.000 claims abstract description 4
- 238000013507 mapping Methods 0.000 claims description 13
- 239000003086 colorant Substances 0.000 claims description 6
- 238000009826 distribution Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000000903 blocking effect Effects 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 21
- 230000009471 action Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 2
- 208000037170 Delayed Emergence from Anesthesia Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000010813 municipal solid waste Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000007704 transition 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
- G06T7/50—Depth or shape recovery
- G06T7/55—Depth or shape recovery from multiple images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The application discloses a parallax optimization method and a device based on image segmentation, wherein the method comprises the following steps: acquiring a binocular image and performing color compression on the binocular image; extracting edge information of the binocular image; partitioning the compressed image, and calculating a correlation coefficient between each block and an adjacent block according to the relationship among the area, the color and the edge information between the block and the adjacent block; merging each block according to the correlation coefficient; and optimizing the parallax of the combined image by using a refine iterative algorithm with block-level granularity, determining whether optimization is needed according to the parallax information between each block and the adjacent block, and always keeping the cost function of the image reduced until the parallax is stable in the iterative optimization process.
Description
Technical Field
The invention belongs to the technical field of computer vision, and relates to a parallax optimization method and a parallax optimization device based on image segmentation.
Background
The binocular stereo vision technology is a technology for constructing stereo vision by using images of two lenses in a binocular camera at the same time, generally, the stereo vision is described by using parallax or depth, so that distance difference is perceived, and full-field 3D measurement can be provided in unstructured and dynamic environments. Stereo vision techniques may be used for a variety of applications, including person tracking, mobile robot navigation, and mining. It can also be used in industrial automation and 3D machine vision applications to perform certain tasks such as trash bin picking, volume measurement, automotive part measurement, and 3D object location and identification.
However, in the practical application process, some stereoscopic vision matching algorithms at present have some problems, and due to inherent differences between two lenses, images obtained by the two lenses have certain differences, and the differences can cause matching results, that is, disparity maps are very uneven, and abnormal disparities such as burrs, holes and the like can occur.
Disclosure of Invention
The invention aims to provide a parallax optimization method and a parallax optimization device based on image segmentation, which can improve the overall uniformity of a parallax image.
An embodiment of the present application provides a disparity optimization method based on image segmentation, including:
acquiring a binocular image and performing color compression on the binocular image;
extracting edge information of the binocular image;
partitioning the compressed image, and calculating a correlation coefficient between each block and an adjacent block according to the relationship among the area, the color and the edge information between the block and the adjacent block;
merging each block according to the correlation coefficient;
and optimizing the parallax of the combined image by using a refine iterative algorithm with block-level granularity, determining whether optimization is needed according to the parallax information between each block and the adjacent block, and always keeping the cost function of the image reduced until the parallax is stable in the iterative optimization process.
In a preferred embodiment, the step of obtaining a binocular image and performing color compression on the binocular image further includes:
respectively counting the color distribution of a plurality of channels of the binocular image and calculating an image histogram;
sorting the image histograms from large to small according to the distribution of the number of pixels, selecting peak values according to the sparsity of colors in each image histogram, taking the color positions of which the number of pixels is larger than the average value in the histogram as peak values, and enabling the color interval between adjacent peak values to be larger than a preset threshold value;
mapping the residual color values in the histogram to one peak value which is closest to the selected peak value to construct a mapping table;
and mapping the binocular image to a compressed color space according to the mapping table.
In a preferred example, the step of extracting the edge information of the binocular image further includes: and extracting edge information of the binocular image by using a canny edge detection algorithm.
In a preferred embodiment, the step of calculating the correlation coefficient between each block and the adjacent block according to the relationship between the area, the color and the edge information between the block and the adjacent block further includes:
the correlation coefficient is calculated by the following formula:
where R denotes a correlation coefficient, AREA denotes a common AREA, BD denotes a common edge length, CD denotes a color distance, and SD denotes a spatial distance.
In a preferred embodiment, the step of optimizing the parallax of the merged image with a granularity of a block level by using a refine iterative algorithm further includes:
taking the sum of the absolute values of the disparity and difference of the merged blocks as initial iteration data, and calculating an initial disparity cost function Dpost and a smoothing cost function Scpost,
wherein the sad _ list stores the sum of absolute values of the differences corresponding to each disparity, disp is the disparity of the current block, init _ disp is the initial disparity,is the disparity of the i-th neighboring block,is a correlation coefficient between the current block and the i-th neighboring block;
iterating through each blockInstead, the disparity Disp of the current block is recalculated(i),
Wherein trans is the ratio of the parallax confidence between the current block and the adjacent block, and the parallax confidence of each block is the minimum value in the sad _ list;
and recalculating the iterated parallax cost function Dpost and the smooth cost function Scost, and if the change of the parallax cost function Dpost and the smooth cost function Scost is less than a preset threshold value, not iterating.
In a preferred example, the disparity cost function Dcost at the initial iteration is 1.
The present application further discloses a parallax optimization device based on image segmentation in another embodiment, including:
the color compression module is used for acquiring binocular images and performing color compression on the binocular images;
an edge extraction module configured to extract edge information of the binocular image;
a blocking module configured to block the compressed image, and calculate a correlation coefficient between each block and an adjacent block according to a relationship between an area, a color, and edge information between the block and the adjacent block;
a merging module configured to merge the respective blocks according to the correlation coefficient;
and the parallax optimization module is configured to optimize the parallax of the merged image by using a refine iterative algorithm with the granularity of a block level, determine whether optimization is needed according to the parallax information between each block and the adjacent block, and always keep the cost function of the image reduced until the parallax is stable in the iterative optimization process.
The present application also discloses a computer-readable storage medium having stored therein computer-executable instructions which, when executed by a processor, implement the steps in the method as described hereinbefore.
Compared with the prior art, the method has the following beneficial effects:
in this embodiment, disparity optimization is performed based on image segmentation, the color-compressed image is partitioned, merging is performed according to the correlation coefficient between each block and an adjacent block, and disparity optimization is performed at the block level, so that the overall disparity of the obtained disparity map is uniform, natural in transition, and convenient for subsequent continuous use.
Drawings
Fig. 1 is a flowchart of a disparity optimization method based on image segmentation according to an embodiment of the present invention.
FIG. 2a is a color histogram of an original image before color compression according to an embodiment of the present invention;
FIG. 2b is a color histogram after color compression according to an embodiment of the present invention.
Detailed Description
In the following description, numerous technical details are set forth in order to provide a better understanding of the present application. However, it will be understood by those skilled in the art that the technical solutions claimed in the present application can be implemented without these technical details and with various changes and modifications based on the following embodiments.
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.
An embodiment of the present application provides a parallax optimization method based on image segmentation, and fig. 1 is a flowchart of the parallax optimization method in the embodiment, where the method includes:
In an embodiment, the step 101 of acquiring a binocular image and performing color compression on the binocular image further includes:
counting color distributions of a plurality of channels of the binocular image and calculating an image histogram, respectively, for example, as shown in fig. 2 a;
according to the distribution of the number of pixels of the color histogram of the image, sequencing corresponding colors of the pixel histograms according to the number of the pixels from large to small, traversing the sequenced color histograms, taking the color position of the histogram with the number of the corresponding pixels larger than the mean value as a peak value, and controlling the color interval between adjacent peak values to be larger than a threshold value 8 so as to avoid over-dense;
mapping the residual color values of various colors in the color channel to the positions of the peak values with the shortest distance of the colors according to the principle of proximity, and then obtaining the peak values corresponding to all the colors respectively so as to form a color mapping table;
and according to the color mapping table, taking out the corresponding new color from each pixel in the binocular image according to the color mapping relationship of the mapping table, so as to form a new image formed by the mapped new color, namely the image after color space compression, and obtain the compressed image shown in fig. 2 b.
And 102, extracting edge information of the binocular image.
In an embodiment, the step of extracting the edge information of the binocular image further includes: using a canny edge detection algorithm to extract edge information of the binocular image, wherein the canny edge detection firstly carries out noise reduction processing on the image through Gaussian filtering, calculates the gradient value and the direction of the image to express the change degree of the gray value, then filters out non-maximum value areas, and finally uses upper and lower threshold values to judge the edge, pixels with the gradient value larger than the upper threshold value are judged as the edge, pixels smaller than the lower threshold value are judged as the non-edge, pixels adjacent to edge points in the middle area are also judged as the edge, and the upper and lower threshold values used in the patent are respectively 30 and 100.
and 104, merging the blocks according to the correlation coefficient. Specifically, when the correlation coefficient is greater than the threshold, the adjacent small blocks are considered to be very close to the current block, and it is considered that the two small blocks can be merged into the same block. And after merging, continuously traversing the merged blocks until no neighbor small blocks with the correlation coefficient larger than the threshold value appear, namely the current block cannot be merged, and then finishing the merging of the current block. And the subsequent residual blocks are also merged according to the method, when the correlation coefficients between all the blocks and the surrounding blocks can not meet the threshold value, the blocks can not be merged any more, and the merging is completed at this moment.
In an embodiment, the step of optimizing the disparity of the merged image with a granularity of a block level using a refine iterative algorithm further comprises:
taking the sum of the absolute values of the disparity and difference of the merged blocks as initial iteration data, and calculating an initial disparity cost function Dpost and a smoothing cost function Scpost,
wherein the sad _ list is stored everyThe sum of absolute values of differences corresponding to the disparities, disp is the disparity of the current block, init _ disp is the initial disparity,is the disparity of the i-th neighboring block,is a correlation coefficient between the current block and the i-th neighboring block;
iterating through each block, and recalculating the parallax Disp of the current block(i),
Wherein trans is the ratio of the parallax confidence between the current block and the adjacent block, and the parallax confidence of each block is the minimum value in the sad _ list;
and recalculating the iterated parallax cost function Dpost and the smooth cost function Scost, and if the change of the parallax cost function Dpost and the smooth cost function Scost is less than a preset threshold value, not iterating.
In an embodiment, the disparity cost function Dcost at the initial iteration is 1.
The second embodiment of the present application further discloses a binocular stereo matching preprocessing device, including:
the color compression module is used for acquiring binocular images and performing color compression on the binocular images;
an edge extraction module configured to extract edge information of the binocular image;
a blocking module configured to block the compressed image, and calculate a correlation coefficient between each block and an adjacent block according to a relationship between an area, a color, and edge information between the block and the adjacent block;
a merging module configured to merge the respective blocks according to the correlation coefficient;
and the parallax optimization module is configured to optimize the parallax of the merged image by using a refine iterative algorithm with the granularity of a block level, determine whether optimization is needed according to the parallax information between each block and the adjacent block, and always keep the cost function of the image reduced until the parallax is stable in the iterative optimization process.
Accordingly, other embodiments of the present application may also provide a computer-readable storage medium having stored therein computer-executable instructions that, when executed by a processor, implement the method embodiments of the present application. Computer-readable storage media, including both non-transitory and non-transitory, removable and non-removable media, may implement information storage by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), Static Random Access Memory (SRAM), Dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), Read Only Memory (ROM), Electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), Digital Versatile Discs (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information that can be accessed by a computing device.
It is noted that, in the present patent application, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, the use of the verb "comprise a" to define an element does not exclude the presence of another, same element in a process, method, article, or apparatus that comprises the element. In the present patent application, if it is mentioned that a certain action is executed according to a certain element, it means that the action is executed according to at least the element, and two cases are included: performing the action based only on the element, and performing the action based on the element and other elements. The expression of a plurality of, a plurality of and the like includes 2, 2 and more than 2, more than 2 and more than 2.
In some cases, the actions or steps recited in the claims may be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing may also be possible or may be advantageous.
Claims (7)
1. A parallax optimization method based on image segmentation is characterized by comprising the following steps:
acquiring a binocular image and performing color compression on the binocular image;
extracting edge information of the binocular image;
partitioning the compressed image, and calculating a correlation coefficient between each block and an adjacent block according to the relationship between the area, color and edge information between the block and the adjacent block, wherein the correlation coefficient is calculated by the following formula:
wherein R represents a correlation coefficient, AREA represents a common AREA, BD represents a common edge length, CD represents a color distance, and SD represents a spatial distance;
merging each block according to the correlation coefficient;
and optimizing the parallax of the combined image by using a refine iterative algorithm with block-level granularity, determining whether optimization is needed according to the parallax information between each block and the adjacent block, and always keeping the cost function of the image reduced until the parallax is stable in the iterative optimization process.
2. The image segmentation based parallax optimization method according to claim 1, wherein the step of obtaining binocular images and performing color compression on the binocular images further comprises:
respectively counting the color distribution of a plurality of channels of the binocular image and calculating an image histogram;
sorting the image histograms from large to small according to the distribution of the number of pixels, selecting peak values according to the sparsity of colors in each image histogram, taking the color positions of which the number of pixels is larger than the average value in the histogram as peak values, and enabling the color interval between adjacent peak values to be larger than a preset threshold value;
mapping the residual color values in the histogram to one peak value which is closest to the selected peak value to construct a mapping table;
and mapping the binocular image to a compressed color space according to the mapping table.
3. The image segmentation-based parallax optimization method according to claim 1, wherein the step of extracting the edge information of the binocular image further comprises: and extracting edge information of the binocular image by using a canny edge detection algorithm.
4. The image segmentation based disparity optimization method of claim 1, wherein the step of optimizing the disparity of the merged image with a block-level granularity using a refine iterative algorithm further comprises:
taking the sum of the absolute values of the disparity and difference of the merged blocks as initial iteration data, and calculating an initial disparity cost function Dpost and a smoothing cost function Scpost,
wherein the sad _ list stores the sum of absolute values of the differences corresponding to each disparity, disp is the disparity of the current block, init _ disp is the initial disparity,is the disparity of the i-th neighboring block,is a correlation coefficient between the current block and the i-th neighboring block;
iterating through each block, and recalculating the parallax Disp of the current block(i),
Wherein trans is the ratio of the parallax confidence between the current block and the adjacent block, and the parallax confidence of each block is the minimum value in the sad _ list;
and recalculating the iterated parallax cost function Dpost and the smooth cost function Scost, and if the change of the parallax cost function Dpost and the smooth cost function Scost is less than a preset threshold value, not iterating.
5. An image segmentation based disparity optimization method according to claim 4, wherein the disparity cost function Dcot at the initial iteration is 1.
6. A parallax optimization apparatus based on image segmentation, comprising:
the color compression module is used for acquiring binocular images and performing color compression on the binocular images;
an edge extraction module configured to extract edge information of the binocular image;
a blocking module configured to block the compressed image, calculate a correlation coefficient between each block and an adjacent block according to a relationship between an area, a color, and edge information between the block and the adjacent block, the correlation coefficient being calculated by the following formula:
wherein R represents a correlation coefficient, AREA represents a common AREA, BD represents a common edge length, CD represents a color distance, and SD represents a spatial distance;
a merging module configured to merge the respective blocks according to the correlation coefficient;
and the parallax optimization module is configured to optimize the parallax of the merged image by using a refine iterative algorithm with the granularity of a block level, determine whether optimization is needed according to the parallax information between each block and the adjacent block, and always keep the cost function of the image reduced until the parallax is stable in the iterative optimization process.
7. A computer-readable storage medium having stored thereon computer-executable instructions which, when executed by a processor, implement the steps in the method of any one of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010600271.6A CN111476836B (en) | 2020-06-29 | 2020-06-29 | Parallax optimization method and device based on image segmentation |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010600271.6A CN111476836B (en) | 2020-06-29 | 2020-06-29 | Parallax optimization method and device based on image segmentation |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111476836A CN111476836A (en) | 2020-07-31 |
CN111476836B true CN111476836B (en) | 2020-11-13 |
Family
ID=71764023
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010600271.6A Active CN111476836B (en) | 2020-06-29 | 2020-06-29 | Parallax optimization method and device based on image segmentation |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111476836B (en) |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US8385630B2 (en) * | 2010-01-05 | 2013-02-26 | Sri International | System and method of processing stereo images |
CN103702098B (en) * | 2013-12-09 | 2015-12-30 | 上海交通大学 | Three viewpoint three-dimensional video-frequency depth extraction methods of constraint are combined in a kind of time-space domain |
CN104680510B (en) * | 2013-12-18 | 2017-06-16 | 北京大学深圳研究生院 | RADAR disparity maps optimization method, Stereo matching disparity map optimization method and system |
CN104331890B (en) * | 2014-10-30 | 2017-06-16 | 北京大学深圳研究生院 | A kind of global disparity method of estimation and system |
-
2020
- 2020-06-29 CN CN202010600271.6A patent/CN111476836B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN111476836A (en) | 2020-07-31 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102930530B (en) | Stereo matching method of double-viewpoint image | |
CN111210429B (en) | Point cloud data partitioning method and device and obstacle detection method and device | |
CN111553946B (en) | Method and device for removing ground point cloud and method and device for detecting obstacle | |
CN111582054A (en) | Point cloud data processing method and device and obstacle detection method and device | |
Tan et al. | Stereo disparity through cost aggregation with guided filter | |
CN106530336A (en) | Stereo matching algorithm based on color information and graph-cut theory | |
CN104331890A (en) | Method and system for estimating global disparity | |
CN107798694A (en) | A kind of pixel parallax value calculating method, device and terminal | |
KR101766431B1 (en) | Method and apparatus for detecting disparity by using hierarchical stereo matching | |
Zhang et al. | Local stereo matching: An adaptive weighted guided image filtering-based approach | |
Mukherjee et al. | A hybrid algorithm for disparity calculation from sparse disparity estimates based on stereo vision | |
CN111476836B (en) | Parallax optimization method and device based on image segmentation | |
Borisagar et al. | A novel segment-based stereo matching algorithm for disparity map generation | |
Wang et al. | Robust obstacle detection based on a novel disparity calculation method and G-disparity | |
KR101178015B1 (en) | Generating method for disparity map | |
CN111508009B (en) | Binocular stereo matching preprocessing method and device | |
CN113344988B (en) | Stereo matching method, terminal and storage medium | |
Vosters et al. | Efficient and stable sparse-to-dense conversion for automatic 2-D to 3-D conversion | |
Zhang et al. | Local stereo disparity estimation with novel cost aggregation for sub-pixel accuracy improvement in automotive applications | |
Ishikawa | Multi-scale feature selection in stereo | |
CN110910438B (en) | High-speed stereo matching algorithm for ultrahigh-resolution binocular image | |
Shin et al. | Visual stereo matching combined with intuitive transition of pixel values | |
Lim et al. | Depth map rasterization using triangulation and color consistency for various sampling structures | |
KR101220003B1 (en) | Generating method for disparity map | |
Kalomiros | Dense disparity features for fast stereo vision |
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 | ||
GR01 | Patent grant | ||
CP03 | Change of name, title or address |
Address after: Room 411, 4th floor, main building, No. 835 and 937, Dangui Road, China (Shanghai) pilot Free Trade Zone, Pudong New Area, Shanghai, 200131 Patentee after: Shanghai hailichuang Technology Co.,Ltd. Address before: 201203 Room 411, 4th Floor, Main Building (1 Building) of Zhangjiang Guochuang Center, 899 Dangui Road, Pudong New Area, Shanghai Patentee before: SHANGHAI HYNITRON MICROELECTRONIC Co.,Ltd. |
|
CP03 | Change of name, title or address |