CN107452003A - A kind of method and device of the image segmentation containing depth information - Google Patents
A kind of method and device of the image segmentation containing depth information Download PDFInfo
- Publication number
- CN107452003A CN107452003A CN201710525948.2A CN201710525948A CN107452003A CN 107452003 A CN107452003 A CN 107452003A CN 201710525948 A CN201710525948 A CN 201710525948A CN 107452003 A CN107452003 A CN 107452003A
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- image segmentation
- information
- region
- 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.)
- Pending
Links
- 238000003709 image segmentation Methods 0.000 title claims abstract description 61
- 238000000034 method Methods 0.000 title claims abstract description 23
- 238000004422 calculation algorithm Methods 0.000 claims description 12
- 238000004364 calculation method Methods 0.000 claims description 12
- 238000004590 computer program Methods 0.000 claims description 5
- 230000011218 segmentation Effects 0.000 abstract description 10
- 238000005267 amalgamation Methods 0.000 abstract 1
- 238000005457 optimization Methods 0.000 abstract 1
- 238000005192 partition Methods 0.000 abstract 1
- 230000008092 positive effect Effects 0.000 abstract 1
- 239000013598 vector Substances 0.000 description 6
- 230000006870 function Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of method of the image segmentation containing depth information, comprise the following steps:Obtaining step:The information that clicks of user's input is obtained, and image to be split is divided into each region unit, the information that clicks is the pixel on image to be split;Judgment step:Judge that pixel belongs to foreground area or background area on each region unit according to information is clicked;First image segmentation step:The result of pixel on each region unit is judged according to confidence collection of illustrative plates to realize that image is split.The invention also discloses a kind of electronic equipment, computer-readable recording medium and containing depth information image segmentation device.The method of the segmentation of the image containing depth information of the present invention automatically generates segmentation tag to different characteristics of image, then the label generated under different characteristic is carried out amalgamation judging, ultimately forms the image splitting scheme of optimization;The image partition method of present invention test result positive effect on five big RGBD data sets is more preferable.
Description
Technical Field
The present invention relates to the field of image processing technologies, and in particular, to a method and an apparatus for segmenting an image containing depth information.
Background
Currently, in the field of image processing, there is a great demand for foreground and background segmentation of images, such as people in images often need to be segmented and synthesized into other backgrounds. In a foreground and background segmentation algorithm in the related art, a statistical model is respectively constructed for a foreground and a background according to a part of foreground and background areas specified by a user, and the statistical regularity of respective pixels is represented; because of the limitation of the precision of the statistical model, if the model components are more, the foreground and background models are easy to be confused; if the model component is less, some important features are easy to miss, so the segmentation fineness is not ideal.
Image intelligent segmentation is an important problem in computer vision, including image editing, target recognition and image retrieval. Most existing intelligent segmentation methods operate only on RGB images. Until recently, some companies and researchers began to segment images using RGB-D information generated by a depth sensor represented by Kinect, that is, segment the edges of different objects in the images intelligently and automatically. However, due to the long length of some key objects in the volume or depth dimension, or similar positions of different objects in the depth, depth information often does not simply help the image segmentation effect.
Disclosure of Invention
In order to overcome the defects of the prior art, one of the objectives of the present invention is to provide a method for image segmentation containing depth information, which can solve the technical problem of image segmentation.
Another object of the present invention is to provide an electronic device, which can solve the technical problem of image segmentation.
It is a further object of the present invention to provide a computer-readable storage medium that solves the technical problem of image segmentation.
It is a fourth object of the present invention to provide an image segmentation apparatus including depth information, which can solve the technical problem of image segmentation.
One of the purposes of the invention is realized by adopting the following technical scheme:
a method of image segmentation with depth information, comprising the steps of:
an acquisition step: acquiring click information input by a user, and dividing an image to be segmented into region blocks, wherein the click information is pixel points on the image to be segmented;
a judging step: judging whether the pixel points on each region block belong to the foreground region or the background region according to the clicking information;
a first image segmentation step: and judging the pixel characteristics of the pixel points on each region block according to the confidence map so as to realize image segmentation.
Further, the step of determining specifically includes the following substeps:
and (3) label pair distribution step: introducing a label pair into each pixel point on an image to be segmented, wherein the label pair comprises pixel attributes and pixel characteristics;
and (3) judging the label pair: and judging whether the pixel points on each area block belong to the foreground area or the background area according to the label pair.
Further, the first image segmentation step specifically includes the following sub-steps:
geodesic distance calculation step: calculating the geodesic distance of the pixel points on each region block relative to the pointing information according to the pixel characteristics;
a probability value calculation step: calculating to obtain a probability value of the pixel point according to the geodesic distance, wherein the probability value is the probability of a foreground pixel point or the probability of a background pixel point;
a second image segmentation step: and performing image segmentation according to the probability value.
Further, a dixter algorithm is employed in the geodesic distance calculation step to find the geodesic distance.
The second purpose of the invention is realized by adopting the following technical scheme:
an electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, the processor implementing the following steps when executing the program:
an acquisition step: acquiring click information input by a user, and dividing an image to be segmented into region blocks, wherein the click information is pixel points on the image to be segmented;
a judging step: judging whether the pixel points on each region block belong to the foreground region or the background region according to the clicking information;
a first image segmentation step: and judging the pixel characteristics of the pixel points on each region block according to the confidence map so as to realize image segmentation.
Further, the step of determining specifically includes the following substeps:
and (3) label pair distribution step: introducing a label pair into each pixel point on an image to be segmented, wherein the label pair comprises pixel attributes and pixel characteristics;
and (3) judging the label pair: and judging whether the pixel points on each area block belong to the foreground area or the background area according to the label pair.
Further, the first image segmentation step specifically includes the following sub-steps:
geodesic distance calculation step: calculating the geodesic distance of the pixel points on each region block relative to the pointing information according to the pixel characteristics;
a probability value calculation step: calculating the probability value of whether the pixel point is a foreground pixel point or a background pixel point according to the calculated geodesic distance,
a second image segmentation step: and performing image segmentation according to the probability value.
Further, a dixter algorithm is employed in the geodesic distance calculation step to find the geodesic distance.
The third purpose of the invention is realized by adopting the following technical scheme:
a computer-readable storage medium, on which a computer program is stored which, when being executed by a processor, carries out the method as described in any one of the above.
The fourth purpose of the invention is realized by adopting the following technical scheme:
an apparatus for image segmentation with depth information, comprising:
an acquisition module: the system comprises a processing unit, a display unit and a processing unit, wherein the processing unit is used for acquiring click information input by a user and dividing an image to be segmented into region blocks, and the click information is pixel points on the image to be segmented;
a judging module: the pixel characteristics are used for judging whether the pixel points on each area block belong to the foreground area or the background area according to the clicking information;
a first image segmentation module: and the image segmentation module is used for judging the pixel characteristics of the pixel points on each area block according to the confidence map so as to realize image segmentation.
Compared with the prior art, the invention has the beneficial effects that:
the image segmentation method containing depth information automatically generates segmentation labels for different image characteristics, and then fusion judgment is carried out on the labels generated under different characteristics to finally form an optimized image segmentation scheme; the image segmentation method has a better test result on five RGBD data sets.
Drawings
FIG. 1 is a flow chart of a method of image segmentation with depth information according to the present invention;
fig. 2 is a configuration diagram of an image segmentation apparatus including depth information according to the present invention.
Detailed Description
The present invention will be further described with reference to the accompanying drawings and the detailed description, and it should be noted that any combination of the embodiments or technical features described below can be used to form a new embodiment without conflict.
The first embodiment is as follows:
as shown in fig. 1, the present invention provides a method for image segmentation with depth information, comprising the following steps:
s1: acquiring click information input by a user, and dividing an image to be segmented into region blocks, wherein the click information is pixel points on the image to be segmented; before image segmentation, a foreground region and a background region are firstly clicked once on an image to be segmented, the two clicks are used as clicking information, and the process is that a learning positive sample and a learning negative sample are respectively given to an algorithm;
assuming that I represents a pixel point on the image I, Ω represents a set formed by all pixels of the image I, and N represents a set formed by adjacent pixel pairs; the interactive image segmentation can be equivalent to the segmentation of omega into two mutually exclusive sets omega according to the click information given by the user1And Ω1I.e. it is expressed as a binary markov random field problem, the energy function is as follows:
wherein S isiThe classification label of the pixel i is represented, and the classification labels of all the pixels are represented by S. If the pixel point i is a background pixel point, SiIf pixel i is a foreground pixel, S is equal to 0i1. D (S) in the formulai) Display handle SiA cost function corresponding to i. D (S)i) Can be expressed as:
D(Si)=-logP(Si)
wherein, P (S)i) The representative pixel i is marked SiThe probability of (c). The probability is set to 1 for a pixel belonging to the foreground or the background specified by the user. In addition, f (S)i,Sj) Represents that a pair is formedIs marked as (S)i,Sj) In an RGB image, f (S)i,Sj) Can be expressed as
Wherein,representing the degree of similarity of adjacent pixels I, j, IiRepresenting the pixel value of pixel i, the cost function becomes small if we label neighboring pixels with different labels. λ represents the equilibrium relationship between unary operators and pixel pairs.
By minimizing E (S), we can obtain the optimal pixel label S*。
S2: judging whether the pixel points on each region block belong to the foreground region or the background region according to the clicking information; the foreground region includes foreground pixel points, the background region includes background pixel points, and the step S2 specifically includes the following sub-steps:
s21: introducing a label pair into each pixel point on an image to be segmented, wherein the label pair comprises pixel attributes and pixel characteristics; introducing a label pair X for each pixel ii=<Si,Ci>In which S isiStill expressed is a classification label of the pixel i, said classification label is the pixel attribute, the pixel belongs to the foreground pixel or the background pixel, if the pixel i is the background pixel, then SiIf pixel i is a foreground pixel, S is equal to 0i=1,CiWhich information is used for making a judgment is shown, and the color feature, the depth feature and the normal vector feature are respectively shown as 0,1 and 2. And marking the color feature, the depth feature and the normal vector feature as pixel features, and linearizing the label pair in a [0,2 x N), so as to obtain a Markov random field model using a mixed label:
s22: and judging whether the pixel points on each area block belong to the foreground area or the background area according to the label pair. For RGBD information, we use three features of pixel i at a time, respectively: color features, depth features and normal vector features are explained, the normal vector features are calculated by a 3D cloud model projected by depth information, three labels are obtained for each pixel point i, then which label is the true correct label is judged, and the pixel point is marked and judged through the label; si
S3: and judging the result of the pixel points on each region block according to the confidence map so as to realize image segmentation. The step S3 specifically includes the following sub-steps:
step S1: calculating the geodesic distance of the pixel points on each region block relative to the pointing information according to the pixel characteristics; the dixotera algorithm is used to find the geodesic distance.
Step S2: calculating to obtain a probability value of the pixel point according to the geodesic distance, wherein the probability value is the probability of a foreground pixel point or the probability of a background pixel point;
step S3: and performing image segmentation according to the probability value.
Establishing a confidence map of the foreground/background, wherein for a single pixel, the cost function of each pixel is as follows:wherein,may represent the likelihood of whether pixel i is foreground or background, as measured by some particular information;
the confidence map is established based on geodesic distance. The advantage of using geodesic distances is that for pixels with similar characteristics but widely differing spatial distances and without strong connectivity, the system does not assign them the same label; in addition, since the depth information shows the physical connection relationship of the pixels, the distance between the pixel i and the user input information can be more effectively measured using the geodesic distance.
The user input being represented by U, U1Representing foreground pixels, U0Representing background pixels. Next, a graph structure G with weights is established in the database, where V denotes a vertex set, E denotes an edge set, and the weights are obtained by using different distance measurement methods for different information: for RGB information, we translate the RGB values into LAB space, using the L2 norm for distance measurement; for depth information, the absolute value of the difference between a pixel and U is taken as a distance measure; for the information of the normal vector, the cosine similarity of unit normal vectors of two pixels is taken as distance measurement; the above is the way of doing the measurement for three different features;
in combination with the knowledge of graph theory, the geodesic distance of any two pixels i and j, which is the shortest path d (i, j) between i and j in the image to be segmented, can be accurately obtained by using the dixtera algorithm. Using this method, one can iteratively derive any one pixel i whose geodesic distance from its nearest known foreground pixel isThe geodesic distance to its nearest known background pixel is d (i, U)0) Then, the two values are calculated to obtain the probability:
wherein, S'iIs SiOf the opposite label, that is, if SiIs 0, S'iIs 1 and vice versa.
For pairs of pixels, one can get:
wherein,
represents by CiThe information is based on geodetic distances calculated by a distance algorithm.
Through the steps, the probability that any pixel i or pixel pair i, j belongs to the foreground or the background can be determinedAfter calculation, the algorithm can perform fast segmentation according to the probability, and the judgment threshold of the probability is adjustable and can be adjusted according to actual needs.
Description of the effects: tests were performed on the RGBD salient object, Berkeley 3D dataset, NYU depth2dataset, alignedkv2, kv2data five large RGBD datasets with the following results, where the percentages indicate the accuracy compared to the standard manual classification results:
as can be seen from the above table, the algorithm of the present invention is significantly superior to other existing algorithms.
Example two:
the second embodiment discloses an electronic device, which includes a processor, a memory and a program, where the processor and the memory may be one or more of, the program is stored in the memory and configured to be executed by the processor, and when the processor executes the program, the method for image segmentation with depth information according to the first embodiment is implemented. The electronic device may be a series of electronic devices such as a mobile phone, a computer, a tablet computer, and the like.
Example three:
the third embodiment discloses a readable computer storage medium, which is used for storing a program, and when the program is executed by a processor, the method for image segmentation containing depth information in the first embodiment is realized.
Example four:
as shown in fig. 2, the present invention discloses an apparatus for image segmentation with depth information, which includes the following modules:
an acquisition module: the system comprises a processing unit, a display unit and a processing unit, wherein the processing unit is used for acquiring click information input by a user and dividing an image to be segmented into region blocks, and the click information is pixel points on the image to be segmented;
a judging module: the pixel characteristics are used for judging whether the pixel points on each area block belong to the foreground area or the background area according to the clicking information;
a first image segmentation module: and the image segmentation module is used for judging the pixel characteristics of the pixel points on each area block according to the confidence map so as to realize image segmentation.
The above embodiments are only preferred embodiments of the present invention, and the protection scope of the present invention is not limited thereby, and any insubstantial changes and substitutions made by those skilled in the art based on the present invention are within the protection scope of the present invention.
Claims (10)
1. A method of image segmentation including depth information, comprising the steps of:
an acquisition step: acquiring click information input by a user, and dividing an image to be segmented into region blocks, wherein the click information is pixel points on the image to be segmented;
a judging step: judging whether the pixel points on each region block belong to the foreground region or the background region according to the clicking information;
a first image segmentation step: and judging the pixel characteristics of the pixel points on each region block according to the confidence map so as to realize image segmentation.
2. The method of image segmentation including depth information according to claim 1, wherein the determining step comprises the following sub-steps:
and (3) label pair distribution step: introducing a label pair into each pixel point on an image to be segmented, wherein the label pair comprises pixel attributes and pixel characteristics;
and (3) judging the label pair: and judging whether the pixel points on each area block belong to the foreground area or the background area according to the label pair.
3. The method of image segmentation including depth information according to claim 2, wherein the first image segmentation step comprises the following sub-steps:
geodesic distance calculation step: calculating the geodesic distance of the pixel points on each region block relative to the pointing information according to the pixel characteristics;
a probability value calculation step: calculating to obtain a probability value of the pixel point according to the geodesic distance, wherein the probability value is the probability of a foreground pixel point or the probability of a background pixel point;
a second image segmentation step: and performing image segmentation according to the probability value.
4. The method of image segmentation with depth information as set forth in claim 3, wherein a dixtamal algorithm is employed in the geodesic distance calculation step to find the geodesic distance.
5. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of:
an acquisition step: acquiring click information input by a user, and dividing an image to be segmented into region blocks, wherein the click information is pixel points on the image to be segmented;
a judging step: judging whether the pixel points on each region block belong to the foreground region or the background region according to the clicking information;
a first image segmentation step: and judging the pixel characteristics of the pixel points on each region block according to the confidence map so as to realize image segmentation.
6. The electronic device of claim 5, wherein the determining step specifically comprises the sub-steps of:
and (3) label pair distribution step: introducing a label pair into each pixel point on an image to be segmented, wherein the label pair comprises pixel attributes and pixel characteristics;
and (3) judging the label pair: and judging whether the pixel points on each area block belong to the foreground area or the background area according to the label pair.
7. The electronic device of claim 6, wherein the first image segmentation step comprises in particular the sub-steps of:
geodesic distance calculation step: calculating the geodesic distance of the pixel points on each region block relative to the pointing information according to the pixel characteristics;
a probability value calculation step: calculating to obtain a probability value of the pixel point according to the geodesic distance, wherein the probability value is the probability of a foreground pixel point or the probability of a background pixel point;
a second image segmentation step: and performing image segmentation according to the probability value.
8. The electronic device of claim 7, wherein a dixtar algorithm is employed in the geodetic distance calculating step to find the geodetic distance.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements the method of any one of claims 1-4.
10. An apparatus for image segmentation including depth information, comprising:
an acquisition module: the system comprises a processing unit, a display unit and a processing unit, wherein the processing unit is used for acquiring click information input by a user and dividing an image to be segmented into region blocks, and the click information is pixel points on the image to be segmented;
a judging module: the pixel characteristics are used for judging whether the pixel points on each area block belong to the foreground area or the background area according to the clicking information;
a first image segmentation module: and the image segmentation module is used for judging the pixel characteristics of the pixel points on each area block according to the confidence map so as to realize image segmentation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710525948.2A CN107452003A (en) | 2017-06-30 | 2017-06-30 | A kind of method and device of the image segmentation containing depth information |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710525948.2A CN107452003A (en) | 2017-06-30 | 2017-06-30 | A kind of method and device of the image segmentation containing depth information |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107452003A true CN107452003A (en) | 2017-12-08 |
Family
ID=60487636
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710525948.2A Pending CN107452003A (en) | 2017-06-30 | 2017-06-30 | A kind of method and device of the image segmentation containing depth information |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107452003A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109493363A (en) * | 2018-09-11 | 2019-03-19 | 北京达佳互联信息技术有限公司 | A kind of FIG pull handle method, apparatus and image processing equipment based on geodesic distance |
CN109523512A (en) * | 2018-10-17 | 2019-03-26 | 哈尔滨理工大学 | A kind of Automatic medical image segmentation method based on multichannel chromatogram tag fusion |
CN114240963A (en) * | 2021-11-25 | 2022-03-25 | 声呐天空资讯顾问有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
CN116385459A (en) * | 2023-03-08 | 2023-07-04 | 阿里巴巴(中国)有限公司 | Image segmentation method and device |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101710418A (en) * | 2009-12-22 | 2010-05-19 | 上海大学 | Interactive mode image partitioning method based on geodesic distance |
CN102542543A (en) * | 2012-01-06 | 2012-07-04 | 西安电子科技大学 | Block similarity-based interactive image segmenting method |
CN103996189A (en) * | 2014-05-05 | 2014-08-20 | 小米科技有限责任公司 | Image segmentation method and device |
-
2017
- 2017-06-30 CN CN201710525948.2A patent/CN107452003A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101710418A (en) * | 2009-12-22 | 2010-05-19 | 上海大学 | Interactive mode image partitioning method based on geodesic distance |
CN102542543A (en) * | 2012-01-06 | 2012-07-04 | 西安电子科技大学 | Block similarity-based interactive image segmenting method |
CN103996189A (en) * | 2014-05-05 | 2014-08-20 | 小米科技有限责任公司 | Image segmentation method and device |
Non-Patent Citations (1)
Title |
---|
JIE FENG等: "Interactive Segmentation on RGBD Image via Cue Selection", 《2016 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109493363A (en) * | 2018-09-11 | 2019-03-19 | 北京达佳互联信息技术有限公司 | A kind of FIG pull handle method, apparatus and image processing equipment based on geodesic distance |
CN109523512A (en) * | 2018-10-17 | 2019-03-26 | 哈尔滨理工大学 | A kind of Automatic medical image segmentation method based on multichannel chromatogram tag fusion |
CN109523512B (en) * | 2018-10-17 | 2019-10-29 | 哈尔滨理工大学 | A kind of Automatic medical image segmentation method based on multichannel chromatogram tag fusion |
CN114240963A (en) * | 2021-11-25 | 2022-03-25 | 声呐天空资讯顾问有限公司 | Image processing method, image processing device, storage medium and electronic equipment |
CN116385459A (en) * | 2023-03-08 | 2023-07-04 | 阿里巴巴(中国)有限公司 | Image segmentation method and device |
CN116385459B (en) * | 2023-03-08 | 2024-01-09 | 阿里巴巴(中国)有限公司 | Image segmentation method and device |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Chen et al. | Improved saliency detection in RGB-D images using two-phase depth estimation and selective deep fusion | |
WO2022213879A1 (en) | Target object detection method and apparatus, and computer device and storage medium | |
CN110544258B (en) | Image segmentation method and device, electronic equipment and storage medium | |
CA2826534C (en) | Backfilling points in a point cloud | |
CN105809651B (en) | Image significance detection method based on the comparison of edge non-similarity | |
CN109658445A (en) | Network training method, increment build drawing method, localization method, device and equipment | |
EP2833322A1 (en) | Stereo-motion method of three-dimensional (3-D) structure information extraction from a video for fusion with 3-D point cloud data | |
US20150036870A1 (en) | Automated graph local constellation (glc) method of correspondence search for registration of 2-d and 3-d data | |
Dai et al. | Building segmentation and outline extraction from UAV image-derived point clouds by a line growing algorithm | |
CN109063549B (en) | High-resolution aerial video moving target detection method based on deep neural network | |
CN111143489B (en) | Image-based positioning method and device, computer equipment and readable storage medium | |
CN107452003A (en) | A kind of method and device of the image segmentation containing depth information | |
CN110910445B (en) | Object size detection method, device, detection equipment and storage medium | |
CN110956131A (en) | Single-target tracking method, device and system | |
CN113139540B (en) | Backboard detection method and equipment | |
CN106709870B (en) | Close-range image straight-line segment matching method | |
CN106407978B (en) | Method for detecting salient object in unconstrained video by combining similarity degree | |
CN114565916A (en) | Target detection model training method, target detection method and electronic equipment | |
CN116843754A (en) | Visual positioning method and system based on multi-feature fusion | |
CN105631849B (en) | The change detecting method and device of target polygon | |
CN108961385A (en) | A kind of SLAM patterning process and device | |
CN109584262A (en) | Cloud detection method of optic, device and electronic equipment based on remote sensing image | |
CN114283343B (en) | Map updating method, training method and device based on remote sensing satellite image | |
CN115063473A (en) | Object height detection method and device, computer equipment and storage medium | |
CN114463503A (en) | Fusion method and device of three-dimensional model and geographic information system |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171208 |
|
RJ01 | Rejection of invention patent application after publication |