CN112116534A - Ghost eliminating method based on position information - Google Patents
Ghost eliminating method based on position information Download PDFInfo
- Publication number
- CN112116534A CN112116534A CN202010789333.2A CN202010789333A CN112116534A CN 112116534 A CN112116534 A CN 112116534A CN 202010789333 A CN202010789333 A CN 202010789333A CN 112116534 A CN112116534 A CN 112116534A
- Authority
- CN
- China
- Prior art keywords
- image
- block
- target
- position information
- algorithm
- 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
- 238000000034 method Methods 0.000 title claims abstract description 35
- 230000008439 repair process Effects 0.000 claims abstract description 17
- 238000001514 detection method Methods 0.000 claims abstract description 11
- 230000002708 enhancing effect Effects 0.000 claims abstract description 3
- 230000008030 elimination Effects 0.000 claims description 9
- 238000003379 elimination reaction Methods 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 7
- 230000009466 transformation Effects 0.000 claims description 6
- 230000008569 process Effects 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G06T5/77—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformation in the plane of the image
- G06T3/40—Scaling the whole image or part thereof
- G06T3/4038—Scaling the whole image or part thereof for image mosaicing, i.e. plane images composed of plane sub-images
-
- G06T5/80—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/20—Analysis of motion
- G06T7/223—Analysis of motion using block-matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/46—Descriptors for shape, contour or point-related descriptors, e.g. scale invariant feature transform [SIFT] or bags of words [BoW]; Salient regional features
- G06V10/462—Salient features, e.g. scale invariant feature transforms [SIFT]
-
- 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/513—Sparse representations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention discloses a ghost eliminating method based on target position information, which comprises the steps of firstly obtaining the position information of a moving object by adopting a target detection method, and then automatically completing the repair of an image after a dynamic target is removed by adopting an improved Criminisi algorithm. And finally, carrying out image splicing, and enhancing and displaying the extracted target to a corresponding position in a three-dimensional entity form. The invention solves the problem of ghost phenomenon caused by dynamic objects when the existing unmanned aerial vehicle splices scene images shot at different moments, and lays a foundation for rapidly and accurately acquiring the target area images subsequently and comprehensively and intuitively displaying the large-scale real-state scene of the target area.
Description
Technical Field
The invention relates to a ghost eliminating method based on position information.
Background
In most of the existing unmanned aerial vehicle sensing systems, an image sensor is an indispensable important environmental information source. The image information not only contains rich target information, but also has the characteristic of convenient visual interpretation, and is an important basis for the ground station operator to understand and adapt to the environment. However, when the unmanned aerial vehicle splices scene images taken at different times, when a moving object is located at a superposed portion of adjacent images, due to misalignment caused by movement of the object, a ghost phenomenon of the moving object may occur in a final spliced image, which affects a final splicing effect, as shown in fig. 1. At present, in the video splicing process, when a dynamic object exists in a scene, the front background and the rear background are separated, the background is spliced firstly, and then the foreground is inserted. Some people adopt a gradual-in and gradual-out fusion algorithm, so that the splicing efficiency is improved, but the ghost phenomenon generated by a dynamic object is not solved.
Disclosure of Invention
In view of the above, it is an object of the first aspect of the present invention to provide a ghost elimination method based on position information. Can eliminate ghost phenomenon and avoid influencing the splicing effect.
The purpose of the first aspect of the invention is realized by the following technical scheme:
the invention discloses a ghost eliminating method based on position information, which comprises the following steps:
detecting and extracting the moving target by adopting a YOLO target detection algorithm to obtain the position information of the moving target in the image;
adopting an image restoration algorithm to restore the image of the target position area;
and carrying out image splicing by adopting an SIFT algorithm, and enhancing and displaying the extracted target to a corresponding position in a three-dimensional entity form.
In particular, the YOLO target detection algorithm is to divide an image into S × S grids, and the grid is responsible for detecting a target according to the position of the center of the target on the grid; b boxes can be predicted by each grid, and each box comprises position information and confidence degree of the target; the input is one image and the output is one tensor of S × S × [ B × 5+ C ].
In particular, the image restoration algorithm adopts a modified Criminisi image restoration algorithm, and the restoration step comprises the following steps:
step S21, obtaining an image area needing to be repaired according to the characteristic detection, and initializing a repair boundary;
step S22: selecting a sample block psi according to the size of the block structure sparsitypCalculating the priority value of the sample block, and selecting the sample block with the maximum priority value as the current block to be repaired;
step S23: searching an optimal matching block in the rectangular area according to the new matching criterion;
step S24: copying the optimal matching block to the current block to be repaired, and updating confidence coefficient information;
step S25: and judging whether the repair is completed, returning to the step S22 if the repair is not completed, and ending the repair if the repair is completed.
In particular, the algorithm of the improved criminiisi image inpainting algorithm selects the data item s (p) based on the sparsity of the block structure and redefines the priority p (p) as follows:
P(p)＝αCs(p)×βD(p)，α+β＝1；
wherein, cs (p) and d (p) represent coefficient weights of the confidence term and the block structure sparsity data term, respectively;
where N (P) denotes a neighborhood block centered at point P, which is larger than the sample block ψpLarge, | n (p) | represents the number of elements in the domain; | Ns(p) | denotes NsThe number of elements in (p), ω, represents the sample block ψpAnd psikIs likeDegree, d (ψ)p，ψk) Representing the mean square distance of two blocks of samples, a being a normalization constant.
In particular, the size of the sample block has the following forms according to the image sparsity:
wherein, Pmax and Pmin are the maximum value and the minimum value of the block structure sparsity value, respectively.
In particular, the optimal matching block is found by using a method of combining the low-level features of the image with the SSD criterion, and the new matching criterion is defined as follows:
d(SSD，BC)(Ψpi，Ψpj)＝dSSD(Ψpi，Ψpj)·(dBC(Ψpi，Ψpj)+1)；
wherein d is(SSD，BC)(Ψpi，Ψpj) Representing a block of samples ΨpiTo ΨpjSSD of (d)BC(Ψpi，Ψpj) Representing a block of samples ΨpiTo ΨpjThe improved Criminisi image restoration algorithm is applied, even if two sample blocks have the same probability distribution, the SSD criterion can be used for searching the optimal matching block; the finding of the best matching block will be done according to SSD criteria and image histogram information.
Particularly, the image mosaic algorithm adopts an SIFT algorithm to perform feature extraction and feature matching, and then a transformation model between a non-matching point and an estimated image is removed by using a RANSAC robust estimation method.
It is an object of a second aspect of the invention to provide a computer arrangement comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method as described above when executing the computer program.
It is an object of a third aspect of the invention to provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, performs the method as previously described.
The invention has the beneficial effects that:
the invention solves the problem of ghost phenomenon caused by dynamic objects when the existing unmanned aerial vehicle splices scene images shot at different moments, and lays a foundation for rapidly and accurately acquiring the target area images subsequently and comprehensively and intuitively displaying the large-scale real-state scene of the target area.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the present invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
Drawings
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail with reference to the accompanying drawings, in which:
FIG. 1 is a flow chart of a ghosting elimination algorithm based on target location information;
FIG. 2 is a flow chart of an improved Criminisi image inpainting algorithm;
FIG. 3 is a flow chart of image stitching;
fig. 4 is a photograph showing an example of an experimental result of the ghost elimination algorithm based on the target position information.
Detailed Description
Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be understood that the preferred embodiments are illustrative of the invention only and are not limiting upon the scope of the invention.
The invention discloses a ghost eliminating method based on position information, which comprises the following steps:
detecting and extracting a moving target by adopting a YOLO target detection algorithm aiming at an acquired unmanned aerial vehicle aerial image sequence to obtain position information of the moving target in an image;
in this embodiment, the YOLO target detection algorithm is used to divide an image into S × S grids, and the grid is responsible for detecting a target according to the position where the center of the target falls on the grid; b boxes can be predicted by each grid, and each box comprises position information and confidence degree of the target; the input is one image and the output is one tensor of S × S × [ B × 5+ C ].
Secondly, repairing the image of the target position area by adopting an image repairing algorithm;
in this embodiment, the image restoration algorithm adopts an improved Criminisi image restoration algorithm, and the restoration step includes:
step S21, obtaining an image area needing to be repaired according to the characteristic detection, and initializing a repair boundary;
the algorithm of the improved Criminisi image inpainting algorithm selects data items s (p) based on the sparsity of the block structure and redefines the priority p (p) as follows:
P(p)＝αCs(p)×βD(p)，α+β＝1；
wherein, cs (p) and d (p) represent coefficient weights of the confidence term and the block structure sparsity data term, respectively;
where N (P) denotes a neighborhood block centered at point P, which is larger than the sample block ψpLarge, | n (p) | represents the number of elements in the domain; | Ns(p) | denotes NsThe number of elements in (p), ω, represents the sample block ψpAnd psikSimilarity of d (ψ)p，ψk) Representing the mean square distance of two blocks of samples, a being a normalization constant.
Step S22: selecting a sample block psi according to the size of the block structure sparsitypCalculating the priority value of the sample block, and selecting the sample block with the maximum priority value as the current block to be repaired;
in this embodiment, the size of the sample block has the following forms according to the image sparsity:
wherein, Pmax and Pmin are the maximum value and the minimum value of the block structure sparsity value, respectively.
Step S23: searching an optimal matching block in the rectangular area according to the new matching criterion; specifically, the optimal matching block is found by using a method of combining the features of the image at the lower level with the SSD criterion, and the new matching criterion is defined as follows:
d(SSD，BC)(Ψpi，Ψpj)＝dSSD(Ψpi，Ψpj)·(dBC(Ψpi，Ψpj)+1)；
wherein d is(SSD，BC)(Ψpi，Ψpj) Representing a block of samples ΨpiTo ΨpjSSD of (d)BC(Ψpi，Ψpj) Representing a block of samples ΨpiTo ΨpjThe improved Criminisi image restoration algorithm is applied, even if two sample blocks have the same probability distribution, the SSD criterion can be used for searching the optimal matching block; the finding of the best matching block will be done according to SSD criteria and image histogram information.
Step S24: copying the optimal matching block to the current block to be repaired, and updating confidence coefficient information;
step S25: and judging whether the repair is completed, returning to the step S22 if the repair is not completed, and ending the repair if the repair is completed.
And thirdly, image splicing is carried out by adopting an SIFT algorithm, and the extracted target is enhanced and displayed to a corresponding position in a three-dimensional entity form.
In the embodiment, the image stitching process adopts an SIFT algorithm to perform feature extraction and feature matching, then a transformation model between a non-matching point and an estimated image is removed by using a RANSAC robust estimation method, specifically, an image transformation model is established by using matching logarithm solving parameters, and then the panoramic stitching is realized through image fusion.
Examples of the applications
The low-altitude area unmanned aerial vehicle aerial video data used in the example is collected in an airport in Henan province, 5 frames of images are selected in an equal-interval sampling mode, the scene of the test image is flat, the texture of the scene is single, and a moving object (such as a vehicle) exists in the scene, as shown in fig. 4 (a).
The used unmanned aerial vehicle belongs to a fixed wing type unmanned aerial vehicle, the unmanned aerial vehicle is driven by a power system to take off in a sliding mode, the high-altitude continuous flight is kept, and the performance parameters are shown in table 1.
TABLE 1 UAV Performance parameters
| Item | Parameter(s) |
| Captain | 1.23m |
| Load weight | 5800g |
| Flying height | 100m-200m |
| Duration of flight | 60min |
| Speed of rotation | 18m/s |
| Control mode | Program automatic control |
| Navigation mode | GPS/IMU |
| Sensor with a sensor element | Non-measuring digital camera |
The drone sensor (camera mounted on the drone) used a consumer-grade camera, whose performance parameters are shown in table 2.
TABLE 2 sensor Performance parameters
| Item | Parameter(s) |
| Name (R) | CCD camera |
| Video format | avi |
| Image size | 1280*720 |
| Focal length of camera | 35mm |
Through the YOLO target detection algorithm, information of a moving target in the image is successfully extracted, as shown in fig. 4 (b). The background information of the image is restored by using the proposed image restoration algorithm shown in fig. 2 in combination with the target position information, and the restoration effect is shown in fig. 4 (c). The repairing algorithm effectively distinguishes the structure and the texture of the image by using the data items based on the sparsity of the block structure. By combining the low-level features of the image with the SSD criterion, the effective pixels are increased, the repair precision is improved, and the structural integrity of the repaired image is well maintained.
Through the above processing, clean images without moving targets are successfully acquired, and the images are subjected to image stitching by using the algorithm shown in fig. 3, and the stitching result is shown in fig. 4 (d). In order to ensure the integrity of the image information, the extracted target is enhanced and displayed to the corresponding position in the form of a three-dimensional entity in combination with the position information of the target, as shown in fig. 4 (e).
Any process or method descriptions in flow charts or otherwise herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing specific logical functions or steps in the process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
Finally, the above embodiments are only intended to illustrate the technical solutions of the present invention and not to limit the present invention, and although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions, and all of them should be covered by the claims of the present invention.
Claims (10)
1. A ghost eliminating method based on position information is characterized in that: the method comprises the following steps:
detecting and extracting the moving target by adopting a YOLO target detection algorithm to obtain the position information of the moving target in the image;
adopting an image restoration algorithm to restore the image of the target position area;
and carrying out image splicing by adopting an SIFT algorithm, and enhancing and displaying the extracted target to a corresponding position in a three-dimensional entity form.
2. A ghost elimination method based on position information according to claim 1, characterized in that: the YOLO target detection algorithm is to divide an image into S multiplied by S grids, and the grids are responsible for detecting a target according to the position of the center of the target on a certain grid; b boxes can be predicted by each grid, and each box comprises position information and confidence degree of the target; the input is one image and the output is one tensor of S × S × [ B × 5+ C ].
3. A ghost elimination method based on position information according to claim 1, characterized in that: the image restoration algorithm adopts an improved Criminisi image restoration algorithm, and the restoration steps comprise:
step S21: according to the characteristic detection, obtaining an image area needing to be repaired, and initializing a repair boundary;
step S22: selecting a sample block psi according to the size of the block structure sparsitypCalculating the priority value of the sample block, and selecting the sample block with the maximum priority value as the current block to be repaired;
step S23: searching an optimal matching block in the rectangular area according to the new matching criterion;
step S24: copying the optimal matching block to the current block to be repaired, and updating confidence coefficient information;
step S25: and judging whether the repair is completed, returning to the step S22 if the repair is not completed, and ending the repair if the repair is completed.
4. A ghost elimination method based on position information according to claim 1, characterized in that: the algorithm of the improved Criminisi image inpainting algorithm selects data items s (p) based on the sparsity of the block structure and redefines the priority p (p) as follows:
P(p)＝αCs(p)×βD(p)，α+β＝1；
wherein, cs (p) and d (p) represent coefficient weights of the confidence term and the block structure sparsity data term, respectively;
where N (P) denotes a neighborhood block centered at point P, which is larger than the sample block ψpLarge, | n (p) | represents the number of elements in the domain; | Ns(p) | denotes NsThe number of elements in (p), ω, represents the sample block ψpAnd psikSimilarity of d (ψ)p，ψk) Representing the mean square distance of two blocks of samples, a being a normalization constant.
5. The method of claim 4, wherein: the size of the sample block has the following forms according to the image sparsity:
wherein, Pmax and Pmin are the maximum value and the minimum value of the block structure sparsity value, respectively.
6. A ghost elimination method based on position information according to claim 3, wherein: the optimal matching block is found by using a method of combining the low-level features of the image with SSD criteria, and the new matching criteria are defined as follows:
d(SSD，BC)(Ψpi，Ψpj)＝dSSD(Ψpi，Ψpj)·(dBC(Ψpi，Ψpj)+1)；
wherein d is(SSD，BC)(Ψpi，Ψpj) Representing a block of samples ΨpiTo ΨpjSSD of (d)BC(Ψpi，Ψpj) Representing a block of samples ΨpiTo ΨpjThe improved Criminisi image restoration algorithm is applied, even if two sample blocks have the same probability distribution, the SSD criterion can be used for searching the optimal matching block; the finding of the best matching block will be done according to SSD criteria and image histogram information.
7. A ghost elimination method based on position information according to claim 1, characterized in that: in the image splicing process, an SIFT algorithm is adopted for feature extraction and feature matching, and then a transformation model between a non-matching point and an estimated image is removed by using a RANSAC robust estimation method.
8. A ghost elimination method based on position information according to claim 7, wherein: a transformation model between a non-matching point and an estimated image is removed by using a RANSAC robust estimation method, an image transformation model is established by using matching logarithm solving parameters, and then the panorama splicing is realized through image fusion.
9. A computer apparatus comprising a memory, a processor, and a computer program stored on the memory and capable of running on the processor, wherein: the processor, when executing the computer program, implements the method of any of claims 1-7.
10. 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 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010789333.2A CN112116534A (en) | 2020-08-07 | 2020-08-07 | Ghost eliminating method based on position information |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010789333.2A CN112116534A (en) | 2020-08-07 | 2020-08-07 | Ghost eliminating method based on position information |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112116534A true CN112116534A (en) | 2020-12-22 |
Family
ID=73803704
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010789333.2A Pending CN112116534A (en) | 2020-08-07 | 2020-08-07 | Ghost eliminating method based on position information |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116534A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160283A (en) * | 2021-03-23 | 2021-07-23 | 河海大学 | Target tracking method based on SIFT under multi-camera scene |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160335748A1 (en) * | 2014-01-23 | 2016-11-17 | Thomson Licensing | Method for inpainting a target area in a target video |
| CN106204503A (en) * | 2016-09-08 | 2016-12-07 | 天津大学 | Based on improving confidence level renewal function and the image repair algorithm of matching criterior |
| CN106910208A (en) * | 2017-03-07 | 2017-06-30 | 中国海洋大学 | A kind of scene image joining method that there is moving target |
| CN110033475A (en) * | 2019-03-29 | 2019-07-19 | 北京航空航天大学 | A kind of take photo by plane figure moving object segmentation and removing method that high-resolution texture generates |
| CN110555908A (en) * | 2019-08-28 | 2019-12-10 | 西安电子科技大学 | three-dimensional reconstruction method based on indoor moving target background restoration |
-
2020
- 2020-08-07 CN CN202010789333.2A patent/CN112116534A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160335748A1 (en) * | 2014-01-23 | 2016-11-17 | Thomson Licensing | Method for inpainting a target area in a target video |
| CN106204503A (en) * | 2016-09-08 | 2016-12-07 | 天津大学 | Based on improving confidence level renewal function and the image repair algorithm of matching criterior |
| CN106910208A (en) * | 2017-03-07 | 2017-06-30 | 中国海洋大学 | A kind of scene image joining method that there is moving target |
| CN110033475A (en) * | 2019-03-29 | 2019-07-19 | 北京航空航天大学 | A kind of take photo by plane figure moving object segmentation and removing method that high-resolution texture generates |
| CN110555908A (en) * | 2019-08-28 | 2019-12-10 | 西安电子科技大学 | three-dimensional reconstruction method based on indoor moving target background restoration |
Non-Patent Citations (1)
| Title |
|---|
| 唐明明: "基于块结构稀疏度的图像修复算法", 中国优秀硕士学位论文全文数据库 信息科技辑（月刊）, pages 306 - 36 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160283A (en) * | 2021-03-23 | 2021-07-23 | 河海大学 | Target tracking method based on SIFT under multi-camera scene |
| CN113160283B (en) * | 2021-03-23 | 2024-04-16 | 河海大学 | Target tracking method under multi-camera scene based on SIFT |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10607369B2 (en) | Method and device for interactive calibration based on 3D reconstruction in 3D surveillance system | |
| CN108428255B (en) | Real-time three-dimensional reconstruction method based on unmanned aerial vehicle | |
| CN111881720B (en) | Automatic enhancement and expansion method, recognition method and system for data for deep learning | |
| WO2020014909A1 (en) | Photographing method and device and unmanned aerial vehicle | |
| EP2874097A2 (en) | Automatic scene parsing | |
| CN110473221B (en) | Automatic target object scanning system and method | |
| CN108663026B (en) | Vibration measuring method | |
| CN113359843B (en) | Unmanned aerial vehicle autonomous landing method and device, electronic equipment and storage medium | |
| CN111899345B (en) | Three-dimensional reconstruction method based on 2D visual image | |
| CN111415364A (en) | Method, system and storage medium for converting image segmentation samples in computer vision | |
| CN115240089A (en) | Vehicle detection method of aerial remote sensing image | |
| CN112465856A (en) | Unmanned aerial vehicle-based ship track correction method and device and electronic equipment | |
| CN115493612A (en) | Vehicle positioning method and device based on visual SLAM | |
| CN112116534A (en) | Ghost eliminating method based on position information | |
| CN115063485B (en) | Three-dimensional reconstruction method, device and computer-readable storage medium | |
| CN110705134A (en) | Driving test method, device, equipment and computer readable storage medium | |
| CN114758135A (en) | Unsupervised image semantic segmentation method based on attention mechanism | |
| Kaimkhani et al. | UAV with Vision to Recognise Vehicle Number Plates | |
| CN113239931A (en) | Logistics station license plate recognition method | |
| Jian et al. | Ghosting Elimination Method Based on Target Location Information | |
| Yang et al. | A fast and effective panorama stitching algorithm on UAV aerial images | |
| JP7207479B2 (en) | Building gauge determination method | |
| CN113869163B (en) | Target tracking method and device, electronic equipment and storage medium | |
| CN110796028B (en) | Unmanned aerial vehicle image small target detection method and system based on local adaptive geometric transformation | |
| Knyaz | Recognition of low-resolution objects in remote sensing images |
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 |