CN112084881B - Cross-domain pedestrian re-identification method and device and storage medium - Google Patents
Cross-domain pedestrian re-identification method and device and storage medium Download PDFInfo
- Publication number
- CN112084881B CN112084881B CN202010830172.7A CN202010830172A CN112084881B CN 112084881 B CN112084881 B CN 112084881B CN 202010830172 A CN202010830172 A CN 202010830172A CN 112084881 B CN112084881 B CN 112084881B
- Authority
- CN
- China
- Prior art keywords
- image
- data set
- images
- domain
- target
- 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 35
- 238000006243 chemical reaction Methods 0.000 claims abstract description 61
- 238000012545 processing Methods 0.000 claims abstract description 51
- 125000004122 cyclic group Chemical group 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G06T3/04—
Abstract
The invention provides a cross-domain pedestrian re-identification method, a device and a storage medium, wherein the method comprises the following steps: respectively obtaining a plurality of images corresponding to respective target areas from photographing equipment preset in the target areas, and respectively obtaining a plurality of corresponding image sets through the images of the target areas; combining image sets according to the number of the image sets, and performing image style conversion processing on the combined image sets to obtain an image data set to be identified; and carrying out identification processing on the image data set to be identified to obtain an identification result. According to the invention, the diversity of the data set samples is enhanced compared with that before the conversion, the inter-domain difference of the samples is reduced, so that the model has better generalization capability, the accuracy of cross-domain pedestrian re-identification can be effectively improved, the problem of low accuracy of cross-domain pedestrian re-identification can be effectively solved, and the cross-domain pedestrian re-identification can be better served for social public safety systems.
Description
Technical Field
The invention mainly relates to the technical field of image data set processing, in particular to a cross-domain pedestrian re-identification method, a cross-domain pedestrian re-identification device and a storage medium.
Background
Image dataset processing techniques convert an input image dataset into another image dataset having desired characteristics. For example, the output image data set may be processed to have a higher signal-to-noise ratio, or the details of the image data set may be highlighted by an enhancement process to facilitate verification by an operator. Image processing techniques are often used for preprocessing and feature extraction in computer vision research.
Image dataset processing, techniques for computer analysis of image datasets to achieve desired results. Also known as image processing. Image dataset processing generally refers to digital image dataset processing. A digital image data set is a large two-dimensional array of elements called pixels and values called grey-scale values, which is captured by an industrial camera, video camera, scanner, or the like. Image dataset processing techniques generally include image dataset compression, enhancement and restoration, matching, description and identification.
Pedestrian re-identification, also known as pedestrian re-identification, is a technique that utilizes computer vision techniques to determine whether a particular pedestrian is present in an image dataset or video sequence. Is widely regarded as a sub-problem for image dataset retrieval. Given a monitored pedestrian image dataset, the pedestrian image dataset is retrieved across devices. The method aims to make up for visual limitation of a fixed camera, can be combined with a pedestrian detection/pedestrian tracking technology, can be widely applied to the fields of intelligent video monitoring, intelligent security and the like, and has the problems that the existing identification method has high requirements on samples, and the cross-domain pedestrian re-identification accuracy is low due to the fact that target data are difficult to obtain.
Disclosure of Invention
The invention provides a cross-domain pedestrian re-identification method, a cross-domain pedestrian re-identification device and a storage medium, aiming at the defects of the prior art.
The technical scheme for solving the technical problems is as follows: a cross-domain pedestrian re-identification method comprises the following steps:
respectively obtaining a plurality of images corresponding to respective target areas from photographing equipment preset in the target areas, and respectively obtaining a plurality of corresponding image sets through the images of the target areas;
combining image sets according to the number of the image sets, and performing image style conversion processing on the combined image sets to obtain an image data set to be identified;
and carrying out identification processing on the image data set to be identified to obtain an identification result.
Another technical solution of the present invention for solving the above technical problems is as follows: a cross-domain pedestrian re-identification apparatus comprising:
the image set obtaining module is used for obtaining a plurality of images corresponding to respective target areas from photographing equipment which is preset in the target areas respectively, and obtaining a plurality of corresponding image sets through the images of the target areas respectively;
the image set processing module is used for combining image sets according to the number of the image sets and carrying out image style and style conversion processing on the combined image sets to obtain an image data set to be identified;
and the identification result obtaining module is used for carrying out identification processing on the image data set to be identified to obtain an identification result.
Another technical solution of the present invention for solving the above technical problems is as follows: a cross-domain pedestrian re-identification apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor when executing the computer program implementing a cross-domain pedestrian re-identification method as described above.
Another technical solution of the present invention for solving the above technical problems is as follows: a computer readable storage medium storing a computer program which, when executed by a processor, implements a cross-domain pedestrian re-identification method as described above.
The invention has the beneficial effects that: the method comprises the steps of obtaining a plurality of image sets from photographing equipment, combining the image sets according to the number of the image sets, converting the image styles and styles of the combined image sets to obtain the image data set to be recognized, enhancing the diversity of data set samples compared with the data set samples before conversion, reducing the inter-domain difference of the samples, enabling the model to have better generalization capability, obtaining a recognition result through the recognition processing of the image data set to be recognized, effectively improving the accuracy of cross-domain pedestrian re-recognition, effectively solving the problem of low accuracy of cross-domain pedestrian re-recognition, and enabling the cross-domain pedestrian re-recognition to be better served for social public safety systems.
Drawings
Fig. 1 is a flowchart illustrating a cross-domain pedestrian re-identification method according to an embodiment of the present invention;
fig. 2 is a block diagram of a cross-domain pedestrian re-identification apparatus according to an embodiment of the present invention.
Detailed Description
The principles and features of this invention are described below in conjunction with the following drawings, which are set forth by way of illustration only and are not intended to limit the scope of the invention.
Fig. 1 is a flowchart illustrating a cross-domain pedestrian re-identification method according to an embodiment of the present invention.
As shown in fig. 1, a cross-domain pedestrian re-identification method includes the following steps:
respectively obtaining a plurality of images corresponding to respective target areas from photographing equipment preset in the target areas, and respectively obtaining a plurality of corresponding image sets through the images of the target areas;
combining image sets according to the number of the image sets, and performing image style conversion processing on the combined image sets to obtain an image data set to be identified;
and carrying out identification processing on the image data set to be identified to obtain an identification result.
In the embodiment, the plurality of image sets are obtained from the photographing device, the image data set to be identified is obtained according to the image set combination of the number of the plurality of image sets, and the image style and style of the combined image set are converted, so that the diversity of the data set samples is enhanced compared with the diversity of the data set samples before conversion, the inter-domain difference of the samples is reduced, the model has better generalization capability, the identification result is obtained by the identification processing of the image data set to be identified, the accuracy of cross-domain pedestrian re-identification can be effectively improved, the problem of low accuracy of cross-domain pedestrian re-identification can be effectively solved, and the cross-domain pedestrian re-identification system can be better served for the social public safety system.
Optionally, as an embodiment of the present invention, the obtaining, from a photographing apparatus preset in a plurality of target areas, a plurality of images corresponding to the respective target areas respectively, and obtaining, from the plurality of images of the respective target areas, a plurality of image sets respectively corresponding to the plurality of images includes:
obtaining a plurality of source domain A images from photographing equipment arranged in a target area A, and obtaining a source domain A image data set according to the source domain A images;
acquiring a plurality of target domain B images from photographing equipment arranged in a target domain B, and acquiring a target domain B image data set according to the plurality of first target domain B images;
acquiring a plurality of target domain C images from photographing equipment arranged in a target region C, and acquiring a target domain C image data set according to the plurality of target domain C images;
target area D images are respectively obtained from the photographing devices arranged in the plurality of target areas D, and corresponding target area D image sets are obtained through the respective target area D images.
It should be understood that the target domain B image data set is a small amount of target domain image data; the target domain C image data set is a large amount of target domain image data.
In the embodiment, the image data sets of the multiple regions are obtained through the multiple cameras, so that a foundation is laid for subsequent processing, the accuracy of cross-domain pedestrian re-identification is effectively improved, the problem of low accuracy of cross-domain pedestrian re-identification can be effectively solved, and the cross-domain pedestrian re-identification system can be better served for social public safety systems.
Optionally, as an embodiment of the present invention, the image set combination according to the number of the plurality of image sets, and the image style and style conversion processing is performed on the combined image set to obtain the image data set to be recognized includes:
when the number of images in the target domain B image dataset is smaller than the number of preset images, inputting the source domain image dataset and the target domain B image dataset into a pre-constructed cyclic generation countermeasure network together for image style and style conversion processing to obtain a first style conversion image dataset, and taking the first style conversion image dataset as an image dataset to be identified;
when the number of images in the target domain C image dataset is greater than or equal to the number of preset images, inputting the source domain image dataset and the target domain C image dataset into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a second style conversion image dataset, and taking the second style conversion image dataset as the image dataset to be identified;
when images are not obtained in preset photographing equipment of the target area B and the target area C, inputting the source area image data set and any one of the target area D image data sets into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a third style conversion image data set, and taking the third style conversion image data set as the image data set to be identified;
or when images are not obtained in the preset photographing equipment of the target area B and the target area C, inputting the source area image data set and the plurality of target area D image sets into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a fourth style conversion image data set, and taking the fourth style conversion image data set as the image data set to be identified.
It should be understood that in the case of few or no target domain image data sets, the image data set to be recognized is obtained by performing image style conversion processing on the existing different image data sets.
In the embodiment, the situation of different target domain image data sets is processed, so that the problem that under the condition that the target domain image data sets are few or no target domain image data sets, the diversity of the image data sets is increased and the inter-domain difference of samples is reduced by processing the existing image data sets is solved, the model has better generalization capability, meanwhile, the accuracy of pedestrian re-identification is improved, and the model can better serve a social public safety system.
Optionally, as an embodiment of the present invention, the identifying the image dataset to be identified to obtain an identification result includes:
inputting the image data set to be recognized into a pre-constructed re-recognition model for training to obtain a trained re-recognition model;
and testing the trained re-recognition model according to the target domain C image data set to obtain a recognition result.
In the above embodiment, the image data set to be recognized is input to the re-recognition model for training to obtain a trained re-recognition model; and testing the trained re-recognition model according to the target domain C image data set to obtain a recognition result, effectively improving the accuracy of re-recognition of the cross-domain pedestrians, effectively solving the problem of low accuracy of re-recognition of the cross-domain pedestrians, and better serving the social public safety system.
Fig. 2 is a block diagram of a cross-domain pedestrian re-identification apparatus according to an embodiment of the present invention.
Alternatively, as another embodiment of the present invention, as shown in fig. 2, a cross-domain pedestrian re-identification apparatus includes:
the image set obtaining module is used for obtaining a plurality of images corresponding to respective target areas from photographing equipment which is preset in the target areas respectively, and obtaining a plurality of corresponding image sets through the images of the target areas respectively;
the image set processing module is used for combining image sets according to the number of the image sets and carrying out image style and style conversion processing on the combined image sets to obtain an image data set to be identified;
and the identification result obtaining module is used for carrying out identification processing on the image data set to be identified to obtain an identification result.
Optionally, as an embodiment of the present invention, the image set obtaining module is specifically configured to:
obtaining a plurality of source domain A images from photographing equipment arranged in a target area A, and obtaining a source domain A image data set according to the source domain A images;
acquiring a plurality of target domain B images from photographing equipment arranged in a target domain B, and acquiring a target domain B image data set according to the plurality of first target domain B images;
acquiring a plurality of target domain C images from photographing equipment arranged in a target region C, and acquiring a target domain C image data set according to the plurality of target domain C images;
target area D images are respectively obtained from the photographing devices arranged in the plurality of target areas D, and corresponding target area D image sets are obtained through the respective target area D images.
Optionally, as an embodiment of the present invention, the image set processing module is specifically configured to:
when the number of images in the target domain B image dataset is smaller than the number of preset images, inputting the source domain image dataset and the target domain B image dataset into a pre-constructed cyclic generation countermeasure network together for image style and style conversion processing to obtain a first style conversion image dataset, and taking the first style conversion image dataset as an image dataset to be identified;
when the number of images in the target domain C image dataset is greater than or equal to the number of preset images, inputting the source domain image dataset and the target domain C image dataset into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a second style conversion image dataset, and taking the second style conversion image dataset as the image dataset to be identified;
when images are not obtained in preset photographing equipment of the target area B and the target area C, inputting the source area image data set and any one of the target area D image data sets into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a third style conversion image data set, and taking the third style conversion image data set as the image data set to be identified;
or when images are not obtained in the preset photographing equipment of the target area B and the target area C, inputting the source area image data set and the plurality of target area D image sets into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a fourth style conversion image data set, and taking the fourth style conversion image data set as the image data set to be identified.
Optionally, as an embodiment of the present invention, the identification result obtaining module is specifically configured to:
inputting the image data set to be recognized into a pre-constructed re-recognition model for training to obtain a trained re-recognition model;
and testing the trained re-recognition model according to the target domain C image data set to obtain a recognition result.
Alternatively, another embodiment of the present invention provides a cross-domain pedestrian re-identification apparatus, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the cross-domain pedestrian re-identification method is implemented as described above. The device may be a computer or the like.
Alternatively, another embodiment of the present invention provides a computer-readable storage medium storing a computer program which, when executed by a processor, implements the cross-domain pedestrian re-identification method as described above.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, a division of a unit is merely a logical division, and an actual implementation may have another division, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment of the present invention.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated unit, if implemented in the form of a software functional unit and sold or used as a stand-alone product, may be stored in a computer readable storage medium. It will be understood that the technical solution of the present invention essentially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
While the invention has been described with reference to specific embodiments, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (6)
1. A cross-domain pedestrian re-identification method is characterized by comprising the following steps:
respectively obtaining a plurality of images corresponding to respective target areas from photographing equipment preset in the target areas, and respectively obtaining a plurality of corresponding image sets through the images of the target areas;
combining image sets according to the number of the image sets, and performing image style conversion processing on the combined image sets to obtain an image data set to be identified;
carrying out identification processing on the image data set to be identified to obtain an identification result;
the process of respectively obtaining a plurality of images corresponding to respective target areas from photographing devices preset in the target areas, and respectively obtaining a plurality of corresponding image sets through the plurality of images of the target areas comprises the following steps:
obtaining a plurality of source domain A images from photographing equipment arranged in a target area A, and obtaining a source domain A image data set according to the source domain A images;
acquiring a plurality of target domain B images from photographing equipment arranged in a target domain B, and acquiring a target domain B image data set according to the plurality of target domain B images;
acquiring a plurality of target domain C images from photographing equipment arranged in a target region C, and acquiring a target domain C image data set according to the plurality of target domain C images;
respectively obtaining images of the target areas D from photographing equipment arranged in the plurality of target areas D, and obtaining corresponding image sets of the target areas D through the images of the target areas D;
the process of combining the image sets according to the number of the image sets, and performing image style and style conversion processing on the combined image sets to obtain the image data set to be identified comprises the following steps:
when the number of images in the target domain B image dataset is smaller than the number of preset images, inputting the source domain A image dataset and the target domain B image dataset into a pre-constructed cyclic generation countermeasure network together for image style and style conversion processing to obtain a first style conversion image dataset, and taking the first style conversion image dataset as an image dataset to be identified;
when the number of images in the target domain C image dataset is greater than or equal to the number of preset images, inputting the source domain A image dataset and the target domain C image dataset into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a second style conversion image dataset, and taking the second style conversion image dataset as the image dataset to be identified;
when images are not obtained in preset photographing equipment of the target area B and the target area C, inputting the image data set of the source area A and any one image data set of the target area D into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a third style conversion image data set, and taking the third style conversion image data set as the image data set to be identified;
or when images are not obtained in the preset photographing equipment of the target area B and the target area C, inputting the image data set of the source area A and the image sets of the target areas D into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a fourth style conversion image data set, and taking the fourth style conversion image data set as the image data set to be identified.
2. The cross-domain pedestrian re-identification method according to claim 1, wherein the identifying the image dataset to be identified to obtain the identification result comprises:
inputting the image data set to be recognized into a pre-constructed re-recognition model for training to obtain a trained re-recognition model;
and testing the trained re-recognition model according to the target domain C image data set to obtain a recognition result.
3. A cross-domain pedestrian re-identification apparatus, comprising:
the image set obtaining module is used for obtaining a plurality of images corresponding to respective target areas from photographing equipment which is preset in the target areas respectively, and obtaining a plurality of corresponding image sets through the images of the target areas respectively;
the image set processing module is used for combining image sets according to the number of the image sets and carrying out image style and style conversion processing on the combined image sets to obtain an image data set to be identified;
the identification result obtaining module is used for carrying out identification processing on the image data set to be identified to obtain an identification result;
the image set obtaining module is specifically configured to:
obtaining a plurality of source domain A images from photographing equipment arranged in a target area A, and obtaining a source domain A image data set according to the source domain A images;
acquiring a plurality of target domain B images from photographing equipment arranged in a target domain B, and acquiring a target domain B image data set according to the plurality of target domain B images;
acquiring a plurality of target domain C images from photographing equipment arranged in a target region C, and acquiring a target domain C image data set according to the plurality of target domain C images;
respectively obtaining images of the target areas D from photographing equipment arranged in the plurality of target areas D, and obtaining corresponding image sets of the target areas D through the images of the target areas D;
the image set processing module is specifically configured to:
when the number of images in the target domain B image dataset is smaller than the number of preset images, inputting the source domain A image dataset and the target domain B image dataset into a pre-constructed cyclic generation countermeasure network together for image style and style conversion processing to obtain a first style conversion image dataset, and taking the first style conversion image dataset as an image dataset to be identified;
when the number of images in the target domain C image dataset is greater than or equal to the number of preset images, inputting the source domain A image dataset and the target domain C image dataset into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a second style conversion image dataset, and taking the second style conversion image dataset as the image dataset to be identified;
when images are not obtained in preset photographing equipment of the target area B and the target area C, inputting the image data set of the source area A and any one image data set of the target area D into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a third style conversion image data set, and taking the third style conversion image data set as the image data set to be identified;
or when images are not obtained in the preset photographing equipment of the target area B and the target area C, inputting the image data set of the source area A and the image sets of the target areas D into the cyclic generation countermeasure network together for image style and style conversion processing to obtain a fourth style conversion image data set, and taking the fourth style conversion image data set as the image data set to be identified.
4. The cross-domain pedestrian re-identification device according to claim 3, wherein the identification result obtaining module is specifically configured to:
inputting the image data set to be recognized into a pre-constructed re-recognition model for training to obtain a trained re-recognition model;
and testing the trained re-recognition model according to the target domain C image data set to obtain a recognition result.
5. A cross-domain pedestrian re-identification apparatus comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that when the computer program is executed by the processor, the cross-domain pedestrian re-identification method according to any one of claims 1 to 2 is implemented.
6. A computer-readable storage medium storing a computer program, wherein the computer program, when executed by a processor, implements the cross-domain pedestrian re-identification method according to any one of claims 1 to 2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010830172.7A CN112084881B (en) | 2020-08-18 | 2020-08-18 | Cross-domain pedestrian re-identification method and device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010830172.7A CN112084881B (en) | 2020-08-18 | 2020-08-18 | Cross-domain pedestrian re-identification method and device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112084881A CN112084881A (en) | 2020-12-15 |
| CN112084881B true CN112084881B (en) | 2022-04-19 |
Family
ID=73729718
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010830172.7A Active CN112084881B (en) | 2020-08-18 | 2020-08-18 | Cross-domain pedestrian re-identification method and device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112084881B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107832711A (en) * | 2017-11-13 | 2018-03-23 | 常州大学 | A kind of recognition methods again of the pedestrian based on transfer learning |
| US10108850B1 (en) * | 2017-04-24 | 2018-10-23 | Intel Corporation | Recognition, reidentification and security enhancements using autonomous machines |
| CN110569819A (en) * | 2019-09-16 | 2019-12-13 | 天津通卡智能网络科技股份有限公司 | Bus passenger re-identification method |
| CN111291705A (en) * | 2020-02-24 | 2020-06-16 | 北京交通大学 | Cross-multi-target-domain pedestrian re-identification method |
| CN111401281A (en) * | 2020-03-23 | 2020-07-10 | 山东师范大学 | Unsupervised pedestrian re-identification method and system based on deep clustering and sample learning |
-
2020
- 2020-08-18 CN CN202010830172.7A patent/CN112084881B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10108850B1 (en) * | 2017-04-24 | 2018-10-23 | Intel Corporation | Recognition, reidentification and security enhancements using autonomous machines |
| CN107832711A (en) * | 2017-11-13 | 2018-03-23 | 常州大学 | A kind of recognition methods again of the pedestrian based on transfer learning |
| CN110569819A (en) * | 2019-09-16 | 2019-12-13 | 天津通卡智能网络科技股份有限公司 | Bus passenger re-identification method |
| CN111291705A (en) * | 2020-02-24 | 2020-06-16 | 北京交通大学 | Cross-multi-target-domain pedestrian re-identification method |
| CN111401281A (en) * | 2020-03-23 | 2020-07-10 | 山东师范大学 | Unsupervised pedestrian re-identification method and system based on deep clustering and sample learning |
Non-Patent Citations (1)
| Title |
|---|
| "Person Re-identification Method Based on Cross-domain Image Style Conversion";Chenkui Wang 等;《ICDSP 2020: Proceedings of the 2020 4th International Conference on Digital Signal Processing》;20200619;第17-21页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112084881A (en) | 2020-12-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111738230B (en) | Face recognition method, face recognition device and electronic equipment | |
| WO2019033572A1 (en) | Method for detecting whether face is blocked, device and storage medium | |
| CN105184238A (en) | Human face recognition method and system | |
| US11227149B2 (en) | Method and apparatus with liveness detection and object recognition | |
| CN110399826B (en) | End-to-end face detection and identification method | |
| Dietlmeier et al. | How important are faces for person re-identification? | |
| CN110866466A (en) | Face recognition method, face recognition device, storage medium and server | |
| US9323989B2 (en) | Tracking device | |
| Fayyaz et al. | An improved surveillance video forgery detection technique using sensor pattern noise and correlation of noise residues | |
| CN111259792A (en) | Face living body detection method based on DWT-LBP-DCT characteristics | |
| CN114387548A (en) | Video and liveness detection method, system, device, storage medium and program product | |
| CN112084881B (en) | Cross-domain pedestrian re-identification method and device and storage medium | |
| CN113239738B (en) | Image blurring detection method and blurring detection device | |
| CN113014876B (en) | Video monitoring method and device, electronic equipment and readable storage medium | |
| US8538142B2 (en) | Face-detection processing methods, image processing devices, and articles of manufacture | |
| Debbarma et al. | Keypoints based copy-move forgery detection of digital images | |
| Li et al. | Teamgl at acrv robotic vision challenge 1: Probabilistic object detection via staged non-suppression ensembling | |
| Maser et al. | Identifying the origin of finger vein samples using texture descriptors | |
| CN108399411B (en) | A kind of multi-cam recognition methods and device | |
| Shaikh et al. | Modality identification for heterogeneous face recognition | |
| Biswas et al. | A new approach of edge detection via polynomial evaluation based gabor filter | |
| CN115170616B (en) | Personnel trajectory analysis method, device, terminal and storage medium | |
| CN115018886B (en) | Motion trajectory identification method, device, equipment and medium | |
| Muhammad et al. | Saliency-based video summarization for face anti-spoofing | |
| KR101422549B1 (en) | Method and system for face recognition |
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 |