Attention and Texture Feature Enhancement for Person Re-identification
In view of the low accuracy of existing person re-identification to deal with low image resolution, illuminative difference, posture and perspective diversity, this paper proposes a multi-task pedestrian recognition algorithm based on spatial attention and texture feature enhancement. The spatial at...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press
2022-03-01
|
| Series: | Jisuanji kexue yu tansuo |
| Subjects: | |
| Online Access: | http://fcst.ceaj.org/fileup/1673-9418/PDF/2010046.pdf |
| _version_ | 1831573134251130880 |
|---|---|
| author | LI Jie |
| author_facet | LI Jie |
| author_sort | LI Jie |
| collection | DOAJ |
| description | In view of the low accuracy of existing person re-identification to deal with low image resolution, illuminative difference, posture and perspective diversity, this paper proposes a multi-task pedestrian recognition algorithm based on spatial attention and texture feature enhancement. The spatial attention module designed by the algorithm pays more attention to the potential image areas related to the pedestrian attributes, which further explores attribute features. The texture feature enhancement module of the person re-identification network reduces the interference of light, occlusion on person re-identification by fusing the global and local features corresponding to different spatial levels. Finally, the multi-stage weighted loss function integrates the attribute features and pedestrian features to avoid the decrease of mean average precision caused by attribute heterogeneity. Experimental results show that the mean average precision can achieve 81.1% and 70.1% respectively on the Market-1501 and DukeMTMC-reID datasets. |
| first_indexed | 2024-12-17T13:40:06Z |
| format | Article |
| id | doaj.art-3152cbff5e914b3989d9ea22f59790b7 |
| institution | Directory Open Access Journal |
| issn | 1673-9418 |
| language | zho |
| last_indexed | 2024-12-17T13:40:06Z |
| publishDate | 2022-03-01 |
| publisher | Journal of Computer Engineering and Applications Beijing Co., Ltd., Science Press |
| record_format | Article |
| series | Jisuanji kexue yu tansuo |
| spelling | doaj.art-3152cbff5e914b3989d9ea22f59790b72022-12-21T21:46:19ZzhoJournal of Computer Engineering and Applications Beijing Co., Ltd., Science PressJisuanji kexue yu tansuo1673-94182022-03-0116366166810.3778/j.issn.1673-9418.2010046Attention and Texture Feature Enhancement for Person Re-identificationLI Jie0Information Network Center, Civil Aviation University of China, Tianjin 300300, ChinaIn view of the low accuracy of existing person re-identification to deal with low image resolution, illuminative difference, posture and perspective diversity, this paper proposes a multi-task pedestrian recognition algorithm based on spatial attention and texture feature enhancement. The spatial attention module designed by the algorithm pays more attention to the potential image areas related to the pedestrian attributes, which further explores attribute features. The texture feature enhancement module of the person re-identification network reduces the interference of light, occlusion on person re-identification by fusing the global and local features corresponding to different spatial levels. Finally, the multi-stage weighted loss function integrates the attribute features and pedestrian features to avoid the decrease of mean average precision caused by attribute heterogeneity. Experimental results show that the mean average precision can achieve 81.1% and 70.1% respectively on the Market-1501 and DukeMTMC-reID datasets.http://fcst.ceaj.org/fileup/1673-9418/PDF/2010046.pdf|spatial attention|texture feature enhancement|pedestrian attributes|person re-identification |
| spellingShingle | LI Jie Attention and Texture Feature Enhancement for Person Re-identification Jisuanji kexue yu tansuo |spatial attention|texture feature enhancement|pedestrian attributes|person re-identification |
| title | Attention and Texture Feature Enhancement for Person Re-identification |
| title_full | Attention and Texture Feature Enhancement for Person Re-identification |
| title_fullStr | Attention and Texture Feature Enhancement for Person Re-identification |
| title_full_unstemmed | Attention and Texture Feature Enhancement for Person Re-identification |
| title_short | Attention and Texture Feature Enhancement for Person Re-identification |
| title_sort | attention and texture feature enhancement for person re identification |
| topic | |spatial attention|texture feature enhancement|pedestrian attributes|person re-identification |
| url | http://fcst.ceaj.org/fileup/1673-9418/PDF/2010046.pdf |
| work_keys_str_mv | AT lijie attentionandtexturefeatureenhancementforpersonreidentification |