ABOS: an attention-based one-stage framework for person search
Abstract Person search is of great significance to public safety research, such as crime surveillance, video surveillance and security. Person search is a method of locating and identifying the queried person from a complete set of images. The main cause of false recall and missed detection in perso...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-09-01
|
| Series: | EURASIP Journal on Wireless Communications and Networking |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13638-022-02157-9 |
| _version_ | 1798004416442269696 |
|---|---|
| author | Yuqi Chen Dezhi Han Mingming Cui Zhongdai Wu Chin-Chen Chang |
| author_facet | Yuqi Chen Dezhi Han Mingming Cui Zhongdai Wu Chin-Chen Chang |
| author_sort | Yuqi Chen |
| collection | DOAJ |
| description | Abstract Person search is of great significance to public safety research, such as crime surveillance, video surveillance and security. Person search is a method of locating and identifying the queried person from a complete set of images. The main cause of false recall and missed detection in person search is the presence of person occlusion in the images. In order to improve the accuracy of person search when the person to be queried is occluded, this paper proposes an attention-based one-stage framework for person search (ABOS) using an anchor-free model as a baseline. The method uses the channel attention module to express different forms of occlusion and take full advantage of the spatial attention module to highlight the target region of the occluded pedestrians. These attention modules integrate deep and shallow features to guide the network to pay attention to the visible area of the occluded target and extract the semantic information of the pedestrians. Experimental results on CUHK-SYSU and PRW datasets show that the proposed person search method based on attention mechanism in this paper has better performance than existing methods, achieving 93.7 $$\%$$ % of mAP on CUHK-SYSU dataset and 46.4 $$\%$$ % of mAP on PRW dataset, respectively. |
| first_indexed | 2024-04-11T12:24:25Z |
| format | Article |
| id | doaj.art-21ed4c4a350c4db2b1fbc65d030c72f1 |
| institution | Directory Open Access Journal |
| issn | 1687-1499 |
| language | English |
| last_indexed | 2024-04-11T12:24:25Z |
| publishDate | 2022-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Wireless Communications and Networking |
| spelling | doaj.art-21ed4c4a350c4db2b1fbc65d030c72f12022-12-22T04:24:00ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992022-09-012022111410.1186/s13638-022-02157-9ABOS: an attention-based one-stage framework for person searchYuqi Chen0Dezhi Han1Mingming Cui2Zhongdai Wu3Chin-Chen Chang4Department of Engineering, Shanghai Maritime UniversityDepartment of Engineering, Shanghai Maritime UniversityDepartment of Engineering, Shanghai Maritime UniversityShanghai Ship and Shipping Research Institute Co., Ltd.Department of Information Engineering and Computer Science, Feng Chia UniversityAbstract Person search is of great significance to public safety research, such as crime surveillance, video surveillance and security. Person search is a method of locating and identifying the queried person from a complete set of images. The main cause of false recall and missed detection in person search is the presence of person occlusion in the images. In order to improve the accuracy of person search when the person to be queried is occluded, this paper proposes an attention-based one-stage framework for person search (ABOS) using an anchor-free model as a baseline. The method uses the channel attention module to express different forms of occlusion and take full advantage of the spatial attention module to highlight the target region of the occluded pedestrians. These attention modules integrate deep and shallow features to guide the network to pay attention to the visible area of the occluded target and extract the semantic information of the pedestrians. Experimental results on CUHK-SYSU and PRW datasets show that the proposed person search method based on attention mechanism in this paper has better performance than existing methods, achieving 93.7 $$\%$$ % of mAP on CUHK-SYSU dataset and 46.4 $$\%$$ % of mAP on PRW dataset, respectively.https://doi.org/10.1186/s13638-022-02157-9Person searchPerson occlusionAttention mechanismAnchor-free |
| spellingShingle | Yuqi Chen Dezhi Han Mingming Cui Zhongdai Wu Chin-Chen Chang ABOS: an attention-based one-stage framework for person search EURASIP Journal on Wireless Communications and Networking Person search Person occlusion Attention mechanism Anchor-free |
| title | ABOS: an attention-based one-stage framework for person search |
| title_full | ABOS: an attention-based one-stage framework for person search |
| title_fullStr | ABOS: an attention-based one-stage framework for person search |
| title_full_unstemmed | ABOS: an attention-based one-stage framework for person search |
| title_short | ABOS: an attention-based one-stage framework for person search |
| title_sort | abos an attention based one stage framework for person search |
| topic | Person search Person occlusion Attention mechanism Anchor-free |
| url | https://doi.org/10.1186/s13638-022-02157-9 |
| work_keys_str_mv | AT yuqichen abosanattentionbasedonestageframeworkforpersonsearch AT dezhihan abosanattentionbasedonestageframeworkforpersonsearch AT mingmingcui abosanattentionbasedonestageframeworkforpersonsearch AT zhongdaiwu abosanattentionbasedonestageframeworkforpersonsearch AT chinchenchang abosanattentionbasedonestageframeworkforpersonsearch |