Multi‐directional saliency metric learning for person re‐identification
A multi‐directional salience based similarity evaluation for person re‐identification (re‐id) is presented. After distribution analysis for salience consistency between image pairs, a similarity between matched patches is established by weighted fusion of multi‐directional salience. The weight of sa...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2016-10-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2015.0343 |
| _version_ | 1797685088001982464 |
|---|---|
| author | Ying Chen Zhonghua Huo Chunjian Hua |
| author_facet | Ying Chen Zhonghua Huo Chunjian Hua |
| author_sort | Ying Chen |
| collection | DOAJ |
| description | A multi‐directional salience based similarity evaluation for person re‐identification (re‐id) is presented. After distribution analysis for salience consistency between image pairs, a similarity between matched patches is established by weighted fusion of multi‐directional salience. The weight of saliency in each direction is obtained using metric learning by means of structural support vector machines ranking. The discriminative and accurate performance of re‐id is achieved. Compared with existing salience based person matching framework, the proposed method achieves higher re‐id rate with multi‐directional salience based similarity evaluation. |
| first_indexed | 2024-03-12T00:39:14Z |
| format | Article |
| id | doaj.art-856d0af07ab049bc89e01084c35f6a13 |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:39:14Z |
| publishDate | 2016-10-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-856d0af07ab049bc89e01084c35f6a132023-09-15T09:05:18ZengWileyIET Computer Vision1751-96321751-96402016-10-0110762363310.1049/iet-cvi.2015.0343Multi‐directional saliency metric learning for person re‐identificationYing Chen0Zhonghua Huo1Chunjian Hua2Key Laboratory of Advanced Process Control for Light Industry (Ministry of Education)Jiangnan UniversityWuxi214122Jiangsu ProvincePeople's Republic of ChinaKey Laboratory of Advanced Process Control for Light Industry (Ministry of Education)Jiangnan UniversityWuxi214122Jiangsu ProvincePeople's Republic of ChinaJiangsu Key Laboratory of Advanced Food Manufacturing Equipment and Technology KeyJiangnan UniversityWuxi214122Jiangsu ProvincePeople's Republic of ChinaA multi‐directional salience based similarity evaluation for person re‐identification (re‐id) is presented. After distribution analysis for salience consistency between image pairs, a similarity between matched patches is established by weighted fusion of multi‐directional salience. The weight of saliency in each direction is obtained using metric learning by means of structural support vector machines ranking. The discriminative and accurate performance of re‐id is achieved. Compared with existing salience based person matching framework, the proposed method achieves higher re‐id rate with multi‐directional salience based similarity evaluation.https://doi.org/10.1049/iet-cvi.2015.0343multi-directional salience based similarity evaluationperson reidentificationdistribution analysissalience consistencyimage pairsweighted fusion |
| spellingShingle | Ying Chen Zhonghua Huo Chunjian Hua Multi‐directional saliency metric learning for person re‐identification IET Computer Vision multi-directional salience based similarity evaluation person reidentification distribution analysis salience consistency image pairs weighted fusion |
| title | Multi‐directional saliency metric learning for person re‐identification |
| title_full | Multi‐directional saliency metric learning for person re‐identification |
| title_fullStr | Multi‐directional saliency metric learning for person re‐identification |
| title_full_unstemmed | Multi‐directional saliency metric learning for person re‐identification |
| title_short | Multi‐directional saliency metric learning for person re‐identification |
| title_sort | multi directional saliency metric learning for person re identification |
| topic | multi-directional salience based similarity evaluation person reidentification distribution analysis salience consistency image pairs weighted fusion |
| url | https://doi.org/10.1049/iet-cvi.2015.0343 |
| work_keys_str_mv | AT yingchen multidirectionalsaliencymetriclearningforpersonreidentification AT zhonghuahuo multidirectionalsaliencymetriclearningforpersonreidentification AT chunjianhua multidirectionalsaliencymetriclearningforpersonreidentification |