Learning Correspondence Structures for Person Re-identification
Lin, Weiyao, Shen, Yang, Yan, Junchi, Xu, Mingliang, Wu, Jianxin, Wang, Jingdong, Lu, Ke
–arXiv.org Artificial Intelligence
This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global constraint-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Finally, we also extend our approach by introducing a multi-structure scheme, which learns a set of local correspondence structures to capture the spatial correspondence sub-patterns between a camera pair, so as to handle the spatial misalignments between individual images in a more precise way. Experimental results on various datasets demonstrate the effectiveness of our approach.
arXiv.org Artificial Intelligence
Apr-27-2017
- Country:
- Asia > China
- Beijing > Beijing (0.04)
- Henan Province > Zhengzhou (0.04)
- Jiangsu Province > Nanjing (0.04)
- Shanghai > Shanghai (0.04)
- Asia > China
- Genre:
- Research Report (1.00)
- Technology: