We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
Sparse coding with cross-view invariant dictionaries for person re-identification.
- Authors
Xu, Yunlu; Guo, Jie; Huang, Zheng; Qiu, Weidong
- Abstract
The task of matching observations of the same person in disjoint views captured by non-overlapping cameras is known as the person re-identification problem. It is challenging owing to low-quality images, inter-object occlusions, and variations in illumination, viewpoints and poses. Unlike previous approaches that learn Mahalanobis-like distance metrics, we propose a novel approach based on dictionary learning that takes the advances of sparse coding of discriminatingly and cross-view invariantly encoding features representing different people. Firstly, we propose a robust and discriminative feature extraction method of different feature levels. The feature representations are projected to a lower computation common subspace. Secondly, we learn a single cross-view invariant dictionary for each feature level for different camera views and a fusion strategy is utilized to generate the final matching results. Experimental statistics show the superior performance of our approach by comparing with state-of-the-art methods on two publicly available benchmark datasets VIPeR and PRID 2011.
- Subjects
IMAGE quality analysis; COMPRESSED sensing; FEATURE extraction; DESCRIPTOR systems; METRIC projections
- Publication
Multimedia Tools & Applications, 2018, Vol 77, Issue 9, p10715
- ISSN
1380-7501
- Publication type
Article
- DOI
10.1007/s11042-017-4893-5