Person re‐identification based on contextual characteristic. Issue 17 (1st August 2013)

• Record Type: Journal Article
• Authors: Leng, Qingming; Hu, Ruimin; Liang, Chao; Wang, Yimin
• Is Part Of: Electronics letters. Volume 49:Issue 17(2013)
• Page Start: 1074
• Page End: 1076
• Publication Date: 2013-08-01
• Subjects: feature extraction -- image matching -- learning (artificial intelligence) -- pattern clustering; gallery image ranking -- Mahalanobis distance -- kÌ‐farthest neighbors -- k‐nearest neighbours -- movement factors -- appearance feature variation -- precise feature matching -- distance metric learning -- robust appearance descriptors -- contextual characteristic -- person reidentification; Electronics -- Periodicals; 621.381
• DOI: 10.1049/el.2013.1464
• Languages: English
• ISSNs: 0013-5194

Abstract

Abstract : An efficient contextual characteristic is proposed for person re‐identification. Most current approaches are based on either constructing robust appearance descriptors or learning a distance metric for precise feature matching. However, re‐identifying results may be inaccurate and not robust due to appearance features variation caused by various environment changes and individual movement factors. In this reported work consideration is given to the introduction of the contextual characteristic that contains similarities of both k ‐nearest and ḱ ‐farthest neighbours between the probe and the gallery, and combines it with Mahalanobis distance for ranking every gallery image more accurately. The experimental result has validated the effectiveness of the proposed method on a challenging publicly available dataset.