Multi-shot human re-identification using a fast multi-scale video covariance descriptor. (October 2017)

• Record Type: Journal Article
• Authors: Hadjkacem, Bassem; Ayedi, Walid; Abid, Mohamed; Snoussi, Hichem
• Is Part Of: Engineering applications of artificial intelligence. Volume 65(2017:May)
• Page Start: 60
• Page End: 67
• Publication Date: 2017-10
• Subjects: Person re-identification -- Multi-scale features -- Video Tree Structure -- Spatio-temporal covariance -- Moving regions; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2017.07.010
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: Multi-shot person re-identification in non-overlapping camera networks has become an important research area. In order to tackle this problem, a robust and adaptive person modeling against occlusion and uncontrolled changes is required. In this paper, a new Multi-Scale Video Covariance (MS-VC) unsupervised approach was proposed to efficiently describe human in motion and requires no labeled training data. The MS-VC approach is based on the computing of the features extracted from a new structured representation called Video Tree Structure (VIDTREST) of any video sequence and can efficiently describe behavioral biometrics and appearance of each human by combining spatio-temporal information in a fixed-size vector. The VIDTREST model captures moving regions of interest. In addition, it decreases the color weight which can discard background noise and resolve clothing similarity cases in the appearance models and other changes. Furthermore, a fast algorithm was suggested to decompose each sequence under VIDTREST, extract its multi-scale features and compute its covariance matrices in one pass. The proposed method was evaluated with CAVIAR and PRID datasets. Our experimental results outperform the recognition rates of the existing unsupervised approaches in-the-state-of-the-art. Highlights: An introduction of a multi-scale video covariance descriptor (MS-VC). Image sequence representation by a novel video tree structure (VIDTREST). Proposition of a fast algorithm to compute multi-scale features and signatures. An MS-VC integrates spatio-temporal features and VIDTREST form to discard noise. The effectiveness of MS-VC was proved on CAVIAR and PRID databases.