Person Re-Identification by Iterative Re-Weighted Sparse Ranking

• Published in: IEEE transactions on pattern analysis and machine intelligence Vol. 37; no. 8; pp. 1629 - 1642
• Main Authors: Lisanti, Giuseppe, Masi, Iacopo, Bagdanov, Andrew D., Del Bimbo, Alberto
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-08-2015; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Biometric Identification - methods; Cameras; Histograms; Humans; Image color analysis; Measurement; person re-identification; Probes; Robustness; sparse methods; Vectors; Video Recording - methods; video surveillance; sparse methods; Person re-identification; video surveillance
• ISSN: 0162-8828; 1939-3539; 2160-9292
• DOI: 10.1109/TPAMI.2014.2369055

In this paper we introduce a method for person re-identification based on discriminative, sparse basis expansions of targets in terms of a labeled gallery of known individuals. We propose an iterative extension to sparse discriminative classifiers capable of ranking many candidate targets. The approach makes use of soft- and hard- re-weighting to redistribute energy among the most relevant contributing elements and to ensure that the best candidates are ranked at each iteration. Our approach also leverages a novel visual descriptor which we show to be discriminative while remaining robust to pose and illumination variations. An extensive comparative evaluation is given demonstrating that our approach achieves state-of-the-art performance on single- and multi-shot person re-identification scenarios on the VIPeR, i-LIDS, ETHZ, and CAVIAR4REID datasets. The combination of our descriptor and iterative sparse basis expansion improves state-of-the-art rank-1 performance by six percentage points on VIPeR and by 20 on CAVIAR4REID compared to other methods with a single gallery image per person. With multiple gallery and probe images per person our approach improves by 17 percentage points the state-of-the-art on i-LIDS and by 72 on CAVIAR4REID at rank-1. The approach is also quite efficient, capable of single-shot person re-identification over galleries containing hundreds of individuals at about 30 re-identifications per second.