An Adaptive Multi-Projection Metric Learning for Person Re-Identification Across Non-Overlapping Cameras

• Published in: IEEE transactions on circuits and systems for video technology Vol. 29; no. 9; pp. 2809 - 2821
• Main Authors: Hu, Hai-Miao, Fang, Wen, Li, Bo, Tian, Qi
• Format: Journal Article
• Language: English
• Published: New York IEEE 01.09.2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: adaptive multi-projection metric learning; Cameras; Computer science; Identification; Identification methods; Image color analysis; Learning; Learning systems; Lighting; Measurement; Methods; metric learning; multi-projection metric learning; Performance enhancement; Person re-identification; Projection; Training
• ISSN: 1051-8215; 1558-2205
• DOI: 10.1109/TCSVT.2018.2869898

Person re-identification is one of the most important and challenging problems in video analytics systems; it aims to match people across non-overlapping camera views. For person re-identification, metric learning is introduced to improve the performance by providing a metric adapted for cross-view matching. The essence of metric learning is to search for an optimal projection matrix to project the original features into a new feature space. However, most existing metric learning methods overlook the inconsistency of feature distributions in multiple cameras. In this paper, we propose a multi-projection metric learning (MPML) method to overcome the inconsistency among multiple cameras in person re-identification. Our solution is to jointly learn multiple projection matrices using paired samples from different cameras to project features from different cameras into a common feature space. To make our method adaptive to newly added cameras without affecting the learned projection matrices, we further propose an adaptive MPML method, which can learn new camera projection matrices without having to update any of the obtained projection matrices. The proposed methods are evaluated on four major person re-identification data sets, with comprehensive experiments showing the effectiveness of the proposed methods and notable improvements over the state-of-the-art approaches.