Hierarchical Integration of Rich Features for Video-Based Person Re-Identification

作     者：Liu, Zheng Wang, Yunhong Li, Annan 

作者机构：Beihang Univ State Key Lab Virtual Real Technol & Syst Sch Engn & Comp Sci Beijing 100083 Peoples R China Beihang Univ Beijing Adv Innovat Ctr Big Data & Brain Comp Beijing 100083 Peoples R China 

出 版 物：《IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY》 (IEEE Trans Circuits Syst Video Technol)

年 卷 期：2019年第29卷第12期

页      面：3646-3659页

核心收录：

学科分类：0808[工学-电气工程] 08[工学] 

基　　金：National Key Research and Development Program of China [2016YFB1001002] 

主　　题：Feature extraction Legged locomotion Semantics Optical computing Optical imaging Visualization Recurrent neural networks Person re-identification spatio-temporal aggregation similarity measuring multi-model ensemble 

摘      要：Person re-identification (ReID) aims to associate the identity of pedestrians captured by cameras across non-overlapped areas. Video-based ReID plays an important role in intelligent video surveillance systems and has attracted growing attention in recent years. In this paper, we propose an end-to-end video-based ReID framework based on the convolutional neural network (CNN) for efficient spatio-temporal modeling and enhanced similarity measuring. Specifically, we build our descriptor of sequences by basic mathematical calculations on the semantic mid-level image features, which avoids the time consuming computations and the loss of spatial correlations. We further hierarchically extract image features from multiple intermediate CNN stages to build multi-level sequence descriptors. For a descriptor at one stage, we design an effective auxiliary pairwise loss which is jointly optimized with a triplet loss. To integrate hierarchical representation, we propose an intuitive yet effective summation-based similarity integration scheme to match identities more accurately. Furthermore, we extend our framework by a multi-model ensemble strategy, which effectively assembles three popular CNN models to represent walking sequences more comprehensively and improve the performance. Extensive experiments on three video-based ReID datasets show that the proposed framework outperforms the state-of-the-art methods.