Hierarchical Integration of Rich Features for Video-Based Person Re-Identification
- 29 November 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. 29 (12), 3646-3659
- https://doi.org/10.1109/tcsvt.2018.2883995
Abstract
Person re-identification (ReID) aims to associate the identity of pedestrians captured by cameras across nonoverlapped 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-toend 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 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.Funding Information
- National Basic Research Program of China (2016YFB1001002)
This publication has 80 references indexed in Scilit:
- Bit-Scalable Deep Hashing With Regularized Similarity Learning for Image Retrieval and Person Re-IdentificationIEEE Transactions on Image Processing, 2015
- Relevance Metric Learning for Person Re-Identification by Exploiting Listwise SimilaritiesIEEE Transactions on Image Processing, 2015
- Localized Multifeature Metric Learning for Image-Set-Based Face RecognitionIEEE Transactions on Circuits and Systems for Video Technology, 2015
- Person Re-identification Using Data-Driven Metric AdaptationLecture Notes in Computer Science, 2015
- Re-Identification in the Function Space of Feature WarpsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Person Re-Identification by Iterative Re-Weighted Sparse RankingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2014
- Soft Biometrics; Human Identification Using Comparative DescriptionsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Context-based person identification framework for smart video surveillanceMachine Vision and Applications, 2013
- Person Re-identification by Descriptive and Discriminative ClassificationLecture Notes in Computer Science, 2011
- A Spatio-Temporal Descriptor Based on 3D-GradientsPublished by British Machine Vision Association and Society for Pattern Recognition ,2008