Video-based Person Re-identification with Accumulative Motion Context
Preprint
Abstract
Video based person re-identification plays a central role in realistic security and video surveillance. In this paper we propose a novel Accumulative Motion Context (AMOC) network for addressing this important problem, which effectively exploits the long-range motion context for robustly identifying the same person under challenging conditions. Given a video sequence of the same or different persons, the proposed AMOC network jointly learns appearance representation and motion context from a collection of adjacent frames using a two-stream convolutional architecture. Then AMOC accumulates clues from motion context by recurrent aggregation, allowing effective information flow among adjacent frames and capturing dynamic gist of the persons. The architecture of AMOC is end-to-end trainable and thus motion context can be adapted to complement appearance clues under unfavorable conditions (e.g. occlusions). Extensive experiments are conduced on three public benchmark datasets, i.e., the iLIDS-VID, PRID-2011 and MARS datasets, to investigate the performance of AMOC. The experimental results demonstrate that the proposed AMOC network outperforms state-of-the-arts for video-based re-identification significantly and confirm the advantage of exploiting long-range motion context for video based person re-identification, validating our motivation evidently.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- End-to-End Comparative Attention Networks for Person Re-IdentificationIEEE Transactions on Image Processing, 2017
- Convolutional Two-Stream Network Fusion for Video Action Recognition2016
- Person Re-identification by Exploiting Spatio-Temporal Cues and Multi-view Metric LearningIEEE Signal Processing Letters, 2016
- Scalable Person Re-identification: A Benchmark2015
- Deep feature learning with relative distance comparison for person re-identificationPattern Recognition, 2015
- Kernelized Relaxed Margin Components Analysis for Person Re-identificationIEEE Signal Processing Letters, 2014
- Covariance descriptor based on bio-inspired features for person re-identification and face verificationImage and Vision Computing, 2014
- Person Re-Identification Using Kernel-Based Metric Learning Methods2014
- A Database and Evaluation Methodology for Optical FlowInternational Journal of Computer Vision, 2010
- Individual recognition using gait energy imageIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005