State-aware Re-identification Feature for Multi-target Multi-camera Tracking

Abstract

Multi-target Multi-camera Tracking (MTMCT) aims to extract the trajectories from videos captured by a set of cameras. Recently, the tracking performance of MTMCT is significantly enhanced with the employment of re-identification (Re-ID) model. However, the appearance feature usually becomes unreliable due to the occlusion and orientation variance of the targets. Directly applying Re-ID model in MTMCT will encounter the problem of identity switches (IDS) and tracklet fragment caused by occlusion. To solve these problems, we propose a novel tracking framework in this paper. In this framework, the occlusion status and orientation information are utilized in Re-ID model with human pose information considered. In addition, the tracklet association using the proposed fused tracking feature is adopted to handle the fragment problem. The proposed tracker achieves 81.3\% IDF1 on the multiple-camera hard sequence, which outperforms all other reference methods by a large margin.

To appear in CVPR-2019 TRMTMCT Workshop

References in corpus (12)

• Multiple Object Tracking: A Literature Review
• Person Transfer GAN to Bridge Domain Gap for Person Re-Identification
• Multi-Object Tracking with Multiple Cues and Switcher-Aware Classification
• Multi-Target, Multi-Camera Tracking by Hierarchical Clustering: Recent Progress on DukeMTMC Project
• Multi-Target Tracking in Multiple Non-Overlapping Cameras using Constrained Dominant Sets
• Tracklet Association Tracker: An End-to-End Learning-based Association Approach for Multi-Object Tracking
• Multi-camera Multi-Object Tracking
• Exploit the Connectivity: Multi-Object Tracking with TrackletNet
• Deep Affinity Network for Multiple Object Tracking
• Multi-hierarchical Independent Correlation Filters for Visual Tracking
• Multiple People Tracking Using Hierarchical Deep Tracklet Re-identification
• Learning Non-Uniform Hypergraph for Multi-Object Tracking