Deep Alignment Network Based Multi-Person Tracking With Occlusion and Motion Reasoning
- 10 October 2018
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 21 (5), 1183-1194
- https://doi.org/10.1109/tmm.2018.2875360
Abstract
Tracking-by-detection is one of the most common paradigms for multi-person tracking, due to the availability of automatic pedestrian detectors. However, existing multi-person trackers are greatly challenged by misalignment in the pedestrian detectors (i.e., excessive background and part missing) and occlusion. To address these problems, we propose a deep alignment network based multi-person tracking method with occlusion and motion reasoning. Specifically, the inaccurate detections are firstly corrected via a deep alignment network, in which an alignment estimation module is used to automatically learn the spatial transformation of these detections. As a result, the deep features from our alignment network will have a better representation power and thus lead to more consistent tracks. Then, a coarse-to-fine schema is designed for construing a discriminative association cost matrix with spatial, motion and appearance information. Meanwhile, a principled approach is developed to allow our method to handle occlusion with motion reasoning and the re-identification ability of the pedestrian alignment network. Finally, a simple yet real-time Hungarian algorithm is employed to solve the association problem. Comprehensive experiments on MOT16, ISSIA soccer, PETS09 and TUD datasets validate the effectiveness and robustness of the proposed method.Keywords
Funding Information
- National Natural Science Foundation of China (61572205, 61802135)
- Natural Science Foundation of Fujian Province (2017J01113)
This publication has 51 references indexed in Scilit:
- GMMCP tracker: Globally optimal Generalized Maximum Multi Clique problem for multiple object trackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2015
- Audio Assisted Robust Visual Tracking With Adaptive Particle FilteringIEEE Transactions on Multimedia, 2014
- Occlusion Geodesics for Online Multi-object TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- Multi-cue Visual Tracking Using Robust Feature-Level Fusion Based on Joint Sparse RepresentationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2014
- The Way They Move: Tracking Multiple Targets with Similar AppearancePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- 3D Traffic Scene Understanding From Movable PlatformsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Detection- and Trajectory-Level Exclusion in Multiple Object TrackingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2013
- Continuous Energy Minimization for Multitarget TrackingIEEE Transactions on Pattern Analysis and Machine Intelligence, 2013
- Evaluating Multiple Object Tracking Performance: The CLEAR MOT MetricsEURASIP Journal on Image and Video Processing, 2008
- The Hungarian method for the assignment problemNaval Research Logistics Quarterly, 1955