Multi-Object Tracking Via Multi-Attention

Data association plays a crucial role in Multi-Object Tracking(MOT), but it is usually suppressed by occlusion. In this paper, we propose an online MOT approach via multiple attention mechanism(Multi-Attention) to handle the frequent interactions between targets. Specifically, the proposed Multi-Att...

Full description

Saved in:
Bibliographic Details
Published in2020 International Joint Conference on Neural Networks (IJCNN) pp. 1 - 8
Main Authors Wang, Xianrui, Ling, Hefei, Chen, Jiazhong, Li, Ping
Format Conference Proceeding
LanguageEnglish
Published IEEE 01.07.2020
Subjects
Attention mechanism
Data association
Feature extraction
Multi-object tracking
Object detection
Object tracking
Receptive filed
Robustness
Target tracking
Task analysis
Trajectory
Online AccessGet full text

Cover

More Information
Summary:Data association plays a crucial role in Multi-Object Tracking(MOT), but it is usually suppressed by occlusion. In this paper, we propose an online MOT approach via multiple attention mechanism(Multi-Attention) to handle the frequent interactions between targets. Specifically, the proposed Multi-Attention consists of spatial-attention, channel-attention, and temporal-attention three modules. The spatial-attention module lets the network focus on visible local areas by generating a visibility map, and the channel-attention module combines texture information and context information adaptively to build a recognizable object descriptor, then the temporal-attention module pays different attention to objects in the same trajectory avoiding the suppress caused by contaminated samples. Besides, a multiple branch convolutional block called receptive filed module(RFModule) is introduced to learn multiple levels of information for Multi-Attention. The experimental results on MOTChallenging benchmarks demonstrate the effectiveness of the proposed MOT algorithm against both online and offline trackers.
ISSN:2161-4407
DOI:10.1109/IJCNN48605.2020.9207631