GroupTrack: Multi-Object Tracking by Using Group Motion Patterns

The main challenge of Multi-Object Tracking (MOT) lies in maintaining a distinctive identity for each target in dense crowds or occluded scenarios. Although the existing methods have achieved significantly progress by using robust object detectors or complex association strategies, they cannot effectively solve long-term tracking due to individually motion or appearance modeling for each single target. In this paper, we propose a novel 2D MOT tracker GroupTrack, to learn reliable motion state for each target using group motion patterns. Specifically, for each tracklet, we first choose its neighboring ones to form a group of motion patterns, which can provide informative clues for the motion estimation of the current tracklet. Then, we apply the group motion patterns to perform tracklet prediction and data association. By integrating prior from neighboring motion patterns into the data association process, GroupTrack provides a new paradigm for target motion modeling in extremely crowded and occluded scenarios. Through extensive experiments on the public MOT17 and MOT20 datasets, we demonstrate the effectiveness of our approach in challenging scenarios and show state-of-the-art performance at various MOT metrics.

Authors

• Xinglong Xu
• Weihong Ren
• Gan Sun
• Haoyu Ji 0001
• Yu Gao 0010
• Honghai Liu 0001

Keywords

• Measurement
• Target tracking
• Three-dimensional displays
• Tracking
• Motion estimation
• Detectors
• Reliability
• Object tracking
• Pattern matching
• Intelligent robots
• Motion Patterns
• Multi-object Tracking
• Public Datasets
• Object Detection
• Patterns Of Groups
• Motion Model
• Long-term Tracking
• Crowd Density
• Prediction Accuracy
• Pedestrian
• Low Confidence
• Confidence Score
• Deep Learning Techniques
• Tracking Performance
• Target State
• Video Sequences
• Appearance Features
• Graph Neural Networks
• Current Frame
• Prior Estimates
• Detection Boxes
• Tracking Results
• Individual Motor
• Perspective Camera
• False Matches
• Dynamic Scenes
• Previous Frame