SocialTrack: Multi-Object Tracking in Complex Urban Traffic Scenes Inspired by Social Behavior

TL;DR

SocialTrack is a novel multi-object tracking framework designed for complex urban traffic scenes from UAV perspectives, improving detection, trajectory prediction, and target association through social behavior modeling and multi-scale features.

Contribution

The paper introduces SocialTrack, a new multi-object tracking framework that incorporates social behavior priors, multi-scale detection, and adaptive filtering to enhance tracking accuracy in challenging urban environments.

Findings

Outperforms state-of-the-art methods on UAVDT and MOT17 datasets.

Achieves significant improvements in MOTA and IDF1 metrics.

Demonstrates high modularity and compatibility with existing trackers.

Abstract

As a key research direction in the field of multi-object tracking (MOT), UAV-based multi-object tracking has significant application value in the analysis and understanding of urban intelligent transportation systems. However, in complex UAV perspectives, challenges such as small target scale variations, occlusions, nonlinear crossing motions, and motion blur severely hinder the stability of multi-object tracking. To address these challenges, this paper proposes a novel multi-object tracking framework, SocialTrack, aimed at enhancing the tracking accuracy and robustness of small targets in complex urban traffic environments. The specialized small-target detector enhances the detection performance by employing a multi-scale feature enhancement mechanism. The Velocity Adaptive Cubature Kalman Filter (VACKF) improves the accuracy of trajectory prediction by incorporating a velocity dynamic modeling mechanism. The Group Motion Compensation Strategy (GMCS) models social group motion priors to provide stable state update references for low-quality tracks, significantly improving the target association accuracy in complex dynamic environments. Furthermore, the Spatio-Temporal Memory Prediction (STMP) leverages historical trajectory information to predict the future state of low-quality tracks, effectively mitigating identity switching issues. Extensive experiments on the UAVDT and MOT17 datasets demonstrate that SocialTrack outperforms existing state-of-the-art (SOTA) methods across several key metrics. Significant improvements in MOTA and IDF1, among other core performance indicators, highlight its superior robustness and adaptability. Additionally, SocialTrack is highly modular and compatible, allowing for seamless integration with existing trackers to further enhance performance.