GenTrack2: An Improved Hybrid Approach for Multi-Object Tracking

TL;DR

GenTrack2 introduces a hybrid multi-object tracking method combining stochastic particle filtering with deterministic association, improving identifier consistency and robustness in complex scenarios, demonstrated by superior experimental performance.

Contribution

The paper presents a novel hybrid tracking approach that integrates stochastic particle filtering with deterministic association, including a new scheme for smooth state updates and velocity regression.

Findings

Outperforms state-of-the-art trackers in experiments

Handles weak tracks during occlusions effectively

Operates well on both pre-recorded and live videos

Abstract

This paper proposes a visual multi-object tracking method that jointly employs stochastic and deterministic mechanisms to ensure identifier consistency for unknown and time-varying target numbers under nonlinear dynamics. A stochastic particle filter addresses nonlinear dynamics and non-Gaussian noise, with support from particle swarm optimization (PSO) to guide particles toward state distribution modes and mitigate divergence through proposed fitness measures incorporating motion consistency, appearance similarity, and social-interaction cues with neighboring targets. Deterministic association further enforces identifier consistency via a proposed cost matrix incorporating spatial consistency between particles and current detections, detection confidences, and track penalties. Subsequently, a novel scheme is proposed for the smooth updating of target states while preserving their identities, particularly for weak tracks during interactions with other targets and prolonged occlusions. Moreover, velocity regression over past states provides trend-seed velocities, enhancing particle sampling and state updates. The proposed tracker is designed to operate flexibly for both pre-recorded videos and camera live streams, where future frames are unavailable. Experimental results confirm superior performance compared to state-of-the-art trackers. The source-code reference implementations of both the proposed method and compared-trackers are provided on GitHub: https://github.com/SDU-VelKoTek/GenTrack2