3D Multi-Object Tracking with Semi-Supervised GRU-Kalman Filter

TL;DR

This paper introduces a semi-supervised GRU-Kalman filter approach for 3D multi-object tracking that learns complex motion patterns directly from data, improving accuracy over traditional linear models.

Contribution

The novel integration of a learnable Kalman filter with a semi-supervised training strategy enables data-driven motion modeling in 3D MOT, surpassing existing methods.

Findings

Outperforms traditional tracking-by-detection methods on nuScenes and Argoverse2 datasets.

Learns complex, nonlinear object motion without manual model design.

Improves robustness and convergence speed through semi-supervised learning.

Abstract

3D Multi-Object Tracking (MOT), a fundamental component of environmental perception, is essential for intelligent systems like autonomous driving and robotic sensing. Although Tracking-by-Detection frameworks have demonstrated excellent performance in recent years, their application in real-world scenarios faces significant challenges. Object movement in complex environments is often highly nonlinear, while existing methods typically rely on linear approximations of motion. Furthermore, system noise is frequently modeled as a Gaussian distribution, which fails to capture the true complexity of the noise dynamics. These oversimplified modeling assumptions can lead to significant reductions in tracking precision. To address this, we propose a GRU-based MOT method, which introduces a learnable Kalman filter into the motion module. This approach is able to learn object motion characteristics through data-driven learning, thereby avoiding the need for manual model design and model error. At the same time, to avoid abnormal supervision caused by the wrong association between annotations and trajectories, we design a semi-supervised learning strategy to accelerate the convergence speed and improve the robustness of the model. Evaluation experiment on the nuScenes and Argoverse2 datasets demonstrates that our system exhibits superior performance and significant potential compared to traditional TBD methods.