Bayesian Approximation-Based Trajectory Prediction and Tracking with 4D Radar

TL;DR

This paper introduces Bayes-4DRTrack, a novel 4D Radar-based multi-object tracking framework that uses transformer-based motion prediction and Bayesian approximation to improve robustness and accuracy in adverse weather conditions.

Contribution

It presents a new MOT framework combining transformer-based nonlinear motion prediction with Bayesian approximation, enhancing radar-based tracking performance in challenging scenarios.

Findings

Achieved 5.7% higher AMOTA on K-Radar dataset.

Demonstrated improved robustness in adverse weather.

Outperformed traditional methods with fixed noise covariance.

Abstract

Accurate 3D multi-object tracking (MOT) is vital for autonomous vehicles, yet LiDAR and camera-based methods degrade in adverse weather. Meanwhile, Radar-based solutions remain robust but often suffer from limited vertical resolution and simplistic motion models. Existing Kalman filter-based approaches also rely on fixed noise covariance, hampering adaptability when objects make sudden maneuvers. We propose Bayes-4DRTrack, a 4D Radar-based MOT framework that adopts a transformer-based motion prediction network to capture nonlinear motion dynamics and employs Bayesian approximation in both detection and prediction steps. Moreover, our two-stage data association leverages Doppler measurements to better distinguish closely spaced targets. Evaluated on the K-Radar dataset (including adverse weather scenarios), Bayes-4DRTrack demonstrates a 5.7% gain in Average Multi-Object Tracking Accuracy (AMOTA) over methods with traditional motion models and fixed noise covariance. These results showcase enhanced robustness and accuracy in demanding, real-world conditions.