CVFeb 3, 2025

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

arXiv:2502.01357v1h-index: 92025 IEEE Intelligent Vehicles Symposium (IV)
Originality Incremental advance
AI Analysis

This addresses robust tracking for autonomous vehicles in challenging conditions, representing an incremental improvement over existing Radar-based solutions.

The paper tackled the problem of accurate 3D multi-object tracking for autonomous vehicles in adverse weather by proposing a 4D Radar-based framework, achieving a 5.7% gain in AMOTA over traditional methods.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes