Bayesian Approximation-Based Trajectory Prediction and Tracking with 4D Radar
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913675826167808 |
|---|---|
| author | Kim, Dong-In Paek, Dong-Hee Song, Seung-Hyun Kong, Seung-Hyun |
| author_facet | Kim, Dong-In Paek, Dong-Hee Song, Seung-Hyun Kong, Seung-Hyun |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_01357 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Bayesian Approximation-Based Trajectory Prediction and Tracking with 4D Radar Kim, Dong-In Paek, Dong-Hee Song, Seung-Hyun Kong, Seung-Hyun Computer Vision and Pattern Recognition 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. |
| title | Bayesian Approximation-Based Trajectory Prediction and Tracking with 4D Radar |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.01357 |