Perception system based on cooperative fusion of lidar and cameras
- Author
- Martin Dimitrievski (UGent) , David Van Hamme (UGent) and Wilfried Philips (UGent)
- Organization
- Project
- Abstract
- This paper proposes a novel sensor fusion method capable of detection and tracking of road users under nominal as well as in border cases of system operation. The proposed method is based on a sensor-agnostic Bayesian late fusion framework, augmented with an optional exchange of detector activation information between sensors, referred to as cooperative feedback. Experimental evaluation confirms that we obtain competitive detection and tracking performance in normal operation. The main benefit of the proposed method is in cases of sensor failure where, due to the probabilistic modeling, we observed significant improvements of both detection and tracking accuracy over the state of the art.
- Keywords
- cooperative fusion, camera, lidar, tracking
Downloads
-
ieee sensors 2022 submit.pdf
- full text (Accepted manuscript)
- |
- open access
- |
- |
- 692.36 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-8766228
- MLA
- Dimitrievski, Martin, et al. “Perception System Based on Cooperative Fusion of Lidar and Cameras.” IEEE SENSORS 2022, Proceedings, IEEE, 2022, doi:10.1109/SENSORS52175.2022.9967331.
- APA
- Dimitrievski, M., Van Hamme, D., & Philips, W. (2022). Perception system based on cooperative fusion of lidar and cameras. IEEE SENSORS 2022, Proceedings. Presented at the IEEE SENSORS 2022, Dallas, Texas. https://doi.org/10.1109/SENSORS52175.2022.9967331
- Chicago author-date
- Dimitrievski, Martin, David Van Hamme, and Wilfried Philips. 2022. “Perception System Based on Cooperative Fusion of Lidar and Cameras.” In IEEE SENSORS 2022, Proceedings. New York, USA: IEEE. https://doi.org/10.1109/SENSORS52175.2022.9967331.
- Chicago author-date (all authors)
- Dimitrievski, Martin, David Van Hamme, and Wilfried Philips. 2022. “Perception System Based on Cooperative Fusion of Lidar and Cameras.” In IEEE SENSORS 2022, Proceedings. New York, USA: IEEE. doi:10.1109/SENSORS52175.2022.9967331.
- Vancouver
- 1.Dimitrievski M, Van Hamme D, Philips W. Perception system based on cooperative fusion of lidar and cameras. In: IEEE SENSORS 2022, Proceedings. New York, USA: IEEE; 2022.
- IEEE
- [1]M. Dimitrievski, D. Van Hamme, and W. Philips, “Perception system based on cooperative fusion of lidar and cameras,” in IEEE SENSORS 2022, Proceedings, Dallas, Texas, 2022.
@inproceedings{8766228,
abstract = {{This paper proposes a novel sensor fusion method capable of detection and tracking of road users under nominal as well as in border cases of system operation. The proposed method is based on a sensor-agnostic Bayesian late fusion framework, augmented with an optional exchange of detector activation information between sensors, referred to as cooperative feedback. Experimental evaluation confirms that we obtain competitive detection and tracking performance in normal operation. The main benefit of the proposed method is in cases of sensor failure where, due to the probabilistic modeling, we observed significant improvements of both detection and tracking accuracy over the state of the art.}},
author = {{Dimitrievski, Martin and Van Hamme, David and Philips, Wilfried}},
booktitle = {{IEEE SENSORS 2022, Proceedings}},
isbn = {{9781665484657}},
issn = {{1930-0395}},
keywords = {{cooperative fusion,camera,lidar,tracking}},
language = {{eng}},
location = {{Dallas, Texas}},
pages = {{4}},
publisher = {{IEEE}},
title = {{Perception system based on cooperative fusion of lidar and cameras}},
url = {{http://doi.org/10.1109/SENSORS52175.2022.9967331}},
year = {{2022}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: