Data fusion is one of the key aspects in robust and failure-tolerant vulnerable road user (VRU) perception systems. This paper presents a multi-radar sensor fusion platform that enables automatic detection, tracking and classification of pedestrians and cyclists while aiming to support fail-safe system operation. The sensor fusion platform encapsulates two main modules working concurrently: the first detection-to-detection fusion module performs a spatio-temporal alignment of radar detections, data association of the aligned detections and finally multi-object tracking; the second module is the sensor failure management block, which is responsible for fault-tolerant system operation and encapsulates multilevel verification subsystem. The proposed multi - radar fusion system is experimentally evaluated through multi-target scenarios. Demonstrated results show effectiveness of the proposed platform and failure-tolerance of the system compared to a single sensor solution.
Rykunov, M, De Greef, E, Khalid, H, Aziz, K, Bourdoux, A & Sahli, H 2021, Multi-Radar Fusion for Failure-tolerant Vulnerable Road Users Classification. in 2021 18th European Radar Conference (EuRAD). IEEE, pp. 337-340, European Radar Conference 2021, London, United Kingdom, 16/02/22. https://doi.org/10.23919/EuRAD50154.2022.9784533
Rykunov, M., De Greef, E., Khalid, H., Aziz, K., Bourdoux, A., & Sahli, H. (2021). Multi-Radar Fusion for Failure-tolerant Vulnerable Road Users Classification. In 2021 18th European Radar Conference (EuRAD) (pp. 337-340). IEEE. https://doi.org/10.23919/EuRAD50154.2022.9784533
@inproceedings{19b2b57ae6374cd2b7878834dec27890,
title = "Multi-Radar Fusion for Failure-tolerant Vulnerable Road Users Classification",
abstract = "Data fusion is one of the key aspects in robust and failure-tolerant vulnerable road user (VRU) perception systems. This paper presents a multi-radar sensor fusion platform that enables automatic detection, tracking and classification of pedestrians and cyclists while aiming to support fail-safe system operation. The sensor fusion platform encapsulates two main modules working concurrently: the first detection-to-detection fusion module performs a spatio-temporal alignment of radar detections, data association of the aligned detections and finally multi-object tracking; the second module is the sensor failure management block, which is responsible for fault-tolerant system operation and encapsulates multilevel verification subsystem. The proposed multi - radar fusion system is experimentally evaluated through multi-target scenarios. Demonstrated results show effectiveness of the proposed platform and failure-tolerance of the system compared to a single sensor solution.",
author = "Maxim Rykunov and \{De Greef\}, Eddy and Habib Khalid and Kheireddine Aziz and Andre Bourdoux and Hichem Sahli",
year = "2021",
doi = "10.23919/EuRAD50154.2022.9784533",
language = "English",
isbn = "9781665447232",
pages = "337--340",
booktitle = "2021 18th European Radar Conference (EuRAD)",
publisher = "IEEE",
note = "European Radar Conference 2021, EuRad21 ; Conference date: 16-02-2022 Through 18-02-2022",
url = "https://www.eumw2021.com/conferences/eurad.html",
}