Probabilistic approach for road-users detection

Melotti, G., Lu, W. , Conde, P., Zhao, D. , Asvadi, A., Gonçalves, N. and Premebida, C. (2023) Probabilistic approach for road-users detection. IEEE Transactions on Intelligent Transportation Systems, 24(9), pp. 9253-9267. (doi: 10.1109/TITS.2023.3268578)

Abstract

Object detection in autonomous driving applications implies the detection and tracking of semantic objects that are commonly native to urban driving environments, as pedestrians and vehicles. One of the major challenges in state-of-the-art deep-learning based object detection are false positives which occur with overconfident scores. This is highly undesirable in autonomous driving and other critical robotic-perception domains because of safety concerns. This paper proposes an approach to alleviate the problem of overconfident predictions by introducing a novel probabilistic layer to deep object detection networks in testing. The suggested approach avoids the traditional Sigmoid or Softmax prediction layer which often produces overconfident predictions. It is demonstrated that the proposed technique reduces overconfidence in the false positives without degrading the performance on the true positives. The approach is validated on the 2D-KITTI objection detection through the YOLOV4 and SECOND (Lidar-based detector). The proposed approach enables interpretable probabilistic predictions without the requirement of re-training the network and therefore is very practical.

• Item Type: Articles
• Additional Information: This work was supported by the Fundação para a Ciência e a Tecnologia (FCT) under Project UIDB/00048/2020.
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zhao, Dr Dezong and Lu, Weihao
• Authors: Melotti, G., Lu, W., Conde, P., Zhao, D., Asvadi, A., Gonçalves, N., and Premebida, C.
• College/School: College of Science and Engineering > School of Engineering; College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity
• Journal Name: IEEE Transactions on Intelligent Transportation Systems
• Publisher: IEEE
• ISSN: 1524-9050
• ISSN (Online): 1558-0016
• Published Online: 03 May 2023
• Copyright Holders: Copyright © 2023 IEEE
• First Published: First published in IEEE Transactions on Intelligent Transportation Systems 24(9):9253 - 9267
• Publisher Policy: Reproduced in accordance with the publisher copyright policy