Improving 3D vulnerable road user detection with point augmentation

Lu, W., Zhao, D. , Premebida, C., Zhang, L., Zhao, W. and Tian, D. (2023) Improving 3D vulnerable road user detection with point augmentation. IEEE Transactions on Intelligent Vehicles, 8(5), pp. 3489-3505. (doi: 10.1109/TIV.2023.3246797)

Abstract

Point clouds have been a popular representation to describe 3D environments for autonomous driving applications. Despite accurate depth information, sparsity of pointsresults in difficulties in extracting sufficient features from vulnerable objects of small sizes. One solution is leveraging self-attention networks to build long-range connections between similar objects. Another method is using generative models to estimate the complete shape of objects. Both approaches introduce large memory consumption and extra complexity to the models while the geometric characteristics of objects are overlooked. To overcome this problem, this paper proposes Point Augmentation (PA)- RCNN, focusing on small object detection by generating efficient complementary features without trainable parameters. Specifically, 3D points are sampled with the guidance of object proposals and encoded through the 3D grid-based feature aggregation to produce localised 3D voxel properties. Such voxel attributes are fed to the pooling module with the aid of fictional points, which are transformed from sampled points considering geometric symmetry. Experimental results on Waymo Open Dataset and KITTI dataset show a superior advantage in the detection of distant and small objects in comparison with existing state-ofthe- art methods.

• Item Type: Articles
• Additional Information: This work was sponsored in part by the Engineering and Physical Sciences Research Council of the UK under the EPSRC Innovation Fellowship (EP/S001956/2) and in part by the Newton Advanced Fellowship (UK-China International Cooperation and Exchange Project) jointly supported by the UK Royal Society (NAF\R1\201213).
• Status: Published
• Refereed: Yes
• Glasgow Author(s) Enlighten ID: Zhao, Dr Dezong and Lu, Mr Weihao
• Authors: Lu, W., Zhao, D., Premebida, C., Zhang, L., Zhao, W., and Tian, D.
• College/School: College of Science and Engineering > School of Engineering > Autonomous Systems and Connectivity
• Journal Name: IEEE Transactions on Intelligent Vehicles
• Publisher: IEEE
• ISSN: 2379-8858
• ISSN (Online): 2379-8904
• Published Online: 20 February 2023
• Copyright Holders: Copyright © 2023 IEEE
• First Published: First published in IEEE Transactions on Intelligent Vehicles 8(5): 3489-3505
• Publisher Policy: Reproduced with the permission of the Publisher

Project Code	Award No	Project Name	Principal Investigator	Funder's Name	Funder Ref	Lead Dept
314774		Toward Energy Efficient Autonomous Vehiciles via Cloud-Aided learning	Dezong Zhao	Engineering and Physical Sciences Research Council (EPSRC)	EP/S001956/2	ENG - Autonomous Systems & Connectivity