Towards autonomous driving: a machine learning-based pedestrian detection system using 16-layer LiDAR

Mihai, Stefan, Shah, Purav ORCID: https://orcid.org/0000-0002-0113-5690, Mapp, Glenford E. ORCID: https://orcid.org/0000-0002-0539-5852, Nguyen, Huan X. ORCID: https://orcid.org/0000-0002-4105-2558 and Trestian, Ramona ORCID: https://orcid.org/0000-0003-3315-3081 (2020) Towards autonomous driving: a machine learning-based pedestrian detection system using 16-layer LiDAR. Proceedings of the 13th International Conference on Communications (COMM). In: COMM 2020, 18-20 Jun 2020, Bucharest, Romania. . [Conference or Workshop Item] (Accepted/In press)

[img]
Preview
PDF - Final accepted version (with author's formatting)
Download (768kB) | Preview

Abstract

The advent of driverless and automated vehicle technologies opens up a new era of safe and comfortable transportation. However, one of the most important features that an autonomous vehicle requires, is a reliable pedestrian detection mechanism. Many solutions have been proposed in the literature to achieve this technology, ranging from image processing algorithms applied on a camera feed, to filtering LiDAR scans for points that are reflected off pedestrians. To this extent, this paper proposes a machine learning-based pedestrian detection mechanism using a 16-layer Velodyne Puck LITE LiDAR. The proposed mechanism compensates for the low resolution of the LiDAR through the use of linear interpolation between layers, effectively introducing 15 pseudo-layers to help obtain timely detection at practical distances. The pedestrian candidates are then classified u sing a Support Vector Machine ( SVM), and the algorithm is verified by accuracy testing using real LiDAR frames acquired under different road scenarios.

Item Type: Conference or Workshop Item (Paper)
Research Areas: A. > School of Science and Technology > Computer and Communications Engineering
Item ID: 30273
Notes on copyright: © 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Useful Links:
Depositing User: Ramona Trestian
Date Deposited: 04 Jun 2020 09:30
Last Modified: 27 Jul 2020 17:08
URI: https://eprints.mdx.ac.uk/id/eprint/30273

Actions (login required)

View Item View Item