Real-time Spatial-temporal Context Approach for 3D Object Detection using LiDAR

K. Kumar, Samir Al-Stouhi

2020

Abstract

This paper proposes a real-time spatial-temporal context approach for BEV object detection and classification using LiDAR point-clouds. Current state-of-art BEV object-detection approaches focused mainly on single-frame point-clouds while the temporal factor is rarely exploited. In current approach, we aggregate 3D LiDAR point clouds over time to produce a 4D tensor, which is then fed to a one-shot fully convolutional detector to predict oriented 3D object bounding-box information along with object class. Four different techniques are evaluated to incorporate the temporal dimension; a) joint training b) CLSTM c) non-local context network (NLCN) d) spatial-temporal context network (STCN). The experiments are conducted on large-scale Argoverse dataset and results shows that by using NLCN and STCN, mAP accuracy is increased by a large margin over single frame 3D object detector and YOLO4D 3D object detection with our approach running at a speed of 28fps.

Paper Citation

in Harvard Style

Kumar K. and Al-Stouhi S. (2020). Real-time Spatial-temporal Context Approach for 3D Object Detection using LiDAR.In Proceedings of the 6th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS, ISBN 978-989-758-419-0, pages 432-439. DOI: 10.5220/0009340004320439

in Bibtex Style

@conference{vehits20,
author={K. Kumar and Samir Al-Stouhi},
title={Real-time Spatial-temporal Context Approach for 3D Object Detection using LiDAR},
booktitle={Proceedings of the 6th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,},
year={2020},
pages={432-439},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009340004320439},
isbn={978-989-758-419-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 6th International Conference on Vehicle Technology and Intelligent Transport Systems - Volume 1: VEHITS,
TI - Real-time Spatial-temporal Context Approach for 3D Object Detection using LiDAR
SN - 978-989-758-419-0
AU - Kumar K.
AU - Al-Stouhi S.
PY - 2020
SP - 432
EP - 439
DO - 10.5220/0009340004320439