Home // SENSORCOMM 2023, The Seventeenth International Conference on Sensor Technologies and Applications // View article

Cooperative Tracking of People Using Networked LiDARs

Authors:
Marino Matsuba
Ryota Imai
Masafumi Hashimoto
Kazuhiko Takahashi

Keywords: LiDAR; people tracking; cooperative tracking; diffusion strategy; interacting multimodel estimator

Abstract:
This paper presents a tracking method of people using networked Light Detection And Ranging sensors (LiDARs) set in an environment. Each LiDAR detects people from the LiDAR scan data using a background subtraction method and sends the positions of the people to the neigboring LiDARs. It estimates the people’s positions and velocities and exchanges information with the neigboring LiDARs. A Distributed Interacting MultiModel (DIMM)-based method is used to accurately estimate people’s positions and velocities under various motion modes, such as stopping, walking, and suddenly running, in a distributed manner without a central server. Simulation experiments of the tracking of 20 people using three Velodyne 32-layer LiDARs are conducted in two different network topologies (ring and line network topologies) to quantitatively evaluate the tracking performance and computation effort of the proposed method. Simulation results show that the tracking performance and computation time of the DIMM-based method are comparable to those of conventional centralized interacting multimodel-based method.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2023

Publication date: September 25, 2023

Published in: conference

ISSN: 2308-4405

ISBN: 978-1-68558-090-2

Location: Porto, Portugal

Dates: from September 25, 2023 to September 29, 2023