Home // INTELLI 2016, The Fifth International Conference on Intelligent Systems and Applications // View article

Laser-based Cooperative Estimation of Pose and Size of Moving Objects using Multiple Mobile Robots

Authors:
Yuto Tamura
Ryohei Murabayashi
Masafumi Hashimoto
Kazuhiko Takahashi

Keywords: moving-object tracking; cooperative tracking; pose and size estimation; laser scanner; mobile robot; sensor node

Abstract:
This paper presents laser-based tracking (estimation of pose and size) of moving objects using multiple mobile robots as sensor nodes. Each sensor node is equipped with a single-layer laser scanner and detects moving objects, such as people, cars, and bicycles, in its own laser-scanned images by applying an occupancy-grid-based method. Each sensor node then estimates the objects’ poses (positions and velocities) and sizes using Bayesian filtering and sends these estimates to a central server. The central server combines the estimates to improve the tracking accuracy and then feeds the information back to the sensor nodes. In this cooperative-tracking method, the sensor nodes share their tracking information, allowing tracking of invisible or partially visible objects. The hierarchical architecture of cooperative tracking also makes the system scalable and robust. Experimental results using two sensor nodes confirm the performance of our tracking method.

Pages: 13 to 19

Copyright: Copyright (c) IARIA, 2016

Publication date: November 13, 2016

Published in: conference

ISSN: 2308-4065

ISBN: 978-1-61208-518-0

Location: Barcelona, Spain

Dates: from November 13, 2016 to November 17, 2016