Casualty detection for mobile rescue robots via ground-projected point clouds

File Description SizeFormat 
Saputra_TAROS-2018a[1].pdfAccepted version217.76 kBAdobe PDFView/Open
Title: Casualty detection for mobile rescue robots via ground-projected point clouds
Authors: Saputra, RP
Kormushev, P
Item Type: Conference Paper
Abstract: In order to operate autonomously, mobile rescue robots need to be able to detect human casualties in disaster situations. In this paper, we propose a novel method for autonomous detection of casualties lying down on the ground based on point-cloud data. This data can be obtained from different sensors, such as an RGB-D camera or a 3D LIDAR sensor. The method is based on a ground-projected point-cloud (GPPC) image to achieve human body shape detection. A preliminary experiment has been conducted using the RANSAC method for floor detection and, the HOG feature and the SVM classifier to detect human body shape. The results show that the proposed method succeeds to identify a casualty from point-cloud data in a wide range of viewing angles.
Issue Date: 27-Jul-2018
Date of Acceptance: 25-Jul-2018
ISBN: 9783319967271
ISSN: 0302-9743
Publisher: Springer, Cham
Start Page: 473
End Page: 475
Journal / Book Title: Proc. 19th International Conference Towards Autonomous Robotic Systems (TAROS 2018)
Volume: 1
Copyright Statement: © 2018 Springer-Verlag. The final publication is available at Springer via
Conference Name: Towards Autonomous Robotic Systems (TAROS) 2018
Keywords: 08 Information And Computing Sciences
Artificial Intelligence & Image Processing
Publication Status: Published
Start Date: 2018-07-25
Finish Date: 2018-07-27
Conference Place: Bristol, UK
Open Access location:
Appears in Collections:Faculty of Engineering
Dyson School of Design Engineering

Items in Spiral are protected by copyright, with all rights reserved, unless otherwise indicated.

Creative Commons