Multi-part people detection using 2D range data

Martinez Mozos, Oscar and Kurazume, Ryo and Hasegawa, Tsutomu (2010) Multi-part people detection using 2D range data. International Journal of Social Robotics, 2 (1). pp. 31-40. ISSN 1875-4791

Full content URL: http://dx.doi.org/10.1007/s12369-009-0041-3

Documents
mozos2010ijsr.pdf
[img] PDF
mozos2010ijsr.pdf - Whole Document
Restricted to Repository staff only

681kB
Item Type:Article
Item Status:Live Archive

Abstract

People detection is a key capacity for robotics systems that have to interact with humans. This paper addresses the problem of detecting people using multiple layers of 2D laser range scans. Each layer contains a classifier able to detect a particular body part such as a head, an upper body or a leg. These classifiers are learned using a supervised approach based on AdaBoost. The final person detector is composed of a probabilistic combination of the outputs from the different classifiers. Experimental results with real data demonstrate the effectiveness of our approach to detect persons in indoor environments and its ability to deal with occlusions.

Keywords:Laser-based people detection, Multiple cue classification, Sensor fusion, Multi-part object detection
Subjects:G Mathematical and Computer Sciences > G700 Artificial Intelligence
H Engineering > H671 Robotics
G Mathematical and Computer Sciences > G760 Machine Learning
Divisions:College of Science > School of Computer Science
ID Code:9412
Deposited On:12 May 2013 17:18

Repository Staff Only: item control page