Multi-part people detection using 2D range data

Oscar Martinez Mozos, Ryo Kurazume, Tsutomu Hasegawa

Research output: Contribution to journalArticle

53 Citations (Scopus)

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 Ada Boost. 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.

Original languageEnglish
Pages (from-to)31-40
Number of pages10
JournalInternational Journal of Social Robotics
Volume2
Issue number1
DOIs
Publication statusPublished - Mar 1 2010

Fingerprint

Classifiers
Robotics
Detectors
Lasers

All Science Journal Classification (ASJC) codes

  • Computer Science(all)

Cite this

Multi-part people detection using 2D range data. / Mozos, Oscar Martinez; Kurazume, Ryo; Hasegawa, Tsutomu.

In: International Journal of Social Robotics, Vol. 2, No. 1, 01.03.2010, p. 31-40.

Research output: Contribution to journalArticle

Mozos, Oscar Martinez ; Kurazume, Ryo ; Hasegawa, Tsutomu. / Multi-part people detection using 2D range data. In: International Journal of Social Robotics. 2010 ; Vol. 2, No. 1. pp. 31-40.
@article{96185fc58658422bb5f3788f83b1eac3,
title = "Multi-part people detection using 2D range data",
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 Ada Boost. 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.",
author = "Mozos, {Oscar Martinez} and Ryo Kurazume and Tsutomu Hasegawa",
year = "2010",
month = "3",
day = "1",
doi = "10.1007/s12369-009-0041-3",
language = "English",
volume = "2",
pages = "31--40",
journal = "International Journal of Social Robotics",
issn = "1875-4791",
publisher = "Springer Verlag",
number = "1",

}

TY - JOUR

T1 - Multi-part people detection using 2D range data

AU - Mozos, Oscar Martinez

AU - Kurazume, Ryo

AU - Hasegawa, Tsutomu

PY - 2010/3/1

Y1 - 2010/3/1

N2 - 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 Ada Boost. 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.

AB - 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 Ada Boost. 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.

UR - http://www.scopus.com/inward/record.url?scp=77958576535&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77958576535&partnerID=8YFLogxK

U2 - 10.1007/s12369-009-0041-3

DO - 10.1007/s12369-009-0041-3

M3 - Article

AN - SCOPUS:77958576535

VL - 2

SP - 31

EP - 40

JO - International Journal of Social Robotics

JF - International Journal of Social Robotics

SN - 1875-4791

IS - 1

ER -