Data association and occlusion handling for vision-based people tracking by mobile robots

Grzegorz Cielniak; Tom Duckett; Achim J. Lilienthal

doi:10.1016/j.robot.2010.02.004

Data association and occlusion handling for vision-based people tracking by mobile robots

Grzegorz Cielniak
, Tom Duckett
, Achim J. Lilienthal

Research output: Contribution to journal › Article › peer-review

28 Scopus citations

Abstract

This paper presents an approach for tracking multiple persons on a mobile robot with a combination of colour and thermal vision sensors, using several new techniques. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is incorporated into the tracker. The paper presents a comprehensive, quantitative evaluation of the whole system and its different components using several real world data sets.

Original language	English
Pages (from-to)	435-443
Number of pages	9
Journal	Robotics and Autonomous Systems
Volume	58
Issue number	5
DOIs	https://doi.org/10.1016/j.robot.2010.02.004
State	Published - 31 May 2010
Externally published	Yes

Keywords

AdaBoost
Bayesian estimation
Colour vision
Occlusion detection
Thermal vision

Access to Document

10.1016/j.robot.2010.02.004

Cite this

@article{b59fc882055541c1873f552bfac398cb,

title = "Data association and occlusion handling for vision-based people tracking by mobile robots",

abstract = "This paper presents an approach for tracking multiple persons on a mobile robot with a combination of colour and thermal vision sensors, using several new techniques. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is incorporated into the tracker. The paper presents a comprehensive, quantitative evaluation of the whole system and its different components using several real world data sets.",

keywords = "AdaBoost, Bayesian estimation, Colour vision, Occlusion detection, Thermal vision",

author = "Grzegorz Cielniak and Tom Duckett and Lilienthal, \{Achim J.\}",

year = "2010",

month = may,

day = "31",

doi = "10.1016/j.robot.2010.02.004",

language = "English",

volume = "58",

pages = "435--443",

journal = "Robotics and Autonomous Systems",

issn = "0921-8890",

publisher = "Elsevier B.V.",

number = "5",

}

TY - JOUR

T1 - Data association and occlusion handling for vision-based people tracking by mobile robots

AU - Cielniak, Grzegorz

AU - Duckett, Tom

AU - Lilienthal, Achim J.

PY - 2010/5/31

Y1 - 2010/5/31

N2 - This paper presents an approach for tracking multiple persons on a mobile robot with a combination of colour and thermal vision sensors, using several new techniques. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is incorporated into the tracker. The paper presents a comprehensive, quantitative evaluation of the whole system and its different components using several real world data sets.

AB - This paper presents an approach for tracking multiple persons on a mobile robot with a combination of colour and thermal vision sensors, using several new techniques. First, an adaptive colour model is incorporated into the measurement model of the tracker. Second, a new approach for detecting occlusions is introduced, using a machine learning classifier for pairwise comparison of persons (classifying which one is in front of the other). Third, explicit occlusion handling is incorporated into the tracker. The paper presents a comprehensive, quantitative evaluation of the whole system and its different components using several real world data sets.

KW - AdaBoost

KW - Bayesian estimation

KW - Colour vision

KW - Occlusion detection

KW - Thermal vision

UR - https://www.scopus.com/pages/publications/77950188463

U2 - 10.1016/j.robot.2010.02.004

DO - 10.1016/j.robot.2010.02.004

M3 - Article

AN - SCOPUS:77950188463

SN - 0921-8890

VL - 58

SP - 435

EP - 443

JO - Robotics and Autonomous Systems

JF - Robotics and Autonomous Systems

IS - 5

ER -

Data association and occlusion handling for vision-based people tracking by mobile robots

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this