Deriving occlusions in static scenes from observations of interactions with a moving figure

Bennett Jackson, Robert Bodor, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

Abstract

Many applications in computer vision are based on a single static camera observing a scene which is static except for one or more figures (people, vehicles, etc.) moving through it. In these applications it is useful to understand whether the moving figure is partially occluded by some static element of the scene. Such partial occlusions, when undetected, confuse the analysis of the figure's pose and activity. We present an algorithm that uses only the information provided by moving figures to simply and efficiently derive the position of static occluding bodies. Once these occlusions are obtained, we demonstrate successful reasoning about the occlusion status of future figures within the same scene. The occlusion positions from multiple views of the same scene are used to extract an estimate of the three-dimensional position and shape of the occlusion. Experimental results validating the method are included.

Original languageEnglish (US)
Pages (from-to)1043-1058
Number of pages16
JournalAdvanced Robotics
Volume19
Issue number10 SPEC. ISS.
DOIs
StatePublished - Dec 19 2005

Fingerprint

Computer vision
Cameras

Keywords

  • Computer vision
  • Human activity monitoring
  • Occlusion
  • Structure from motion
  • Surveillance

Cite this

Deriving occlusions in static scenes from observations of interactions with a moving figure. / Jackson, Bennett; Bodor, Robert; Papanikolopoulos, Nikolaos P.

In: Advanced Robotics, Vol. 19, No. 10 SPEC. ISS., 19.12.2005, p. 1043-1058.

Research output: Contribution to journalArticle

@article{8fbfc81cb7b24439bbd16719047edadb,
title = "Deriving occlusions in static scenes from observations of interactions with a moving figure",
abstract = "Many applications in computer vision are based on a single static camera observing a scene which is static except for one or more figures (people, vehicles, etc.) moving through it. In these applications it is useful to understand whether the moving figure is partially occluded by some static element of the scene. Such partial occlusions, when undetected, confuse the analysis of the figure's pose and activity. We present an algorithm that uses only the information provided by moving figures to simply and efficiently derive the position of static occluding bodies. Once these occlusions are obtained, we demonstrate successful reasoning about the occlusion status of future figures within the same scene. The occlusion positions from multiple views of the same scene are used to extract an estimate of the three-dimensional position and shape of the occlusion. Experimental results validating the method are included.",
keywords = "Computer vision, Human activity monitoring, Occlusion, Structure from motion, Surveillance",
author = "Bennett Jackson and Robert Bodor and Papanikolopoulos, {Nikolaos P}",
year = "2005",
month = "12",
day = "19",
doi = "10.1163/156855305774662190",
language = "English (US)",
volume = "19",
pages = "1043--1058",
journal = "Advanced Robotics",
issn = "0169-1864",
publisher = "Taylor and Francis Ltd.",
number = "10 SPEC. ISS.",

}

TY - JOUR

T1 - Deriving occlusions in static scenes from observations of interactions with a moving figure

AU - Jackson, Bennett

AU - Bodor, Robert

AU - Papanikolopoulos, Nikolaos P

PY - 2005/12/19

Y1 - 2005/12/19

N2 - Many applications in computer vision are based on a single static camera observing a scene which is static except for one or more figures (people, vehicles, etc.) moving through it. In these applications it is useful to understand whether the moving figure is partially occluded by some static element of the scene. Such partial occlusions, when undetected, confuse the analysis of the figure's pose and activity. We present an algorithm that uses only the information provided by moving figures to simply and efficiently derive the position of static occluding bodies. Once these occlusions are obtained, we demonstrate successful reasoning about the occlusion status of future figures within the same scene. The occlusion positions from multiple views of the same scene are used to extract an estimate of the three-dimensional position and shape of the occlusion. Experimental results validating the method are included.

AB - Many applications in computer vision are based on a single static camera observing a scene which is static except for one or more figures (people, vehicles, etc.) moving through it. In these applications it is useful to understand whether the moving figure is partially occluded by some static element of the scene. Such partial occlusions, when undetected, confuse the analysis of the figure's pose and activity. We present an algorithm that uses only the information provided by moving figures to simply and efficiently derive the position of static occluding bodies. Once these occlusions are obtained, we demonstrate successful reasoning about the occlusion status of future figures within the same scene. The occlusion positions from multiple views of the same scene are used to extract an estimate of the three-dimensional position and shape of the occlusion. Experimental results validating the method are included.

KW - Computer vision

KW - Human activity monitoring

KW - Occlusion

KW - Structure from motion

KW - Surveillance

UR - http://www.scopus.com/inward/record.url?scp=28844506764&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=28844506764&partnerID=8YFLogxK

U2 - 10.1163/156855305774662190

DO - 10.1163/156855305774662190

M3 - Article

VL - 19

SP - 1043

EP - 1058

JO - Advanced Robotics

JF - Advanced Robotics

SN - 0169-1864

IS - 10 SPEC. ISS.

ER -