Multi-camera human activity monitoring

Loren Fiore, Duc Fehr, Robot Bodor, Andrew Drenner, Guruprasad Somasundaram, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

60 Citations (Scopus)

Abstract

With the proliferation of security cameras, the approach taken to monitoring and placement of these cameras is critical. This paper presents original work in the area of multiple camera human activity monitoring. First, a system is presented that tracks pedestrians across a scene of interest and recognizes a set of human activities. Next, a framework is developed for the placement of multiple cameras to observe a scene. This framework was originally used in a limited X, Y, pan formulation but is extended to include height (Z) and tilt. Finally, an active dual-camera system for task recognition at multiple resolutions is developed and tested. All of these systems are tested under real-world conditions, and are shown to produce usable results.

Original languageEnglish (US)
Pages (from-to)5-43
Number of pages39
JournalJournal of Intelligent and Robotic Systems: Theory and Applications
Volume52
Issue number1
DOIs
StatePublished - May 1 2008

Fingerprint

Cameras
Monitoring

Keywords

  • Camera placement
  • Human activity recognition
  • Pedestrian tracking
  • Surveillance

Cite this

Multi-camera human activity monitoring. / Fiore, Loren; Fehr, Duc; Bodor, Robot; Drenner, Andrew; Somasundaram, Guruprasad; Papanikolopoulos, Nikolaos P.

In: Journal of Intelligent and Robotic Systems: Theory and Applications, Vol. 52, No. 1, 01.05.2008, p. 5-43.

Research output: Contribution to journalArticle

Fiore, Loren ; Fehr, Duc ; Bodor, Robot ; Drenner, Andrew ; Somasundaram, Guruprasad ; Papanikolopoulos, Nikolaos P. / Multi-camera human activity monitoring. In: Journal of Intelligent and Robotic Systems: Theory and Applications. 2008 ; Vol. 52, No. 1. pp. 5-43.
@article{027eab0cc09348a8a72a23b6ade3159c,
title = "Multi-camera human activity monitoring",
abstract = "With the proliferation of security cameras, the approach taken to monitoring and placement of these cameras is critical. This paper presents original work in the area of multiple camera human activity monitoring. First, a system is presented that tracks pedestrians across a scene of interest and recognizes a set of human activities. Next, a framework is developed for the placement of multiple cameras to observe a scene. This framework was originally used in a limited X, Y, pan formulation but is extended to include height (Z) and tilt. Finally, an active dual-camera system for task recognition at multiple resolutions is developed and tested. All of these systems are tested under real-world conditions, and are shown to produce usable results.",
keywords = "Camera placement, Human activity recognition, Pedestrian tracking, Surveillance",
author = "Loren Fiore and Duc Fehr and Robot Bodor and Andrew Drenner and Guruprasad Somasundaram and Papanikolopoulos, {Nikolaos P}",
year = "2008",
month = "5",
day = "1",
doi = "10.1007/s10846-007-9201-6",
language = "English (US)",
volume = "52",
pages = "5--43",
journal = "Journal of Intelligent and Robotic Systems: Theory and Applications",
issn = "0921-0296",
publisher = "Springer Netherlands",
number = "1",

}

TY - JOUR

T1 - Multi-camera human activity monitoring

AU - Fiore, Loren

AU - Fehr, Duc

AU - Bodor, Robot

AU - Drenner, Andrew

AU - Somasundaram, Guruprasad

AU - Papanikolopoulos, Nikolaos P

PY - 2008/5/1

Y1 - 2008/5/1

N2 - With the proliferation of security cameras, the approach taken to monitoring and placement of these cameras is critical. This paper presents original work in the area of multiple camera human activity monitoring. First, a system is presented that tracks pedestrians across a scene of interest and recognizes a set of human activities. Next, a framework is developed for the placement of multiple cameras to observe a scene. This framework was originally used in a limited X, Y, pan formulation but is extended to include height (Z) and tilt. Finally, an active dual-camera system for task recognition at multiple resolutions is developed and tested. All of these systems are tested under real-world conditions, and are shown to produce usable results.

AB - With the proliferation of security cameras, the approach taken to monitoring and placement of these cameras is critical. This paper presents original work in the area of multiple camera human activity monitoring. First, a system is presented that tracks pedestrians across a scene of interest and recognizes a set of human activities. Next, a framework is developed for the placement of multiple cameras to observe a scene. This framework was originally used in a limited X, Y, pan formulation but is extended to include height (Z) and tilt. Finally, an active dual-camera system for task recognition at multiple resolutions is developed and tested. All of these systems are tested under real-world conditions, and are shown to produce usable results.

KW - Camera placement

KW - Human activity recognition

KW - Pedestrian tracking

KW - Surveillance

UR - http://www.scopus.com/inward/record.url?scp=42649121003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=42649121003&partnerID=8YFLogxK

U2 - 10.1007/s10846-007-9201-6

DO - 10.1007/s10846-007-9201-6

M3 - Article

VL - 52

SP - 5

EP - 43

JO - Journal of Intelligent and Robotic Systems: Theory and Applications

JF - Journal of Intelligent and Robotic Systems: Theory and Applications

SN - 0921-0296

IS - 1

ER -