Optimal camera placement for automated surveillance Tasks

Robert Bodor, Andrew Drenner, Paul R Schrater, Nikolaos P Papanikolopoulos

Research output: Contribution to journalArticle

54 Citations (Scopus)

Abstract

Camera placement has an enormous impact on the performance of vision systems, but the best placement to maximize performance depends on the purpose of the system. As a result, this paper focuses largely on the problem of task-specific camera placement. We propose a new camera placement method that optimizes views to provide the highest resolution images of objects and motions in the scene that are critical for the performance of some specified task (e.g. motion recognition, visual metrology, part identification, etc.). A general analytical formulation of the observation problem is developed in terms of motion statistics of a scene and resolution of observed actions resulting in an aggregate observability measure. The goal of this system is to optimize across multiple cameras the aggregate observability of the set of actions performed in a defined area. The method considers dynamic and unpredictable environments, where the subject of interest changes in time. It does not attempt to measure or reconstruct surfaces or objects, and does not use an internal model of the subjects for reference. As a result, this method differs significantly in its core formulation from camera placement solutions applied to problems such as inspection, reconstruction or the Art Gallery class of problems. We present tests of the system's optimized camera placement solutions using real-world data in both indoor and outdoor situations and robot-based experimentation using an all terrain robot vehicle-Jr robot in an indoor setting.

Original languageEnglish (US)
Pages (from-to)257-295
Number of pages39
JournalJournal of Intelligent and Robotic Systems: Theory and Applications
Volume50
Issue number3
DOIs
StatePublished - Nov 1 2007

Fingerprint

Cameras
Observability
Robots
Image resolution
Inspection
Statistics

Keywords

  • Camera networks
  • Observability
  • Optimization
  • Robot/camera placement
  • Sensor networks
  • Vision-based robotics

Cite this

Optimal camera placement for automated surveillance Tasks. / Bodor, Robert; Drenner, Andrew; Schrater, Paul R; Papanikolopoulos, Nikolaos P.

In: Journal of Intelligent and Robotic Systems: Theory and Applications, Vol. 50, No. 3, 01.11.2007, p. 257-295.

Research output: Contribution to journalArticle

@article{9614509639ca4375be6f7c0e9cb72f43,
title = "Optimal camera placement for automated surveillance Tasks",
abstract = "Camera placement has an enormous impact on the performance of vision systems, but the best placement to maximize performance depends on the purpose of the system. As a result, this paper focuses largely on the problem of task-specific camera placement. We propose a new camera placement method that optimizes views to provide the highest resolution images of objects and motions in the scene that are critical for the performance of some specified task (e.g. motion recognition, visual metrology, part identification, etc.). A general analytical formulation of the observation problem is developed in terms of motion statistics of a scene and resolution of observed actions resulting in an aggregate observability measure. The goal of this system is to optimize across multiple cameras the aggregate observability of the set of actions performed in a defined area. The method considers dynamic and unpredictable environments, where the subject of interest changes in time. It does not attempt to measure or reconstruct surfaces or objects, and does not use an internal model of the subjects for reference. As a result, this method differs significantly in its core formulation from camera placement solutions applied to problems such as inspection, reconstruction or the Art Gallery class of problems. We present tests of the system's optimized camera placement solutions using real-world data in both indoor and outdoor situations and robot-based experimentation using an all terrain robot vehicle-Jr robot in an indoor setting.",
keywords = "Camera networks, Observability, Optimization, Robot/camera placement, Sensor networks, Vision-based robotics",
author = "Robert Bodor and Andrew Drenner and Schrater, {Paul R} and Papanikolopoulos, {Nikolaos P}",
year = "2007",
month = "11",
day = "1",
doi = "10.1007/s10846-007-9164-7",
language = "English (US)",
volume = "50",
pages = "257--295",
journal = "Journal of Intelligent and Robotic Systems: Theory and Applications",
issn = "0921-0296",
publisher = "Springer Netherlands",
number = "3",

}

TY - JOUR

T1 - Optimal camera placement for automated surveillance Tasks

AU - Bodor, Robert

AU - Drenner, Andrew

AU - Schrater, Paul R

AU - Papanikolopoulos, Nikolaos P

PY - 2007/11/1

Y1 - 2007/11/1

N2 - Camera placement has an enormous impact on the performance of vision systems, but the best placement to maximize performance depends on the purpose of the system. As a result, this paper focuses largely on the problem of task-specific camera placement. We propose a new camera placement method that optimizes views to provide the highest resolution images of objects and motions in the scene that are critical for the performance of some specified task (e.g. motion recognition, visual metrology, part identification, etc.). A general analytical formulation of the observation problem is developed in terms of motion statistics of a scene and resolution of observed actions resulting in an aggregate observability measure. The goal of this system is to optimize across multiple cameras the aggregate observability of the set of actions performed in a defined area. The method considers dynamic and unpredictable environments, where the subject of interest changes in time. It does not attempt to measure or reconstruct surfaces or objects, and does not use an internal model of the subjects for reference. As a result, this method differs significantly in its core formulation from camera placement solutions applied to problems such as inspection, reconstruction or the Art Gallery class of problems. We present tests of the system's optimized camera placement solutions using real-world data in both indoor and outdoor situations and robot-based experimentation using an all terrain robot vehicle-Jr robot in an indoor setting.

AB - Camera placement has an enormous impact on the performance of vision systems, but the best placement to maximize performance depends on the purpose of the system. As a result, this paper focuses largely on the problem of task-specific camera placement. We propose a new camera placement method that optimizes views to provide the highest resolution images of objects and motions in the scene that are critical for the performance of some specified task (e.g. motion recognition, visual metrology, part identification, etc.). A general analytical formulation of the observation problem is developed in terms of motion statistics of a scene and resolution of observed actions resulting in an aggregate observability measure. The goal of this system is to optimize across multiple cameras the aggregate observability of the set of actions performed in a defined area. The method considers dynamic and unpredictable environments, where the subject of interest changes in time. It does not attempt to measure or reconstruct surfaces or objects, and does not use an internal model of the subjects for reference. As a result, this method differs significantly in its core formulation from camera placement solutions applied to problems such as inspection, reconstruction or the Art Gallery class of problems. We present tests of the system's optimized camera placement solutions using real-world data in both indoor and outdoor situations and robot-based experimentation using an all terrain robot vehicle-Jr robot in an indoor setting.

KW - Camera networks

KW - Observability

KW - Optimization

KW - Robot/camera placement

KW - Sensor networks

KW - Vision-based robotics

UR - http://www.scopus.com/inward/record.url?scp=35348896569&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=35348896569&partnerID=8YFLogxK

U2 - 10.1007/s10846-007-9164-7

DO - 10.1007/s10846-007-9164-7

M3 - Article

VL - 50

SP - 257

EP - 295

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

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

SN - 0921-0296

IS - 3

ER -