Mobile camera positioning to optimize the observability of human activity recognition tasks

Robert Bodor, Andrew Drenner, Michael Janssen, Paul Schrater, Nikolaos Papanikolopoulos

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

The performance of systems for human activity recognition depends heavily on the placement of cameras observing the scene. This work addresses the question of the optimal placement of cameras to maximize the performance of these types of recognition tasks. Specifically, our goal is to optimize the quality of the joint observability of the tasks being performed by the subjects in an area. We develop a general analytical formulation of the observation problem, in terms of the statistics of the motion in the scene and the total resolution of the observed actions, that is applicable to many observation tasks and multi-camera systems. A nonlinear optimization approach is used to find the internal and external (mounting position and orientation) camera parameters that optimize the recognition criteria. In these experiments, a single camera is repositioned using a mobile robot. Initial results for the problem of human activity recognition are presented.

Original languageEnglish (US)
Title of host publication2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS
Pages4037-4042
Number of pages6
DOIs
StatePublished - Dec 1 2005
EventIEEE IRS/RSJ International Conference on Intelligent Robots and Systems, IROS 2005 - Edmonton, AB, Canada
Duration: Aug 2 2005Aug 6 2005

Other

OtherIEEE IRS/RSJ International Conference on Intelligent Robots and Systems, IROS 2005
CountryCanada
CityEdmonton, AB
Period8/2/058/6/05

Fingerprint

Observability
Cameras
Mountings
Mobile robots
Statistics
Experiments

Keywords

  • Human activity monitoring
  • Observability
  • Patrol robotics
  • Tracking

Cite this

Bodor, R., Drenner, A., Janssen, M., Schrater, P., & Papanikolopoulos, N. (2005). Mobile camera positioning to optimize the observability of human activity recognition tasks. In 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS (pp. 4037-4042). [1545599] https://doi.org/10.1109/IROS.2005.1545599

Mobile camera positioning to optimize the observability of human activity recognition tasks. / Bodor, Robert; Drenner, Andrew; Janssen, Michael; Schrater, Paul; Papanikolopoulos, Nikolaos.

2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2005. p. 4037-4042 1545599.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Bodor, R, Drenner, A, Janssen, M, Schrater, P & Papanikolopoulos, N 2005, Mobile camera positioning to optimize the observability of human activity recognition tasks. in 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS., 1545599, pp. 4037-4042, IEEE IRS/RSJ International Conference on Intelligent Robots and Systems, IROS 2005, Edmonton, AB, Canada, 8/2/05. https://doi.org/10.1109/IROS.2005.1545599
Bodor R, Drenner A, Janssen M, Schrater P, Papanikolopoulos N. Mobile camera positioning to optimize the observability of human activity recognition tasks. In 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2005. p. 4037-4042. 1545599 https://doi.org/10.1109/IROS.2005.1545599
Bodor, Robert ; Drenner, Andrew ; Janssen, Michael ; Schrater, Paul ; Papanikolopoulos, Nikolaos. / Mobile camera positioning to optimize the observability of human activity recognition tasks. 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS. 2005. pp. 4037-4042
@inproceedings{4dc3bb3f91d14ded8ccab9a46bfa6ede,
title = "Mobile camera positioning to optimize the observability of human activity recognition tasks",
abstract = "The performance of systems for human activity recognition depends heavily on the placement of cameras observing the scene. This work addresses the question of the optimal placement of cameras to maximize the performance of these types of recognition tasks. Specifically, our goal is to optimize the quality of the joint observability of the tasks being performed by the subjects in an area. We develop a general analytical formulation of the observation problem, in terms of the statistics of the motion in the scene and the total resolution of the observed actions, that is applicable to many observation tasks and multi-camera systems. A nonlinear optimization approach is used to find the internal and external (mounting position and orientation) camera parameters that optimize the recognition criteria. In these experiments, a single camera is repositioned using a mobile robot. Initial results for the problem of human activity recognition are presented.",
keywords = "Human activity monitoring, Observability, Patrol robotics, Tracking",
author = "Robert Bodor and Andrew Drenner and Michael Janssen and Paul Schrater and Nikolaos Papanikolopoulos",
year = "2005",
month = "12",
day = "1",
doi = "10.1109/IROS.2005.1545599",
language = "English (US)",
isbn = "0780389123",
pages = "4037--4042",
booktitle = "2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS",

}

TY - GEN

T1 - Mobile camera positioning to optimize the observability of human activity recognition tasks

AU - Bodor, Robert

AU - Drenner, Andrew

AU - Janssen, Michael

AU - Schrater, Paul

AU - Papanikolopoulos, Nikolaos

PY - 2005/12/1

Y1 - 2005/12/1

N2 - The performance of systems for human activity recognition depends heavily on the placement of cameras observing the scene. This work addresses the question of the optimal placement of cameras to maximize the performance of these types of recognition tasks. Specifically, our goal is to optimize the quality of the joint observability of the tasks being performed by the subjects in an area. We develop a general analytical formulation of the observation problem, in terms of the statistics of the motion in the scene and the total resolution of the observed actions, that is applicable to many observation tasks and multi-camera systems. A nonlinear optimization approach is used to find the internal and external (mounting position and orientation) camera parameters that optimize the recognition criteria. In these experiments, a single camera is repositioned using a mobile robot. Initial results for the problem of human activity recognition are presented.

AB - The performance of systems for human activity recognition depends heavily on the placement of cameras observing the scene. This work addresses the question of the optimal placement of cameras to maximize the performance of these types of recognition tasks. Specifically, our goal is to optimize the quality of the joint observability of the tasks being performed by the subjects in an area. We develop a general analytical formulation of the observation problem, in terms of the statistics of the motion in the scene and the total resolution of the observed actions, that is applicable to many observation tasks and multi-camera systems. A nonlinear optimization approach is used to find the internal and external (mounting position and orientation) camera parameters that optimize the recognition criteria. In these experiments, a single camera is repositioned using a mobile robot. Initial results for the problem of human activity recognition are presented.

KW - Human activity monitoring

KW - Observability

KW - Patrol robotics

KW - Tracking

UR - http://www.scopus.com/inward/record.url?scp=79957977723&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79957977723&partnerID=8YFLogxK

U2 - 10.1109/IROS.2005.1545599

DO - 10.1109/IROS.2005.1545599

M3 - Conference contribution

SN - 0780389123

SN - 9780780389120

SP - 4037

EP - 4042

BT - 2005 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS

ER -