Characterizing human subjects in real-time and three-dimensional spaces by integrating thermal-infrared and visible spectrum cameras

Authors:
Suk Kyu Lee;Kenton McHenry;Rob Kooper;Peter Bajcsy
Affiliations:
National Center for Supercomputing Application, University of Illinois at Urbana-Champaign;National Center for Supercomputing Application, University of Illinois at Urbana-Champaign;National Center for Supercomputing Application, University of Illinois at Urbana-Champaign;National Center for Supercomputing Application, University of Illinois at Urbana-Champaign
Venue:
ICME'09 Proceedings of the 2009 IEEE international conference on Multimedia and Expo
Year:
2009

Citing 4
Cited 2

Image difference threshold strategies and shadow detection

BMVC '95 Proceedings of the 1995 British conference on Machine vision (Vol. 1)
Trinocular Stereo: A Real-Time Algorithm and its Evaluation

International Journal of Computer Vision
Understanding performance in coliseum, an immersive videoconferencing system

ACM Transactions on Multimedia Computing, Communications, and Applications (TOMCCAP)
A convenient multicamera self-calibration for virtual environments

Presence: Teleoperators and Virtual Environments

Tele-immersive environments for rehabilitation activities: an empirical study on proprioception

Multidimensional Systems and Signal Processing
Thermal cameras and applications: a survey

Machine Vision and Applications

Quantified Score

Hi-index	0.00

Visualization

Abstract

In human health and performance studies, there is a need to detect, track and describe human subjects in real-time and in three-dimensional (3D) space. The work presented here is motivated by the problem of detecting human subjects in physical spaces, reconstructing their location in 3D, describing their spectral characteristics at each 3D location, and rendering 3D and spectral characteristics in real time. In this paper, we address the problem of integrating thermal infrared (IR) cameras and visible spectral cameras so that the 3D and spectral characteristics can be acquired in real time. We report performance tradeoffs associated with the integration of thermal-infrared and visible spectrum cameras and the discuss implications of our design for human health and performance studies.