ML Anthology

Real-Time Estimation of Human Body Posture from Monocular Thermal Images

Shoichiro Iwasawa, Kazuyuki Ebihara, Jun Ohya, Shigeo Morishima
CVPR 1997 pp. 15-20
doi:10.1109/CVPR.1997.609290 /cvpr/1997/iwasawa1997cvpr-real/

Abstract

This paper introduces a new real-time method to estimate the posture of a human from thermal images acquired by an infrared camera regardless of the back-ground and lighting conditions. Distance transformation is performed for the human body area extracted from the thresholded thermal image for the. Calculation of the center of gravity. After the orientation of the upper half of the body is obtained by calculating the moment of inertia, significant points such as the top of the head, the tips of the hands and foot are heuristically located. In addition, the elbow and foot positions are estimated from the detected (significant) points using a genetic algorithm based learning procedure. The experimental results demonstrate the robustness of the proposed algorithm and real-time (faster than 20 frames per second) performance.

CVPR Semantic Scholar

Cite

Text

Iwasawa et al. "Real-Time Estimation of Human Body Posture from Monocular Thermal Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609290

Markdown

[Iwasawa et al. "Real-Time Estimation of Human Body Posture from Monocular Thermal Images." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/iwasawa1997cvpr-real/) doi:10.1109/CVPR.1997.609290

BibTeX

@inproceedings{iwasawa1997cvpr-real,
  title     = {{Real-Time Estimation of Human Body Posture from Monocular Thermal Images}},
  author    = {Iwasawa, Shoichiro and Ebihara, Kazuyuki and Ohya, Jun and Morishima, Shigeo},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {15-20},
  doi       = {10.1109/CVPR.1997.609290},
  url       = {https://mlanthology.org/cvpr/1997/iwasawa1997cvpr-real/}
}