Real-time human posture estimation using monocular thermal images

Shoichiro Iwasawa, Kazuyuki Ebihara, Jun Ohya, Shigeo Morishima

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

19 Citations (Scopus)

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 background 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 knee 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.

Original languageEnglish
Title of host publicationProceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
PublisherIEEE Computer Society
Pages492-497
Number of pages6
ISBN (Print)0818683449, 9780818683442
DOIs
Publication statusPublished - 1998
Externally publishedYes
Event3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 - Nara
Duration: 1998 Apr 141998 Apr 16

Other

Other3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998
CityNara
Period98/4/1498/4/16

Fingerprint

Gravitation
Lighting
Genetic algorithms
Cameras
Infrared radiation
Hot Temperature

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Iwasawa, S., Ebihara, K., Ohya, J., & Morishima, S. (1998). Real-time human posture estimation using monocular thermal images. In Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998 (pp. 492-497). [670996] IEEE Computer Society. https://doi.org/10.1109/AFGR.1998.670996

Real-time human posture estimation using monocular thermal images. / Iwasawa, Shoichiro; Ebihara, Kazuyuki; Ohya, Jun; Morishima, Shigeo.

Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. p. 492-497 670996.

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

Iwasawa, S, Ebihara, K, Ohya, J & Morishima, S 1998, Real-time human posture estimation using monocular thermal images. in Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998., 670996, IEEE Computer Society, pp. 492-497, 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998, Nara, 98/4/14. https://doi.org/10.1109/AFGR.1998.670996
Iwasawa S, Ebihara K, Ohya J, Morishima S. Real-time human posture estimation using monocular thermal images. In Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society. 1998. p. 492-497. 670996 https://doi.org/10.1109/AFGR.1998.670996
Iwasawa, Shoichiro ; Ebihara, Kazuyuki ; Ohya, Jun ; Morishima, Shigeo. / Real-time human posture estimation using monocular thermal images. Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998. IEEE Computer Society, 1998. pp. 492-497
@inproceedings{a8469751997e47baaa1c34c10ff390c7,
title = "Real-time human posture estimation using monocular thermal images",
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 background 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 knee 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.",
author = "Shoichiro Iwasawa and Kazuyuki Ebihara and Jun Ohya and Shigeo Morishima",
year = "1998",
doi = "10.1109/AFGR.1998.670996",
language = "English",
isbn = "0818683449",
pages = "492--497",
booktitle = "Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998",
publisher = "IEEE Computer Society",

}

TY - GEN

T1 - Real-time human posture estimation using monocular thermal images

AU - Iwasawa, Shoichiro

AU - Ebihara, Kazuyuki

AU - Ohya, Jun

AU - Morishima, Shigeo

PY - 1998

Y1 - 1998

N2 - 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 background 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 knee 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.

AB - 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 background 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 knee 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.

UR - http://www.scopus.com/inward/record.url?scp=84905401589&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905401589&partnerID=8YFLogxK

U2 - 10.1109/AFGR.1998.670996

DO - 10.1109/AFGR.1998.670996

M3 - Conference contribution

AN - SCOPUS:84905401589

SN - 0818683449

SN - 9780818683442

SP - 492

EP - 497

BT - Proceedings - 3rd IEEE International Conference on Automatic Face and Gesture Recognition, FG 1998

PB - IEEE Computer Society

ER -