Abstract
This paper proposes a new real-time method for estimating human body postures 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, in order to calculate 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 and the ends of the hands and feet 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 performance (faster than 20 frames per second).
Original language | English |
---|---|
Pages (from-to) | 1270-1277 |
Number of pages | 8 |
Journal | Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers |
Volume | 51 |
Issue number | 8 |
Publication status | Published - 1997 |
Externally published | Yes |
Fingerprint
ASJC Scopus subject areas
- Computer Vision and Pattern Recognition
- Electronic, Optical and Magnetic Materials
Cite this
Real-time estimation of human body postures from monocular thermal images. / Iwasawa, Shoichiro; Ebihara, Kazuyuki; Ohya, Jun; Nakatsu, Ryohei; Morishima, Shigeo.
In: Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers, Vol. 51, No. 8, 1997, p. 1270-1277.Research output: Contribution to journal › Article
}
TY - JOUR
T1 - Real-time estimation of human body postures from monocular thermal images
AU - Iwasawa, Shoichiro
AU - Ebihara, Kazuyuki
AU - Ohya, Jun
AU - Nakatsu, Ryohei
AU - Morishima, Shigeo
PY - 1997
Y1 - 1997
N2 - This paper proposes a new real-time method for estimating human body postures 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, in order to calculate 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 and the ends of the hands and feet 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 performance (faster than 20 frames per second).
AB - This paper proposes a new real-time method for estimating human body postures 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, in order to calculate 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 and the ends of the hands and feet 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 performance (faster than 20 frames per second).
UR - http://www.scopus.com/inward/record.url?scp=0031195973&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=0031195973&partnerID=8YFLogxK
M3 - Article
AN - SCOPUS:0031195973
VL - 51
SP - 1270
EP - 1277
JO - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers
JF - Kyokai Joho Imeji Zasshi/Journal of the Institute of Image Information and Television Engineers
SN - 1342-6907
IS - 8
ER -