Real-time human posture estimation using monocular thermal images

被引：12

作者：

Iwasawa, S ^{[1
]}

Ebihara, K ^{[1
]}

Ohya, J ^{[1
]}

Morishima, S ^{[1
]}

机构：

[1] ATR, Media Integrat & Commun Res Labs, Kyoto 61902, Japan

来源：

AUTOMATIC FACE AND GESTURE RECOGNITION - THIRD IEEE INTERNATIONAL CONFERENCE PROCEEDINGS | 1998年

关键词：

D O I：

10.1109/AFGR.1998.670996

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper introduces a new real-lime 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 zipper half of the body is obtained by calculating the moment of inertia, significant points such as the top of the head, the tips oft he 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.

引用

页码：492 / 497

页数：2