DocumentCode :
2951446
Title :
Semi-automatic Recognition of Human Activities under Variable Lighting
Author :
Ruiz, Jaime R. ; Altamirano, Leopoldo ; Morales, Eduardo F. ; León, Adrián ; Gonzalez, Jose A.
Author_Institution :
Dept. of Comput. Sci., Nat. Inst. of Astrophys., Opt., & Electron., Puebla, Mexico
fYear :
2011
fDate :
15-18 Nov. 2011
Firstpage :
108
Lastpage :
113
Abstract :
A novel method is proposed for activity recognition on different lighting conditions. It takes the advantage of Harris and Harris Laplace operators of capturing information in spite of extreme changing lighting conditions. They locate corners along the human body with the assistance of a human operator. Corners are followed through the images to generate a set of trajectories that represent the behavior of the human body. The method shows its effectiveness recognizing behaviors by a comparison procedure based on dynamic time warping. We present examples of recognized activities under changing lighting.
Keywords :
Laplace equations; behavioural sciences computing; gesture recognition; Harris Laplace operator; activity recognition; behavior recognition; dynamic time warping; human activities; human operator; lighting condition; semiautomatic recognition; variable lighting; Feature extraction; Humans; Lighting; Prediction algorithms; Spline; Three dimensional displays; Trajectory; Behavioral analysis; local features; recognition of activities; trajectories; variable lighting;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Electronics, Robotics and Automotive Mechanics Conference (CERMA), 2011 IEEE
Conference_Location :
Cuernavaca, Morelos
Print_ISBN :
978-1-4577-1879-3
Type :
conf
DOI :
10.1109/CERMA.2011.25
Filename :
6125814
Link To Document :
بازگشت