Title :
The extraction and effective identification of human motion characteristics for video images
Author :
Li, Dianmei ; Zhao, Hui ; Chang, Shuhui
Author_Institution :
Coll. of Inf. Sci. & Eng., Shandong Univ., Jinan, China
Abstract :
The identification of the body motion for video images with computer visual technology is analyzing and dealing with the video or sequence of images. It can detect the human motion target, extract the motion characteristics in order to understanding the movement and identifying the person. This paper has introduced a new algorithm for the extraction and effective identification of human motion characteristics for video images. The method fuses seven Hu moment invariants of the human body contour and the feature of limbs angles for motion information. Different features have different weights. Finally a nearest neighbor fuzzy classifier is used to classify subjects. This method can effectively solve the problem of a number of data and complex calculations. Experimental results show that the proposed algorithm has effective recognition performance.
Keywords :
artificial limbs; computer vision; feature extraction; gait analysis; image classification; image sequences; motion estimation; object detection; video signal processing; body motion identification; computer visual technology; feature extraction; human body contour; image sequence; limbs angles; nearest neighbor fuzzy classifier; target detection; video images; Computers; Educational institutions; Humans; Information science; Information theory; Pattern recognition; Target recognition; Hu moment invariants; feature fusion; human motion characteristic; joint angles of limbs; the nearest neighbor fuzzy classifier;
Conference_Titel :
Computer Science and Service System (CSSS), 2011 International Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-9762-1
DOI :
10.1109/CSSS.2011.5974745
