TY - JOUR
T1 - Human action segmentation and recognition via motion and shape analysis
AU - Shao, Ling
AU - Ji, Ling
AU - Liu, Yan
AU - Zhang, Jianguo
PY - 2012/3
Y1 - 2012/3
N2 - In this paper, we present an automated video analysis system which addresses segmentation and detection of human actions in an indoor environment, such as a gym. The system aims at segmenting different movements from the input video and recognizing the action types simultaneously. Two action segmentation techniques, namely color intensity based and motion based, are proposed. Both methods can efficiently segment periodic human movements into temporal cycles. We also apply a novel approach for human action recognition by describing human actions using motion and shape features. The descriptor contains both the local shape and its spatial layout information, therefore is more effective for action modeling and is suitable for detecting and recognizing a variety of actions. Experimental results show that the proposed action segmentation and detection algorithms are highly effective.
AB - In this paper, we present an automated video analysis system which addresses segmentation and detection of human actions in an indoor environment, such as a gym. The system aims at segmenting different movements from the input video and recognizing the action types simultaneously. Two action segmentation techniques, namely color intensity based and motion based, are proposed. Both methods can efficiently segment periodic human movements into temporal cycles. We also apply a novel approach for human action recognition by describing human actions using motion and shape features. The descriptor contains both the local shape and its spatial layout information, therefore is more effective for action modeling and is suitable for detecting and recognizing a variety of actions. Experimental results show that the proposed action segmentation and detection algorithms are highly effective.
KW - Human action segmentation
KW - Motion analysis
KW - PCOG
KW - Motion history image
KW - Human action recognition
UR - http://www.sciencedirect.com/science/article/pii/S0167865511001590
U2 - 10.1016/j.patrec.2011.05.015
DO - 10.1016/j.patrec.2011.05.015
M3 - Article
VL - 33
SP - 438
EP - 445
JO - Pattern Recognition Letters
JF - Pattern Recognition Letters
SN - 0167-8655
IS - 4
ER -