Title :
Video data mining based on K-Means algorithm for surveillance video
Author :
Wang, Jinghua ; Zhang, Guoyan
Author_Institution :
Comput. Sci. & Technol. Dept., Hua Zhong Normal Univ., Wu Han, China
Abstract :
In this paper, we propose a new data mining algorithm, which is used in surveillance video of stationary places. The algorithm combines Background Subtraction with Symmetrical Differencing in order to extract moving targets. According to the amount of motions occurring in video frames, we divide the video into different segments. Video segments are clustered via the improved K-Means algorithm. Then we find the abnormal events, congestions and similar situation retrieval effectively in this way. To a certain extent, intelligent surveillance is implemented well.
Keywords :
data mining; feature extraction; pattern clustering; video surveillance; background subtraction; intelligent surveillance; k-means algorithm; moving target extraction; surveillance video; symmetrical differencing; video data mining; video frames; video segments; Classification algorithms; Clustering algorithms; Data mining; Motion segmentation; Silicon; Streaming media; Surveillance; K-means; surveillance video mining; video mining;
Conference_Titel :
Image Analysis and Signal Processing (IASP), 2011 International Conference on
Conference_Location :
Hubei
Print_ISBN :
978-1-61284-879-2
DOI :
10.1109/IASP.2011.6109120
