DocumentCode :
2930128
Title :
Human activity recognition based on the blob features
Author :
Yang, Jie ; Cheng, Jian ; Lu, Hanqing
Author_Institution :
Nat. Lab. of Pattern Recognition, Chinese Acad. of Sci., Beijing, China
fYear :
2009
fDate :
June 28 2009-July 3 2009
Firstpage :
358
Lastpage :
361
Abstract :
In this paper, we present a novel approach for human activities recognition in the video. We analyze human activities in the sequential frames because human activities can be considered as a temporal object which contains a series of frames. Firstly, we establish a statistical background model and extract foreground object through background subtraction in the video stream. Then, we use foreground blobs of the current frame and a series of frames before the current frame to form a new feature image in certain rules. Finally, we combine the non-zero pixels in the feature image into blobs using the connected component method. Then each blob corresponds to an activity which is characterized by the blob appearance. By recognizing blob features we can recognize activities. We use Gaussian mixture to model features for each type of human activities and employ Mahalanobis distance to measure the similarity.
Keywords :
Gaussian processes; feature extraction; image recognition; image resolution; image sequences; video streaming; Gaussian mixture; Mahalanobis distance; blob features; foreground object extraction; human activity recognition; sequential frames; statistical background model; temporal object; video stream; Feature extraction; Hidden Markov models; Humans; Image analysis; Pattern recognition; Pixel; Stochastic processes; Streaming media; Testing; Video sequences; Activity recognition; video analysis;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on
Conference_Location :
New York, NY
ISSN :
1945-7871
Print_ISBN :
978-1-4244-4290-4
Electronic_ISBN :
1945-7871
Type :
conf
DOI :
10.1109/ICME.2009.5202508
Filename :
5202508
Link To Document :
بازگشت