Title :
Action Recognition Using HOG Feature in Different Resolution Video Sequences
Author :
Huang, Yuanyuan ; Yang, Haomiao ; Huang, Ping
Author_Institution :
Sch. of Comput. Sci. & Eng., Univ. of Electron. Sci. & Technol. of China, Chengdu, China
Abstract :
This paper summarizes the recent development of action recognition at first. Then based on Hierarchical Filtered Motion model and Nearest Neighbor classifier, we do action recognition using HOG feature in video sequences of different resolutions. Here we use KTH dataset for training and MSR action dataset II for testing. The experiment demonstrates that the new feature extraction process is effective and has better performance in the cross-dataset action recognition.
Keywords :
feature extraction; image recognition; image resolution; image sequences; video databases; video signal processing; HOG feature; KTH dataset; MSR action dataset II; cross-dataset action recognition; feature extraction process; hierarchical filtered motion model; nearest neighbor classifier; resolution video sequences; Computer vision; Feature extraction; History; Humans; Spatial resolution; Testing; Video sequences; HOG; Motion History Image; action recognition;
Conference_Titel :
Computer Distributed Control and Intelligent Environmental Monitoring (CDCIEM), 2012 International Conference on
Conference_Location :
Hunan
Print_ISBN :
978-1-4673-0458-0
DOI :
10.1109/CDCIEM.2012.27
