Title :
HMM based classification of sports videos using color feature
Author :
Hanna, Josh ; Patlar, Fatma ; Akbulut, Akhan ; Mendi, Engin ; Bayrak, Coskun
Author_Institution :
Comput. Sci. Dept., Univ. of Arkansas at Little Rock, Little Rock, AR, USA
Abstract :
Video content classification is an important element for efficient access and retrieval of video in any media content management system. Categorizing the video segments can help to provide convenience and ease in accessing the relevant video content without sequential scanning. In this paper, we present a Hidden Markov Model (HMM) based classification technique for sports videos. Speed of color changes is computed for each video frame and used as observation sequences in HMM for classification. Experiments using more than 1 hour of 18 training and 18 testing sports videos of 3 predefined genres (golf, hockey and football) give very satisfactory classification accuracy.
Keywords :
content-based retrieval; hidden Markov models; image classification; image colour analysis; image sequences; sport; video retrieval; video signal processing; HMM based classification technique; classification accuracy; color change speed; color feature; football; golf; hidden Markov model; hockey; media content management system; observation sequence; sequential scanning; sports video; video content access; video content classification; video frame; video retrieval; video segment categorization; Feature extraction; Hidden Markov models; Image color analysis; Multimedia communication; Streaming media; Training; Videos;
Conference_Titel :
Intelligent Systems (IS), 2012 6th IEEE International Conference
Conference_Location :
Sofia
Print_ISBN :
978-1-4673-2276-8
DOI :
10.1109/IS.2012.6335247
