Title :
Object based video similarity retrieval and its application to detecting anchorperson shots in news video
Author :
Chen, Hua-Tsung ; Chen, Duan-Yu ; Lee, Suh-Yin
Author_Institution :
Inst. of Comput. Sci. & Inf. Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan
Abstract :
Semantic feature extraction of video shots and fast video sequence matching are important and required for efficient retrieval in a large video database. A novel mechanism of similarity retrieval is proposed. Similarity measure between video sequences considering the spatio-temporal variation through consecutive frames is presented. For bridging the semantic gap between low-level features and the rich meaning that users desire to capture, video shots are analyzed and characterized by the high-level feature of motion activity in compressed domain. The extracted features of motion activity are further described by the 2D-histogram that is sensitive to the spatio-temporal variation of moving objects. In order to reduce the dimensions of feature vector space in sequence matching, the discrete cosine transform (DCT) is exploited to map semantic features of consecutive frames to the frequency domain while retains the discriminatory information and preserves the Euclidean distance between feature vectors. Experiments are performed on MPEG-7 testing video streams, and the results of sequence matching show that a few DCT transformed coefficients are adequate and thus reveal the effectiveness of the proposed mechanism of video retrieval.
Keywords :
discrete cosine transforms; feature extraction; image matching; image retrieval; image sequences; motion estimation; object detection; video databases; video signal processing; Euclidean distance; MPEG-7 testing video streams; anchorperson shot detection; discrete cosine transform; discriminatory information; feature vector space; news video; object based video similarity retrieval; semantic feature extraction; spatio-temporal variation; video sequence matching; video shots; Discrete cosine transforms; Feature extraction; Frequency domain analysis; Gunshot detection systems; Information retrieval; Motion analysis; Object detection; Spatial databases; Video compression; Video sequences;
Conference_Titel :
Multimedia Software Engineering, 2003. Proceedings. Fifth International Symposium on
Conference_Location :
Taichung, Taiwan
Print_ISBN :
0-7695-2031-6
DOI :
10.1109/MMSE.2003.1254439