Title :
A model of motion attention for video skimming
Author :
Ma, Yu-Fei ; Zhang, Hong-Jiang
Author_Institution :
Microsoft Res. Asia, Beijing, China
Abstract :
One of the key issues in video manipulation is video abstraction in the form of skimmed video. For this purpose, an important task is to determine the content significance of each chunk of frames in a video sequence. In this paper, we present a new computational model of motion attention and the approach to applying this model in video skimming. The effectiveness of our architecture and model is demonstrated by user studies of visual skimming experiments. The results indicate that the precision of motion attention detection is over 80%, and the user satisfaction of visual skimming is beyond 70%.
Keywords :
image motion analysis; image sequences; video signal processing; content significance; motion attention; skimmed video; video abstraction; video manipulation; video sequence; visual skimming; Asia; Cameras; Computational modeling; Computer architecture; Control systems; Image sequence analysis; Machine vision; Motion detection; Power system modeling; Video sequences;
Conference_Titel :
Image Processing. 2002. Proceedings. 2002 International Conference on
Print_ISBN :
0-7803-7622-6
DOI :
10.1109/ICIP.2002.1037976
