Novel Mutual Information Analysis of Attentive Motion Entropy Algorithm for Sports Video Summarization
This study presents a novel summarization method, which utilizes attentive motion analysis, mutual information, and segmental spectro-temporal subtraction, for generating sports video abstracts. The proposed attentive motion entropy and mutual information
- PDF / 1,839,054 Bytes
- 12 Pages / 439.37 x 666.142 pts Page_size
- 4 Downloads / 171 Views
Abstract This study presents a novel summarization method, which utilizes attentive motion analysis, mutual information, and segmental spectro-temporal subtraction, for generating sports video abstracts. The proposed attentive motion entropy and mutual information are both based on an attentive model. To capture and detect significant segments among a video, this work uses color contrast, intensity contrast, and orientation contrast of frames to calculate saliency maps. Regional histograms of oriented gradients based on human shapes are also adopted at the preliminary stage. In the next step, a new algorithm based on mutual information is proposed to improve the smoothness problem when the system selects the boundaries of motion segments. Meanwhile, differential salient motions and oriented gradients are merged to mutual information analysis, subsequently generating an attentive curve. Furthermore, to remove non-motion boundaries, a smoothing technique based on segmental spectro-temporal subtraction is also used for selecting favorable event boundaries. The experiment results show that our proposed algorithm can detect highlights effectively and generate smooth playable clips. Compared with existing systems, the precision and recall rates of our system outperform their results by 8.6 and 11.1 %, respectively. Besides, smoothness is enhanced by 0.7 on average, which also verified feasibility of our system.
B.-W. Chen (&) J.-F. Wang Department of Electrical Engineering, National Cheng Kung University, Tainan, Taiwan, Republic of China e-mail: [email protected] K. Bharanitharan Department of Electrical Engineering, Feng Chia University, Taichung, Taiwan, Republic of China J.-C. Wang Department of Computer Science and Information Engineering, National Central University, Jhongli, Taiwan, Republic of China Z. Fu School of Computer Science, Northwestern Polytechnical University, Xi’an, China
Y.-M. Huang et al. (eds.), Advanced Technologies, Embedded and Multimedia 1031 for Human-centric Computing, Lecture Notes in Electrical Engineering 260, DOI: 10.1007/978-94-007-7262-5_117, Ó Springer Science+Business Media Dordrecht 2014
1032
B.-W. Chen et al.
Keywords Video summarization Attentive motion entropy tion analysis Segmental spectro-temporal subtraction
Mutual informa-
Introduction Video summarization techniques have been proposed for years to offer people comprehensive understanding of the whole story in a video. To date, a great deal of effort has been devoted to providing people with more friendly interfaces and better concept interpretation [1–13]. Traditional video summarization approaches can be roughly classified into two categories: One is the static storyboard [1, 10, 13], which is composed of still images extracted from the original video; the other is the dynamic skimming [2–9, 11, 12], which concatenates several shorter clips. Both of them aim to offer users a compact view of a video. This work mainly focuses on the study of dynamic skimming approaches because generating playable clips is s
Data Loading...
