A Model of Saliency-Based Visual Attention for Rapid Scene Analysis
IEEE Transactions on Pattern Analysis and Machine Intelligence
Rapid serial visual presentation: a space-time trade-off in information presentation
AVI '00 Proceedings of the working conference on Advanced visual interfaces
Content-Based Image Retrieval at the End of the Early Years
IEEE Transactions on Pattern Analysis and Machine Intelligence
Rapid, serial and visual: a presentation technique with potential
Information Visualization
Dynamic key frame presentation techniques for augmenting video browsing
AVI '98 Proceedings of the working conference on Advanced visual interfaces
Rapid scene analysis on compressed video
IEEE Transactions on Circuits and Systems for Video Technology
Hi-index | 0.00 |
In order to represent large video collections in the form of key-frame summary on small screen devices, this paper exploits methodology of the visual attention modelling and rapid serial visual presentation. This approach results in an intuitive layout of efficiently generated video summaries. A robust real-time algorithm for key-frame extraction is presented. The system ranks importance of key-frame regions in the final layout by exploiting visual attention modelling. A final layout is created using an optimisation algorithm based on dynamic programming. Algorithm efficiency and robustness are demonstrated by comparing the results with the manually labelled ground truth.