Abstract
Driven by a high demand for user-centred video interfaces and recent advances in scalable video coding technology, this work introduces a novel framework for video browsing by utilising inherently hierarchical compressed-domain features of scalable video and e cient dynamic video summarisation. This approach enables instant adaptability of generated video summaries to user requirements, available channel bandwidth as well as display size. By utilising compressed domain features an e cient hierarchical analysis of motion activity at di erent layers of complexity is achieved. Exploiting a contour evolution algorithm, a scale space of temporal video descriptors is generated, enabling dynamic video summarisation in real-time. Given the spatial resources of terminal display and generated video summary, the nal browsing layout is generated utilising an unsupervised robust spectral clus- tering technique and a fast discrete optimisation algorithm. Results show excellent scalability of the video browsing interface and good algorithm efficiency.