Spatiotemporal Video Synchronisation by Visual Matching

The media coverage of live events can be turned into a more immersive experience if content from multiple sources, e.g., professional and user generated content, are combined. We have implemented a visual matching approach to establish or improve temporal and visual synchronisation of such heterogeneous content. The approach is based on matching of SIFT descriptors and is implemented on the GPU. In order to visualise and explore the matching results, we have implemented a web-based viewer for the aligned content.