We describe our studies on summarising surveillance videos using optical flow information. The proposed method incorporates motion analysis into a video skimming scheme in which the playback speed is determined by the detectability of interesting motion behaviours according to prior information. A psycho-visual experiment was conducted to compare human performance and viewing strategy for summarised videos using standard video skimming techniques and a proposed motion-based adaptive summarisation technique.
|Title of host publication||IEEE Conference on Advanced Video and Signal Based Surveillance Systems, London, England|
|Pages||546 - 551|
|Number of pages||6|
|Publication status||Published - 5 Sep 2007|
Li, J., Nikolov, SG., Benton, CP., & Scott-Samuel, NE. (2007). Adaptive summarisation of surveillance video sequences. In IEEE Conference on Advanced Video and Signal Based Surveillance Systems, London, England (pp. 546 - 551) https://doi.org/10.1109/AVSS.2007.4425369