CERTH just publicly released version 1.2 of its software for the automatic temporal segmentation of videos. This extends the previous versions by integrating algorithms for video scene segmentation and keyframe selection (up to 5 most representative keyframes of each scene are identified), on top of the segmentation to shots that is also performed by the released software. The new algorithmic additions do not affect the processing speed, which remains at least 2-3 times faster than real-time processing (depending on the processing capability of the graphics card) for the entire video analysis chain (i.e., shot segmentation, scene segmentation and keyframe selection).
The development and release of this software was supported by EU research projects LinkedTV (http://www.linkedtv.eu/) and MediaMixer (http://www.mediamixer.eu/).
The software is available for download at http://mklab.iti.gr/project/video-shot-segm
Related technical papers:
– E. Apostolidis, V. Mezaris, “Fast Shot Segmentation Combining Global and Local Visual Descriptors”, Proc. IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), Florence, Italy, May 2014. (available at http://www.iti.gr/~bmezaris/publications/icassp14_preprint.pdf)
– P. Sidiropoulos, V. Mezaris, I. Kompatsiaris, H. Meinedo, M. Bugalho, I. Trancoso, “Temporal video segmentation to scenes using high-level audiovisual features”, IEEE Transactions on Circuits and Systems for Video Technology, vol. 21, no. 8, pp. 1163-1177, August 2011. (available at http://www.iti.gr/~bmezaris/publications/csvt11_preprint.pdf)