Description

On this page you can download our Hidden Markov Model (HMM) and Hidden Semi Markov Model (HSMM) based C++ software tools for segmenting time-multiplexed videos.
The HSMM-based irregular camera event detection tool is available here.

References
  1. Á. Utasi, Novel Probabilistic Methods for Visual Surveillance Applications, Doctoral School of Information Science and Technology, University of Pannonia, Veszprém, Hungary, January 2012 (PDF Details BibTeX)
  2. Á. Utasi, L. Czúni, "Detecting Irregular Camera Events in Time-Multiplexed Videos", Electronics Letters, Volume 45, Issue 18, pp. 937-939, 2009 (PDF,BibTeX)
  3. Á. Utasi, L. Czúni, "Analysis of Time-Multiplexed Security Videos", in Proc. of The 6th IEEE International Conference on Advanced Video and Signal Based Surveillance, pp. 547-552, Genoa, Italy, 2-4 September 2009 (PDF,BibTeX)

Source codes

HMM-based tool (Viterbi algorithm and Expectation Maximization, C++): download
HSMM-based tool (Viterbi algorithm and Expectation Maximization, C++): download
Test video (huffyuv encoded avi): download

Demo


Download: avi, webm, ogg, mp4

Contact

Ákos Utasi: akos.utasi@sztaki.mta.hu


  _________________________________________
 /  Louis, I think this is the beginning   \
 \         of a beautiful FRIDAY!          /
  -----------------------------------------
        \   ,__,
         \  (oo)____
            (__)    )\
               ||--|| *