Languages
Video-based tracking
Video-based people tracking
An aim of the project is to create video based people tracking algorithm. We define tracking as a estimation of person location in each frame and for each person presented in the video sequence. Currently the most promising methods of multiple person tracking are based on tracking-by-detection approach. Within this framework algorithms consist of following three stages:
- People detection in the key frames of the video sequence
- People trajectories construction
- Person location estimation in the all frames of the video sequence
On the first stage of the pipeline person head detector can be applied to detect people presented in the frame. Some persons may not be found because of errors of the detector. Also detector may not be applied to each frame through its high complexity:
Team
- Anton S. Konushin, Lomonosov Moscow State University
- Evgeny Shalnov, Lomonosov Moscow State University
- Vadim Konushin, Lomonosov Moscow State University
- Vladimir Kononov, Lomonosov Moscow State University
Publications
- Gringauz A, Shalnov E, Konushin A. Modification of the Multi-target Tracking Algorithm Based on Energy Minimization. GraphiCon-2014, 2014 (download)
- Shalnov E, Konushin A. Improvement of MCMC-based video tracking algorithm. Pattern rcognition and image analysis (PRIA-11-2013), 2013 (download)
- Kononov V, Konushin V, Konushin A. People Tracking Algorithm for Human Height Mounted Cameras. DAGM, 2011 (download)
- Shalnov E, Konushin V, Konushin A. An improvement on an MCMC-based video tracking algorithm. Pattern Recognition and Image Analysis, 2015 (download)
Acknowledgements
This work is partillay supported by grant of the President of the Russian Federation for the young scientists МК-4644.2012.9 "Content-based search in video archives" and grant RFBR 11-01-00957-а "Video-based person analysis algorithms for smart interfaces".