A generic bi-directional scheme is proposed that robustifies the estimation of the maximum-a-posteriori (MAP) sequence of states of a visual object. It enables creative, non-technical users to obtain the path of interesting objects in offline available video material, which can then be used to create interactive movies. To robustify against tracker failure the proposed scheme merges the filtering distributions of a forward tracking particle filter and a backward tracking particle filter at some timesteps, using a reliability-based voting scheme such as in democratic integration. The MAP state sequence is obtained using the Viterbi algorithm on reduced state sets per timestep and is interpolated linearly where tracking failure is suspected. The presented scheme is generic, simple and efficient and shows good results for a color-based particle filter.
Caljon, T, Enescu, V, Schelkens, P & Sahli, H 2005, An offline bidirectional tracking scheme. in Advanced Concepts for Intelligent Vision Systems (ACIVS), Antwerp, Belgium. vol. 3708, Lecture Notes in Computer Science, Lecture Notes in Computer Science, Nr. 3708, pp. 587-594, ., pp. 587-594, Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet, Stockholm, Sweden, 21/09/09.
Caljon, T., Enescu, V., Schelkens, P., & Sahli, H. (2005). An offline bidirectional tracking scheme. In Advanced Concepts for Intelligent Vision Systems (ACIVS), Antwerp, Belgium (Vol. 3708, pp. 587-594). (Lecture Notes in Computer Science). Lecture Notes in Computer Science, Nr. 3708, pp. 587-594, ..
@inproceedings{775a480c053b48839d4d05dad808993e,
title = "An offline bidirectional tracking scheme",
abstract = "A generic bi-directional scheme is proposed that robustifies the estimation of the maximum-a-posteriori (MAP) sequence of states of a visual object. It enables creative, non-technical users to obtain the path of interesting objects in offline available video material, which can then be used to create interactive movies. To robustify against tracker failure the proposed scheme merges the filtering distributions of a forward tracking particle filter and a backward tracking particle filter at some timesteps, using a reliability-based voting scheme such as in democratic integration. The MAP state sequence is obtained using the Viterbi algorithm on reduced state sets per timestep and is interpolated linearly where tracking failure is suspected. The presented scheme is generic, simple and efficient and shows good results for a color-based particle filter.",
keywords = "particle filtering, object tracking",
author = "Tom Caljon and Valentin Enescu and Peter Schelkens and Hichem Sahli",
note = "Lecture Notes in Computer Science, Nr. 3708, pp. 587-594, .; Finds and Results from the Swedish Cyprus Expedition: A Gender Perspective at the Medelhavsmuseet ; Conference date: 21-09-2009 Through 25-09-2009",
year = "2005",
month = aug,
day = "20",
language = "English",
isbn = "3-540-29032-X",
volume = "3708",
series = "Lecture Notes in Computer Science",
publisher = "Lecture Notes in Computer Science, Nr. 3708, pp. 587-594, .",
pages = "587--594",
booktitle = "Advanced Concepts for Intelligent Vision Systems (ACIVS), Antwerp, Belgium",
}