Publication
A user supported tracking framework for interactive video production
Christian Bailer; Alain Pagani; Didier Stricker
In: Proceedings of the 10th European Conference on Visual Media Production. Conference on Visual Media Production (CVMP-13), 10th, November 6-7, London, United Kingdom, ACM Press, 11/2013.
Abstract
We present a user supported tracking framework that combines au-
tomatic tracking and extended user input to create error free track-
ing results that are suitable for interactive video production. The
goal of our approach is hereby to keep the necessary user input
as small as possible. In our framework, the user can select between
different tracking algorithms and if he/she wants automatically fuse
the results of different trackers with our robust fusion approach.
The tracked object can be marked in more than one frame, which
can significantly improve the tracking result. After tracking, the
user can validate the results in an easy way, thanks to the support
of a powerful interpolation technique. The tracking results are in-
teractively improved until the complete track has been found. After
the interactive editing process, the tracking result of each object is
stored in an external file in order to create the interactive video.