Publication Details
Tracking movement objects in sequence pictures
Trajectory Identification, Target Tracking, Kalman Filter, Movement Prediction, Motion Correspondence Problem, Prediction Trees, Backtracking, Continuity, Picture Segmentation.
There is presented approach how to tracked tokens in picture sequence.
The aim of my work was determine trajectory of moving simple objects - tokens in picture sequence. I used modified Kalman filter to predict and identify the trajectory of moving objects in sequence of 2D image. Presented approach resolves trajectory ambiguities, a case when a number of tokens are large and their speeds and accelerations vary. Correspondence problem is determined between two or more consecutive frames based on tokens similarity. Tracked objects may vanish, appear at a new position and/or mutually occlude each other. Backtracking is used to solve these problems.
@ARTICLE{FITPUB7100, author = "Igor Pot\'{u}\v{c}ek", title = "Tracking movement objects in sequence pictures", pages = "1--15", journal = "ElectronicsLetters.com", volume = 2003, number = 2, year = 2003, ISSN = "1213-161X", language = "english", url = "https://www.fit.vut.cz/research/publication/7100" }