Publication Details
Robust motion segmentation for on-line application
Beran Vítězslav, doc. Ing., Ph.D. (DCGM FIT BUT)
Motion segmentation, moving objects detection, KLT tracker, Voronoi tessellation.
This paper presents a novel approach for on-line video motion segmentation. Common methods were designed for off-line processing, where time to process one frame is not so important and varies from minutes to hours. The motivation of our work was an application in robotic perception, where a high computational speed is required. The main contribution of this work is an adaptation of existing methods to a higher computational speed and on-line processing. The proposed approach is based on sparse features, we utilized the KLT tracker to obtain their trajectories. A RANSAC-based method is used for initial motion segmentation, resulting motion groups are partitioned by a spatial-proximity constraints. The correspondence of motion groups across frames is solved by one-frame label propagation in forward and backward directions. Finally, an approximation of dense image segmentation is obtained by using the Voronoi tessellation.
@INPROCEEDINGS{FITPUB9988, author = "Luk\'{a}\v{s} Klicnar and V\'{i}t\v{e}zslav Beran", title = "Robust motion segmentation for on-line application", pages = "205--212", booktitle = "Proceedings of WSCG'12", series = "20th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision, WSCG 2012 - Conference Proceedings", year = 2012, location = "Plze\v{n}, CZ", publisher = "University of West Bohemia in Pilsen", ISBN = "978-80-86943-79-4", language = "english", url = "https://www.fit.vut.cz/research/publication/9988" }