Title :
Semi-automatic motion based segmentation using long term motion trajectories
Author :
Baugh, Gary ; Kokaram, Anil
Author_Institution :
Dept. of Electron. & Electr. Eng., Trinity Coll. Dublin, Dublin, Ireland
Abstract :
Semi-automated object segmentation is an important step in the cinema post-production workflow. We propose a dense motion based segmentation process that employs sparse feature based trajectories estimated across a long sequence of frames, articulated with a Bayesian framework. The algorithm first classifies the sparse trajectories into sparsely defined objects. Then the sparse object trajectories together with motion model side information are used to generate a dense object segmentation of each video frame. Unlike previous work, we do not use the sparse trajectories only to propose motion models, but instead use their position and motion throughout the sequence as part of the classification of pixels in the second step. Furthermore, we introduce novel colour and motion priors that employ the sparse trajectories to make explicit the spatiotemporal smoothness constraints important for long term motion segmentation.
Keywords :
Bayes methods; image classification; image colour analysis; image motion analysis; image segmentation; smoothing methods; video signal processing; Bayesian framework; cinema post-production workflow; dense motion based segmentation; dense object segmentation; image colour; image motion; long term motion segmentation; long term motion trajectory; pixel classification; semiautomated object segmentation; semiautomatic motion based segmentation; sparse object trajectory; sparsely defined object; spatiotemporal smoothness constraint; video frame; Image color analysis; Image segmentation; Labeling; Motion segmentation; Pixel; Tracking; Trajectory; Bayesian segmentation; feature tracking; motion segmentation;
Conference_Titel :
Image Processing (ICIP), 2010 17th IEEE International Conference on
Conference_Location :
Hong Kong
Print_ISBN :
978-1-4244-7992-4
Electronic_ISBN :
1522-4880
DOI :
10.1109/ICIP.2010.5653946