| Title: | An EM based approach for motion segmentation of video sequence |
| Authors: | Zhao, Wei Roos, Nico |
| Citation: | WSCG 2016: full papers proceedings: 24th International Conference in Central Europe on Computer Graphics, Visualization and Computer Vision in co-operation with EUROGRAPHICS Association, p. 61-69. |
| Issue Date: | 2016 |
| Publisher: | Václav Skala - UNION Agency |
| Document type: | konferenční příspěvek conferenceObject |
| URI: | wscg.zcu.cz/WSCG2016/!!_CSRN-2601.pdf http://hdl.handle.net/11025/29532 |
| ISBN: | 978-80-86943-57-2 |
| ISSN: | 2464–4617 (print) 2464–4625 (CD-ROM) |
| Keywords: | segmentace pohybu;EM algoritmus;Bayesovská aktualizace;SIFT funkce;shlukování trajektorií |
| Keywords in different language: | motion segmentation;EM algorithm;Bayesian update;SIFT feature;trajectory clustering |
| Abstract: | Motions are important features for robot vision as we live in a dynamic world. Detecting moving objects is crucial for mobile robots and computer vision systems. This paper investigates an architecture for the segmentation of moving objects from image sequences. Objects are represented as groups of SIFT feature points. Instead of tracking the feature points over a sequence of frames, the movements of feature points between two successive frames are used. The segmentation of motions of each pair of frames is based on the expectation-maximization algorithm. The segmentation algorithm is iteratively applied over all frames of the sequence and the results are combined using Bayesian update. |
| Rights: | © Václav Skala - UNION Agency |
| Appears in Collections: | WSCG 2016: Full Papers Proceedings |
Please use this identifier to cite or link to this item:
http://hdl.handle.net/11025/29532Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.