Abstract | ||
---|---|---|
We present a novel method for the detection of motion boundaries in a video sequence based on differential properties of the spatio-temporal domain. Regarding the video sequence as a 3D spatio-temporal function, we consider the second moment matrix of its gradients (averaged over a local window), and show that the eigenvalues of this matrix can be used to detect occlusions and motion discontinuities. Since these cannot always be determined locally (due to false corners and the aperture problem), a scale-space approach is used for extracting the location of motion boundaries. A closed contour is then constructed from the most salient boundary fragments, to provide the final segmentation. The method is shown to give good results on pairs of real images taken in general motion. We use synthetic data to show its robustness to high levels of noise and illumination changes; we also include cases where no intensity edge exists at the location of the motion boundary, or when no parametric motion model can describe the data. |
Year | DOI | Venue |
---|---|---|
2006 | 10.1007/978-3-540-70932-9_3 | WDV |
Keywords | Field | DocType |
occlusion detector,novel method,salient boundary fragment,parametric motion model,general motion,motion boundary,spatio-temporal function,motion discontinuity,motion segmentation,spatio-temporal domain,moment matrix,video sequence,synthetic data,scale space,aperture problem | Structure from motion,Computer vision,Motion field,Computer science,Segmentation,Motion compensation,Robustness (computer science),Parametric statistics,Artificial intelligence,Motion estimation,Real image | Conference |
Volume | ISSN | ISBN |
4358 | 0302-9743 | 3-540-70931-2 |
Citations | PageRank | References |
3 | 0.49 | 18 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Doron Feldman | 1 | 57 | 4.33 |
Daphna Weinshall | 2 | 1780 | 273.93 |