Abstract | ||
---|---|---|
Motion segmentation relies on identifying coherent relationships between image pixels that are associated with motion vectors. However, perspective differences can often deteriorate the performance of conventional techniques. In this paper, we develop a motion segmentation scheme that utilizes the motion map of a single frame to identify motion representations based on motion vanishing points. Segmentation is achieved using graph spectral clustering where a novel graph is constructed using the motion representation distances in the motion vanishing point image associated with the image pixels. Experimental results show that the proposed graph spectral motion segmentation algorithm outperforms state-of-the-art methods for dense segmentation on image sequences with strong perspective effects using motion vectors between only two images. |
Year | DOI | Venue |
---|---|---|
2015 | 10.1109/MMSP.2015.7340869 | 2015 IEEE 17th International Workshop on Multimedia Signal Processing (MMSP) |
Keywords | Field | DocType |
graph spectral motion segmentation,motion vanishing point analysis,image pixels,motion vectors,motion representations,graph spectral clustering,image sequences | Structure from motion,Computer vision,Motion field,Scale-space segmentation,Pattern recognition,Computer science,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Motion estimation,Connected-component labeling,Minimum spanning tree-based segmentation | Conference |
ISSN | Citations | PageRank |
2163-3517 | 0 | 0.34 |
References | Authors | |
10 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dong Tian | 1 | 20 | 8.02 |
Jiun-Yu Kao | 2 | 0 | 0.68 |
Hassan Mansour | 3 | 349 | 34.12 |
Anthony Vetro | 4 | 1580 | 115.57 |