Abstract | ||
---|---|---|
In this paper, a novel multiple motion object segmentation scheme based on homogenous region merging is presented. This scheme is based on utilization of a robust multiresolution motion estimator that can provide good motion estimates from irregularly-shaped regions. In addition, a novel region-merging criterion and an iterative region-merging process have been proposed. Experimental results demonstrate the effectiveness of the proposed method. |
Year | DOI | Venue |
---|---|---|
2001 | 10.1109/ISCAS.2001.922013 | ISCAS (5) |
Keywords | Field | DocType |
robustness,motion estimation,iterative methods,merging,image segmentation,testing,computer vision,data mining,object recognition | Computer vision,Scale-space segmentation,Pattern recognition,Computer science,Iterative method,Segmentation,Segmentation-based object categorization,Image segmentation,Artificial intelligence,Motion estimation,Estimator,Cognitive neuroscience of visual object recognition | Conference |
Citations | PageRank | References |
0 | 0.34 | 9 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Hong Li | 1 | 10 | 8.36 |
Bee June Tye | 2 | 8 | 1.37 |
Ee Ping Ong | 3 | 313 | 33.36 |
Weisi Lin | 4 | 5366 | 280.14 |
Chi Chung Ko | 5 | 753 | 81.90 |