Abstract | ||
---|---|---|
Extracting moving objects from their background or partitioning them have been one of the most prerequisite tasks for various computer vision applications such as surveillance, tracking, human machine interface. etc. Though many previous approaches have been working in a certain level, still they are not robust under various unexpected situation such as large illumination change. In this paper. we propose a motion segmentation method based on our robust illumination invariant optical flow estimation. We present the superiority of our motion estimation method with synthesized images and improved segmentation results with real images. |
Year | DOI | Venue |
---|---|---|
2011 | 10.1007/978-3-642-27186-1_10 | Communications in Computer and Information Science |
Keywords | Field | DocType |
Motion estimation,Optical flow,Segmentation,Illumination invariant | Computer vision,Scale-space segmentation,Segmentation,Computer science,Optical flow estimation,Artificial intelligence,Invariant (mathematics),Human–machine interface,Real image,Motion estimation,Optical flow | Conference |
Volume | ISSN | Citations |
263 | 1865-0929 | 0 |
PageRank | References | Authors |
0.34 | 14 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Yeonho Kim | 1 | 121 | 10.69 |
Soo-Yeong Yi | 2 | 30 | 6.92 |