Name
Abstract | ||
|---|---|---|
Illumination changes are a ubiquitous problem in computer vision. They present a challenge in many applications, including tracking: for example, an object may move in and out of a shadow. We present a new tracking algorithm which is insensitive to illumination changes, while at the same time using all of the available photometric information. The algorithm is based on computing an illumination-invariant optical flow field; the computation is made robust by using a graph cuts formulation. Experimentally, the new technique is shown to quite reliable in both synthetic and real sequences, dealing with a variety of illumination changes that cause problems for density based trackers. |
Year | DOI | Venue |
|---|---|---|
2005 | 10.1109/CVPR.2005.182 | CVPR (2) |
Keywords | Field | DocType |
ubiquitous problem,illumination invariance,computer vision,graph cuts.,optical flow,graph cuts,graph cuts formulation,illumination-invariant optical flow field,illumination-invariant tracking,tracking,illumination change,new tracking algorithm,available photometric information,new technique,cause problem,real sequence,application software,photometry,graph theory,graph cut,robustness,lighting,ubiquitous computing,optical computing | Cut,Graph theory,Computer vision,Shadow,Graph cuts in computer vision,Computer science,Artificial intelligence,Invariant (mathematics),Ubiquitous computing,Optical flow,Computation | Conference |
ISSN | ISBN | Citations |
1063-6919 | 0-7695-2372-2 | 33 |
PageRank | References | Authors |
1.92 | 19 | 2 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Daniel Freedman | 1 | 517 | 27.79 |
| Matthew Turek | 2 | 88 | 6.29 |