Loading...
Please wait, while we are loading the content...
Similar Documents
Robust multisensor image registration with partial distance merits
| Content Provider | Semantic Scholar |
|---|---|
| Author | Sheng, Yunlong Yang, Xiangjie Sévignyc, Léandre Valinb, Pierre |
| Copyright Year | 2000 |
| Abstract | Challenge in the registration of battlefield images in visible and far-infrared bands is the feature inconsistency. We propose a contour-based approach for the registration and apply two free-form curve-matching algorithms: adaptive hill climbing and the iterative closest point algorithm. Both algorithms do not requires explicit curve feature correspondence, are designed to be robust against outliers. We formulate the search as an adaptive hill climbing optimization for minimizing the partial Hausdorff distances. In the iterative closest point algorithm we choose the mean partial distance as the objective function, so that outliers can be easily handled by using rank order statistics. |
| File Format | PDF HTM / HTML |
| Alternate Webpage(s) | http://fourier.phy.ulaval.ca/~sheng/NATO-sensor%20fusion-2000.pdf |
| Alternate Webpage(s) | https://www.intranet.copl.ulaval.ca/sheng/publications/NATO-sensor%20fusion-2000.pdf |
| Alternate Webpage(s) | http://fusion.isif.org/proceedings/fusion00CD/fusion2000/papers/MoD3-4-XiangjieYang090.pdf |
| Language | English |
| Access Restriction | Open |
| Subject Keyword | Algorithm Bands Computational anatomy Computer vision Distance Distance transform Edge detection Entity Name Part Qualifier - adopted Hausdorff dimension Hill climbing Image registration Iterative closest point Iterative method Language Translations License Loss function MATCHING Map Mathematical optimization Mean squared error Natural Science Disciplines Numerous Optimization problem Quadtree registration - ActClass |
| Content Type | Text |
| Resource Type | Article |
