Consensus Maximization for Semantic Region Correspondences
| Autor: | Marc Pollefeys, Luc Van Gool, Danda P. Paude, Hayko Riemenschneider, Pablo Speciale |
|---|---|
| Rok vydání: | 2018 |
| Předmět: |
Mathematical optimization
Computer science business.industry Linear matrix inequality 02 engineering and technology Maximization 010501 environmental sciences 01 natural sciences Ellipsoid Convexity Outlier 0202 electrical engineering electronic engineering information engineering Symmetric matrix Leverage (statistics) 020201 artificial intelligence & image processing Artificial intelligence business 0105 earth and related environmental sciences |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2018.00764 |
| Popis: | We propose a novel method for the geometric registration of semantically labeled regions. We approximate semantic regions by ellipsoids, and leverage their convexity to formulate the correspondence search effectively as a constrained optimization problem that maximizes the number of matched regions, and which we solve globally optimal in a Branch-and-Bound fashion. To this end, we derive suitable linear matrix inequality constraints which describe ellipsoid-to-ellipsoid assignment conditions. Our approach is robust to large percentages of outliers and thus applicable to difficult correspondence search problems. In multiple experiments we demonstrate the flexibility and robustness of our approach on a number of challenging vision problems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|