Jet-Based Local Image Descriptors
| Autor: | Anders Boesen Lindbo Larsen, Anders Lindbjerg Dahl, Kim Steenstrup Pedersen, Sune Darkner |
|---|---|
| Rok vydání: | 2012 |
| Předmět: |
Jet (fluid)
business.industry Computer science GLOH ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale (descriptive set theory) Image (mathematics) Differential geometry Computer Science::Computer Vision and Pattern Recognition Computer Science::Multimedia Computer vision Artificial intelligence business Curse of dimensionality |
| Zdroj: | Computer Vision – ECCV 2012 ISBN: 9783642337116 ECCV (3) |
| DOI: | 10.1007/978-3-642-33712-3_46 |
| Popis: | We present a general novel image descriptor based on higherorder differential geometry and investigate the effect of common descriptor choices. Our investigation is twofold in that we develop a jet-based descriptor and perform a comparative evaluation with current state-of-the-art descriptors on the recently released DTU Robot dataset. We demonstrate how the use of higher-order image structures enables us to reduce the descriptor dimensionality while still achieving very good performance. The descriptors are tested in a variety of scenarios including large changes in scale, viewing angle and lighting. We show that the proposed jet-based descriptor is superior to state-of-the-art for DoG interest points and show competitive performance for the other tested interest points. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|