BRIEF: Computing a Local Binary Descriptor Very Fast
| Autor: | Pascal Fua, Christoph Strecha, Mustafa Özuysal, Vincent Lepetit, Michael Calonder, Tomasz Trzcinski |
|---|---|
| Rok vydání: | 2011 |
| Předmět: |
Binary descriptors
Basis (linear algebra) business.industry Applied Mathematics point matching Feature extraction SURF ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Scale-invariant feature transform Pattern recognition Point set registration Hamming distance Computational Theory and Mathematics Artificial Intelligence Feature (computer vision) SIFT Fraction (mathematics) Computer Vision and Pattern Recognition Artificial intelligence business Quantization (image processing) Software Mathematics |
| Zdroj: | IEEE transactions on pattern analysis and machine intelligence. 34(7) |
| ISSN: | 1939-3539 |
| Popis: | Binary descriptors are becoming increasingly popular as a means to compare feature points very fast while requiring comparatively small amounts of memory. The typical approach to creating them is to first compute floating-point ones, using an algorithm such as SIFT, and then to binarize them. In this paper, we show that we can directly compute a binary descriptor, which we call BRIEF, on the basis of simple intensity difference tests. As a result, BRIEF is very fast both to build and to match. We compare it against SURF and SIFT on standard benchmarks and show that it yields comparable recognition accuracy, while running in an almost vanishing fraction of the time required by either. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|