SURF: Speeded Up Robust Features: Difference between revisions
| (3 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
* [https://link.springer.com/chapter/10.1007/11744023_32 Springer Link to Paper (ECCV 2006) Paywall] | |||
* [http://people.ee.ethz.ch/~surf/eccv06.pdf Paper] | |||
* [[Media:Surf_speeded_up_robust_features_eccv06.pdf | Mirror]] | |||
* | ;Authors: | ||
* Herbert Bay - ETH Zurich | |||
* Tinne Tuytelaars - Katholieke Universiteit Leuven | |||
* Luc Van Gool - ETH Zurich, Katholieke Universiteit Leuven | |||
==Feature Extraction== | ==Feature Extraction== | ||
| Line 38: | Line 44: | ||
* Sample Haar-wavelet responses in x and y-direction at points around each feature | * Sample Haar-wavelet responses in x and y-direction at points around each feature | ||
** Using integral images, only 6 operations are need to compute in x or y direction (Fig. 2 middle) | ** Using integral images, only 6 operations are need to compute in x or y direction (Fig. 2 middle) | ||
**: We have 6 distinct corners so we need | **: We have 6 distinct corners so we need 6 fma operations in total for each direction. (Actually 5 if one value is just multiplied by 1) | ||
* Using a 360-degree (pivoting) sliding window with radius <math>\frac{\pi}{3}</math>, calculate the sum of all horizontal and vertical responses yielding vector. Note the window moves in increments of <math>\frac{\pi}{3}</math> | * Using a 360-degree (pivoting) sliding window with radius <math>\frac{\pi}{3}</math>, calculate the sum of all horizontal and vertical responses yielding vector. Note the window moves in increments of <math>\frac{\pi}{3}</math> | ||
* Pick the direction with the largest vector. | * Pick the direction with the largest vector. | ||