DocumentCode :
3719691
Title :
cFAST: A fast color feature detector
Author :
C. Robert Pech;Jens Vial;Andreas Zell
Author_Institution :
Chair of Cognitive Systems, Computer Science Department, University of Tuebingen, Tuebingen, Germany
fYear :
2015
Firstpage :
248
Lastpage :
253
Abstract :
By extending the basic idea of FAST it is possible to create a detector that can operate directly on a RGB color image and on it detect a higher number of features. The higher number of points and the simplification of the metric put us in the position to impose an additional condition on the keypoints. In order to do so we picked up a problem of FAST and defined a condition for similar points. This additional condition enables results that are better than FAST with regard to stability. Furthermore this condition enables a fast implementation, so that with the triple amount of input data due to the color channels less than threefold of time is required.
Keywords :
"Image color analysis","Feature extraction","Detectors","Databases","Lighting","Color","Measurement"
Publisher :
ieee
Conference_Titel :
Image Processing Theory, Tools and Applications (IPTA), 2015 International Conference on
Print_ISBN :
978-1-4799-8636-1
Electronic_ISBN :
2154-512X
Type :
conf
DOI :
10.1109/IPTA.2015.7367139
Filename :
7367139
Link To Document :
بازگشت