DocumentCode :
3456664
Title :
Object classification inwater sports
Author :
Plestina, Vladimir ; Papic, Vladan
Author_Institution :
Dept. of Polytech., Univ. of Split, Split, Croatia
fYear :
2013
fDate :
7-10 July 2013
Abstract :
Object classification is a difficult task in many domains. In this paper we propose a method for pixel classification in water sports domain. We separate luminance from YCbCr color space and define 2D color plane and 3D color space for pixels set classification. 2D color plane classification is based on Euclidean distance while 3D color space classification is based on the use of bivariate histograms. Experimental results demonstrate the validity and efficiency of the proposed approach.
Keywords :
image classification; image colour analysis; sport; 2D color plane classification; 3D color space classification; Euclidean distance; YCbCr color space; bivariate histograms; object classification; pixel classification; pixels set classification; water sports; Brightness; Correlation; Euclidean distance; Image color analysis; Solid modeling; Testing; Three-dimensional displays; YCbCr color model; supervised image classification; water polo;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Computers and Communications (ISCC), 2013 IEEE Symposium on
Conference_Location :
Split
Type :
conf
DOI :
10.1109/ISCC.2013.6755053
Filename :
6755053
Link To Document :
بازگشت