DocumentCode :
3497068
Title :
A new feature selection algorithm for multispectral and polarimetric vehicle images
Author :
Nakariyakul, Songyot
Author_Institution :
Dept. of Electr. & Comput. Eng., Thammasat Univ., Pathumthani, Thailand
fYear :
2009
fDate :
7-10 Nov. 2009
Firstpage :
2865
Lastpage :
2868
Abstract :
Multispectral and polarimetric data have been shown to provide detailed information useful for automatic target recognition applications. A major limitation of using these data in remote sensing is that they often consist of a large number of features with an inadequate number of samples. To reduce the number of features, we thus present a new generalized steepest ascent feature selection technique that selects only a small subset of important features to use for classification. Our proposed algorithm improves upon the prior steepest ascent algorithm by selecting a better starting search point and performing a more thorough search. It is guaranteed to provide solutions that equal or exceed those of the classical sequential forward floating selection algorithm. Initial results for one multispectral and polarimetric data set show that our algorithm yields better classification results than other suboptimal search algorithms.
Keywords :
feature extraction; geophysical image processing; image recognition; remote sensing; spectral analysis; target tracking; vehicles; automatic target recognition; classical sequential forward floating selection algorithm; feature selection algorithm; generalized steepest ascent feature selection technique; multispectral vehicle images; polarimetric vehicle images; prior steepest ascent algorithm; remote sensing; suboptimal search algorithms; Application software; Classification algorithms; Displays; Land vehicles; Object detection; Object recognition; Polarization; Remote sensing; Target recognition; Vehicle detection; Feature selection; multispectral data; object detection; polarimetric data; remote sensing;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2009 16th IEEE International Conference on
Conference_Location :
Cairo
ISSN :
1522-4880
Print_ISBN :
978-1-4244-5653-6
Electronic_ISBN :
1522-4880
Type :
conf
DOI :
10.1109/ICIP.2009.5414581
Filename :
5414581
Link To Document :
بازگشت