DocumentCode :
58347
Title :
Crop Stage Classification of Hyperspectral Data Using Unsupervised Techniques
Author :
Senthilnath, J. ; Omkar, S.N. ; Mani, V. ; Karnwal, N. ; Shreyas, P.B.
Author_Institution :
Dept. of Aerosp. Eng., Indian Inst. of Sci., Bangalore, India
Volume :
6
Issue :
2
fYear :
2013
fDate :
Apr-13
Firstpage :
861
Lastpage :
866
Abstract :
The presence of a large number of spectral bands in the hyperspectral images increases the capability to distinguish between various physical structures. However, they suffer from the high dimensionality of the data. Hence, the processing of hyperspectral images is applied in two stages: dimensionality reduction and unsupervised classification techniques. The high dimensionality of the data has been reduced with the help of Principal Component Analysis (PCA). The selected dimensions are classified using Niche Hierarchical Artificial Immune System (NHAIS). The NHAIS combines the splitting method to search for the optimal cluster centers using niching procedure and the merging method is used to group the data points based on majority voting. Results are presented for two hyperspectral images namely EO-1 Hyperion image and Indian pines image. A performance comparison of this proposed hierarchical clustering algorithm with the earlier three unsupervised algorithms is presented. From the results obtained, we deduce that the NHAIS is efficient.
Keywords :
geophysical image processing; geophysical techniques; hyperspectral imaging; image classification; remote sensing; EO-1 Hyperion IEEE image; Indian pines image; Niche Hierarchical Artificial Immune System; crop stage classification; hierarchical clustering algorithm; hyperspectral data; hyperspectral images; principal component analysis; spectral bands; unsupervised algorithms; unsupervised classification techniques; Agriculture; Cloning; Clustering algorithms; Hyperspectral imaging; Immune system; Principal component analysis; Hyperspectral images; niche hierarchical artificial immune system; principal component analysis;
fLanguage :
English
Journal_Title :
Selected Topics in Applied Earth Observations and Remote Sensing, IEEE Journal of
Publisher :
ieee
ISSN :
1939-1404
Type :
jour
DOI :
10.1109/JSTARS.2012.2217941
Filename :
6332548
Link To Document :
بازگشت