DocumentCode :
477873
Title :
Application of Texture Analysis in Land Cover Classification of High Resolution Image
Author :
Shen, Guangrong ; Sarris, Apostolos
Author_Institution :
Sch. of Agric. & Biol., Shanghai Jiaotong Univ., Shanghai
Volume :
3
fYear :
2008
fDate :
18-20 Oct. 2008
Firstpage :
513
Lastpage :
517
Abstract :
The present paper deals with the land cover classification of high resolution Quickbird images using the texture feature analysis. The study area covers the wider region of the urbanized environment of Chania, Greece. Different textural features including Entropy and Asm (angular second moment) were extracted based on GLCM (Grey Level Co-occurrence Matrix) texture feature and used as the distinct feature value in classification procedures. The classification was performed on the texture image that was produced by the synthesis of the original image with vegetation index BRI (band ratio index) extracted from the original datasets. Results indicate that the proposed approach brings significant improvement of the classification rate based on the different texture feature images of various bands, allowing a better discrimination and mapping of mixed land cover types.
Keywords :
geophysical signal processing; image classification; image resolution; image texture; Chania; Greece; classification rate; high resolution Quickbird images; high resolution image; image classification; land cover classification; texture feature analysis; Agriculture; Entropy; Feature extraction; Image analysis; Image resolution; Image segmentation; Image texture analysis; Satellites; Statistical analysis; Vegetation mapping; Classification; GLCM; High-resolution Image; Texture feature;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Fuzzy Systems and Knowledge Discovery, 2008. FSKD '08. Fifth International Conference on
Conference_Location :
Shandong
Print_ISBN :
978-0-7695-3305-6
Type :
conf
DOI :
10.1109/FSKD.2008.241
Filename :
4666298
Link To Document :
بازگشت