Semi-automatic extraction of supra-glacial features using fuzzy logic approach for object-oriented classification on WorldView-2 imagery

Shridhar D. Jawak; Yogesh Palanivel V.; Alvarinho J. Luis

doi:10.1117/12.2223024

30 April 2016 Semi-automatic extraction of supra-glacial features using fuzzy logic approach for object-oriented classification on WorldView-2 imagery

Shridhar D. Jawak, Yogesh Palanivel V., Alvarinho J. Luis

Author Affiliations +

Proceedings Volume 9880, Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications VI; 98801S (2016) https://doi.org/10.1117/12.2223024
Event: SPIE Asia-Pacific Remote Sensing, 2016, New Delhi, India

Abstract

High resolution satellite data provide high spatial, spectral and contextual information. Spatial and contextual information of image objects are in demand to extract the information from high resolution satellite data. The supraglacial environment includes several features that are present on the surface of the glacier. The extraction of features from supraglacial environment is quite challenging using pixel-based image analysis. To overcome this, objectoriented approach is implemented. This paper aims at the extraction of geo-information from the supraglacial environment from high resolution satellite image by object-oriented image analysis using the fuzzy logic approach. The object-oriented image analysis involves the multiresolution segmentation for the creation of objects followed by the classification of objects using the fuzzy logic approach. The multiresolution segmentation is executed on the pixel level initially which merges pixels for the creation of objects thus minimizing their heterogeneity. This is followed by the development of rule sets for the classification of various features such as blue ice, debris, snow from the supraglacial environment in WorldView-2 data. The area of extracted feature is compared with the reference data and misclassified area of each feature using various bands is determined. The present object oriented classification achieved an overall accuracy of ≈ 92% for classifying supraglacial features. Finally, it is suggested that Red band is quite effective in the extraction of blue ice and snow, while NIR1 band is effective in debris extraction.

Citation Download Citation

Shridhar D. Jawak, Yogesh Palanivel V., and Alvarinho J. Luis "Semi-automatic extraction of supra-glacial features using fuzzy logic approach for object-oriented classification on WorldView-2 imagery", Proc. SPIE 9880, Multispectral, Hyperspectral, and Ultraspectral Remote Sensing Technology, Techniques and Applications VI, 98801S (30 April 2016); https://doi.org/10.1117/12.2223024

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available