DocumentCode :
67012
Title :
A Multievidence Approach for Crop Discrimination Using Multitemporal WorldView-2 Imagery
Author :
Chellasamy, Menaka ; Zielinski, Rafal Tomasz ; Greve, Mogens Humlekrog
Author_Institution :
Dept. of Agroecology, Aarhus Univ., Aarhus, Denmark
Volume :
7
Issue :
8
fYear :
2014
fDate :
Aug. 2014
Firstpage :
3491
Lastpage :
3501
Abstract :
Despite using multiple input datasets for effective crop classification, it is important to select an appropriate method that efficiently integrates these multiple datasets to produce accurate classification results. In this paper, we present an endorsement theory-based crop classification approach that considers the qualitative information, in terms of prediction probabilities, from different input datasets and integrates them efficiently to produce final classification results. Three different input datasets are used in this study: 1) spectral; 2) texture; and 3) indices from multitemporal (spring, early summer) WorldView-2 multispectral imagery. A multilayer perceptron classifier is trained with the multitemporal datasets separately using a backpropagation learning algorithm, and prediction probabilities are produced for each pixel as evidence against each crop class. An integration rule based on endorsement theory is applied to these multiple evidence by considering their individual contribution, and the most probable class of a pixel is identified. Integration of the three multidate datasets by the proposed method is found to produce higher overall classification accuracy (91.2%) when compared to conventional winner-takes-all approach (89%). In order to determine which individual dataset is more useful for crop discrimination, the dataset´s performance is compared using evidence and contributions produced in the proposed integration method for four selected crops, for both single- and multidate. The results of this analyses showed that seasonal textures information outperformed both spectral and indices. To verify this finding, results of individual dataset classification are examined. The highest overall classification accuracy of 88.8% is achieved by the use of multidate texture, where multidate spectral and indices resulted in 86.3% and 84.4%, respectively.
Keywords :
geophysical image processing; geophysical techniques; image classification; remote sensing; vegetation; backpropagation learning algorithm; crop discrimination; effective crop classification; endorsement theory-based crop classification approach; multilayer perceptron classifier; multiple input datasets; multitemporal WorldView-2 imagery; multitemporal datasets; prediction probabilities; winner-takes-all approach; Accuracy; Agriculture; Feature extraction; Neural networks; Remote sensing; Springs; Vegetation mapping; Crop discrimination; WorldView-2 (WV2); endorsement theory (ET); multitemporal datasets; neural classifier;
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.2014.2349945
Filename :
6897967
Link To Document :
بازگشت