supervised classification of agricultural land cover using a modified k-nn technique (mnn) and landsat remote sensing imagery监督分类的农业土地覆盖使用修改后的事例(内容)和陆地卫星遥感图像的技术.pdf

Remote Sens. 2009, 1, 875-895; doi:10.3390/rs1040875 OPEN ACCESS Remote Sensing ISSN 2072-4292 /journal/Remote Sensing Article Supervised Classification of Agricultural Land Cover Using a Modified -NN Technique (MNN) and Landsat Remote Sensing Imagery Luis Samaniego and Karsten Schulz Department of Computational Hydrosystems, UFZ–Helmholtz-Centre for Environmental Research, Permoserstr. 15, 04318 Leipzig, Germany; E-Mail: luis.samaniego@ufz.de ¨ ¨ Department of Geography, Ludwig-Maximilians-Universitat Munchen, Luisenstr. 37, 80333 Munich, Germany Author to whom correspondence should be addressed; E-Mail: k.schulz@lmu.de; Tel.: +49-89-2180-6681; Fax: +49-89-2180-6675. Received: 9 September 2009; in revised form: 29 October 2009 / Accepted: 30 October 2009 / Published: 9 November 2009 Abstract: Nearest neighbor techniques are commonly used in remote sensing, pattern recognition and statistics to classify objects into a predefined number of categories based on a given set of predictors. These techniques are especially useful for highly nonlinear relationship between the variables. In most studies the distance measure is adopted a priori. In contrast we propose a general procedure to find an adaptive metric that combines a local variance reducing technique and a linear embedding of the observation space into an appropriate Euclidean space. To illustrate the application of this technique, two agricultural land cover classifications using mono-temporal