Skip to main content
SLU publication database (SLUpub)

Conference paper2005

Classification of agricultural crops and quality assessment using multispectral and multitemporal images

Yu Jun, Ranneby Bo

Abstract

In this paper, a new approach for classification of multitemporal satellite data sets, combining multispectral and change detection techniques is proposed. The algorithm is based on the nearest neighbor method and derived in order to optimize the average probability for correct classification, i.e. each class is equally important. As the distributions for different classes are highly overlapping it is not possible to get satisfactory accuracy at pixel level. Instead it is necessary to introduce a new concept, pixel-wise probabilistic classifiers. The pixel-wise vectors of probabilities can be used to judge how reliable a traditional classification is and to derive measures of the uncertainty (entropy) for the individual pixels. The probabilistic classifier gives also unbiased area estimates over arbitrary areas. It has been tested on two test sites of arable land with different characteristics

Published in

Proceedings of the 9th International Symposium on Physical Measurements and Signature in Remote Sensing (ISPMSRS), Beijing, China
2005, Volume: 36, number: 7
Publisher: ISPRS

Conference

The 9th International Symposium on Physical Measurements and Signature in Remote Sensing (ISPMSRS)