Classification of Agricultural Crops and Quality Assessment Using Multispectral and Multitemporal Images
2003 (English)Report (Other academic)
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. The new algorithm was applied to a study area where satellite images (SPOT and Landsat TM) from different seasons over a year were used. It showed that using five seasonal images can substantially improve the classification accuracy compared to using one single image. As an real application to a large scale, the approach was applied to the Dalälven's catchment area. As the distributions for different classes are highly overlapping it is not possible to get satisfactory accuracy at pixel level. In stead it is necessary to introduce a new concept, pixel-wise probabilistic classifiers. The pixel-wise vectors of probabilities can be used to judge how reliablea 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.
Place, publisher, year, edition, pages
Sveriges Lantbruksuniversitet, 2003. , 20 p.
, Research Report, Centre of Biostochastics, ISSN 1651-8543 ; 2003-7
Classification, nearest neighbor method, probabilistic classifier, agricultural crops, quality assessment, multispectral and multitemporal images, remote sensing, catchment area.
Probability Theory and Statistics
Research subject Mathematical Statistics; Earth Sciences with Specialization Environmental Analysis
IdentifiersURN: urn:nbn:se:umu:diva-63723OAI: oai:DiVA.org:umu-63723DiVA: diva2:582498