期刊名称：International Journal of Environment and Geoinformatics
电子版ISSN：2148-9173
出版年度：2018
卷号：5
期号：2
页码：231-243
DOI：10.30897/ijegeo.442002
语种：English
出版社：IJEGEO
摘要：With the latestdevelopment and increasing availability of high spatial resolution sensors,earth observation technology offers a viable solution for crop identificationand management. There is a strong need to produce accurate, reliable and up todate crop type maps for sustainable agriculture monitoring and management. Inthis study, RapidEye, the first high-resolution multi-spectral satellite systemthat operationally provides a Red-edge channel, was used to test the potentialof the data for crop type mapping. This study was investigated at a selectedregion mostly covered with agricultural fields locates in the low lands ofMenemen (İzmir) Plain, TURKEY. The potential of the three classificationalgorithms such as Maximum Likelihood Classification, Support Vector Machineand Object Based Image Analysis istested. Accuracy assessment of land cover maps has been performedthrough error matrix and kappa indexes. The results highlighted that allselected classifiers as highly useful (over 90%) in mapping of crop types inthe study region however the object-based approach slightly outperforming theSupport Vector Machine classification by both overall accuracy and Kappastatistics. The success of selected methods also underlines the potential ofRapidEye data for mapping crop types in Aegean region.
关键词：crop type mapping; Pixel-based classification; Object-based classification
