作者: KEN W. DAWBIN , JOHN C. EVANS
DOI: 10.1080/01431168808954853
关键词: Cartography 、 Geography 、 Pixel 、 Remote sensing 、 Maximum likelihood 、 Confusion 、 Land cover 、 Crop 、 Ground truth 、 Test sample
摘要: Abstract This paper describes digital crop classification techniques developed for Australian conditions. Using extensive ground truth data, supervized maximum likelihood was used to classify Landsat data from five dates across approximately half a scene into winter crops and other land cover types. Inaccuracies in the prediction of total hectarage an independent test sample pixels indicated confusion between wheat barley all combinations dates. However, when wheat, oats were considered together against non-winter crops, predictions very accurate demonstrated applicability this method classification.