Hokkaido University Collection of Scholarly and Academic Papers >
Graduate School of Agriculture / Faculty of Agriculture >
Peer-reviewed Journal Articles, etc >
Random Forest classification of crop type using multi-temporal TerraSAR-X dual-polarimetric data
Title: | Random Forest classification of crop type using multi-temporal TerraSAR-X dual-polarimetric data |
Authors: | Sonobe, Rei Browse this author | Tani, Hiroshi Browse this author →KAKEN DB | Wang, Xiufeng Browse this author →KAKEN DB | Kobayashi, Nobuyuki Browse this author | Shimamura, Hideki Browse this author |
Keywords: | crop | gamma nought | multi-temporal classification approach | TerraSAR-X |
Issue Date: | Feb-2014 |
Publisher: | Taylor&Francis |
Journal Title: | Remote Sensing Letters |
Volume: | 5 |
Issue: | 2 |
Start Page: | 157 |
End Page: | 164 |
Publisher DOI: | 10.1080/2150704X.2014.889863 |
Abstract: | The classification maps are required for the management and the estimation of agricultural disaster compensation; however, those techniques have yet to be established. Some supervised learning models may allow accurate classification. In this study, the Random Forest (RF) classifier and the classification and regression tree (CART) were applied to evaluate the potential of multi-temporal TerraSAR-X dualpolarimetric data, on the StripMap mode, for the classification of crop type. Furthermore, comparisons of the two algorithms and polarizations were carried out. In the study area, beans, beet, grasslands, maize, potato and winter wheat were cultivated, and these crop types were classified using the data set acquired in 2009. The classification results of RF were superior to those of CART, and the overall accuracies were 0.91–0.93. |
Type: | article (author version) |
URI: | http://hdl.handle.net/2115/57984 |
Appears in Collections: | 農学院・農学研究院 (Graduate School of Agriculture / Faculty of Agriculture) > 雑誌発表論文等 (Peer-reviewed Journal Articles, etc)
|
Submitter: 薗部 礼
|