Rice crop classification from MODIS imageries using soft and hard classifiers

N. T. Son, C. F. Chen, C. R. Chen

研究成果: 書貢獻/報告類型會議論文篇章同行評審

摘要

Information on rice growing areas is important for crop production estimation. This study investigated the applicability of the linear mixture model (LMM) and support vector machines (SVM) to classify rice cropping systems in the Vietnamese Mekong Delta using MODIS data. Data were processed for 2006 comprising three main steps: (1) data pre-processing to generate smooth time-series NDVI data, (2) rice crop classification using LMM and SVM, and (3) classification accuracy assessment using the ground reference data and rice area statistics. The classification results indicated that SVM yielded slightly more accurate results than LMM. The overall accuracy and Kappa coefficient achieved by LMM were 79.9% and 0.73, while those by SVM were 85.1% and 0.80, respectively. The Z-test based on Kappa statistics reported the value of 0.275 smaller than 1.96, indicating no significant difference between the two methods. The comparison results between the MODIS-derived rice area and rice area statistics also affirmed close agreement (R2>0.8), in both cases.

原文???core.languages.en_GB???
主出版物標題33rd Asian Conference on Remote Sensing 2012, ACRS 2012
頁面441-445
頁數5
出版狀態已出版 - 2012
事件33rd Asian Conference on Remote Sensing 2012, ACRS 2012 - Pattaya, Thailand
持續時間: 26 11月 201230 11月 2012

出版系列

名字33rd Asian Conference on Remote Sensing 2012, ACRS 2012
1

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???33rd Asian Conference on Remote Sensing 2012, ACRS 2012
國家/地區Thailand
城市Pattaya
期間26/11/1230/11/12

指紋

深入研究「Rice crop classification from MODIS imageries using soft and hard classifiers」主題。共同形成了獨特的指紋。

引用此