Rice crop classification from MODIS imageries using soft and hard classifiers

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

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

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.

Original languageEnglish
Title of host publication33rd Asian Conference on Remote Sensing 2012, ACRS 2012
Pages441-445
Number of pages5
StatePublished - 2012
Event33rd Asian Conference on Remote Sensing 2012, ACRS 2012 - Pattaya, Thailand
Duration: 26 Nov 201230 Nov 2012

Publication series

Name33rd Asian Conference on Remote Sensing 2012, ACRS 2012
Volume1

Conference

Conference33rd Asian Conference on Remote Sensing 2012, ACRS 2012
Country/TerritoryThailand
CityPattaya
Period26/11/1230/11/12

Keywords

  • Linear mixture model
  • MODIS
  • Rice crops
  • Support vector machines

Fingerprint

Dive into the research topics of 'Rice crop classification from MODIS imageries using soft and hard classifiers'. Together they form a unique fingerprint.

Cite this