Issue Description


Authors : R. R. Nagpure

Page Nos : 177-182

Description :
Abstract: The paper presents the methodology developed for classifying Rabi crop using NDVI time series derived from multi-date IRS AWiFS data. The study area covered the part of Chandrapur District, Maharashtra State. Multi-date IRS P6 AWiFS data for Three Rabi seasons (2011-12 to 2013-14) were used in this study. The classification technique is based on multi-stage classification of multi-date dataset by unsupervised Iterative Self Organizing Data Analysis Technique (ISODATA), assignment of classes based on existing temporal spectral profiles of different Rabi crops, local interpolation and decision rule based integration for final classified image. This hybrid classification technique takes advantage of inherent clustering tendency of land use / land cover classes in feature space with existing temporal dimension added to it in terms of NDVI time series data and it also makes use of signatures of known crop classes for assigning the class clusters. The estimated Rabi acreage of study area is needed to be compared with the existing crop acreage estimation of agriculture department. The large number of linear image features (like canals and roads) that were correctly classified using this technique. This technique is simple, time saving, less subjective and requires less expertise compared to hierarchical classification technique. Keywords: multi-date IRS AWiFS data, Self Organizing Data Analysis, NDVI time series data, Rabi, Maximum Likelihood (ML) algorithm.

Date of Online: 30 Sep 2014