Development of Hybrid Unsupervised Classification Techniques for Accuracy Enhancement of Land Use/Land Cover Mapping Using Geo-spatial Technology: Hoshangabad, District Madhya Pradesh, India

Ahirwar R^1*, Malik MS¹and Shukla JP²

¹Academy of Scientific and Innovative Research (AcSIR), CSIR-Institute, CSIR-Advanced Materials and Processes Research Institute, Bhopal, India

²CCSIR-Institute, CSIR-Advanced Materials and Processes Research Institute, Bhopal, India

*Corresponding Author : Ahirwar R
Academy of Scientific and Innovative Research (AcSIR), CSIR-Institute, CSIR-Advanced Materials and Processes Research Institute, Bhopal, India
Tel: +91-968-526-3511
E-mail: gis07rakesh@gmail.com

Received: March 30, 2018 Accepted: June 12, 2018 Published: June 19, 2018

Citation: Ahirwar R, Malik MS, Shukla JP (2018) Development of Hybrid Unsupervised Classification Techniques for Accuracy enhancement of Land Use/Land Cover Mapping Using Geo-spatial Technology: Hoshangabad, District Madhya Pradesh India. Geoinfor Geostat: An Overview 6:3. doi: 10.4172/2327-4581.1000186

A Hybrid approach of Land-use/land-cover (LU/LC) classification has been carried out in the study using Resource Sat-2 LISS-III Satellite data having a resolution of 23.5 m. With the help of ERDAS Imagine image processing software, unsupervised classification process of the satellite image has been made to obtain the required land use/land cover classes. During the classification study, a common mixed class assigned as Common Observed Classes (COC) used for the separation of the required classes to obtain undefined mixed land use/land cover classes with the help of ArcGIS model plate tool. Furthermore, more accuracy gained in
the classification of separated mixed land cover classes by revising unsupervised classification processes. After that pre-defined unsupervised land cover classes and COC unsupervised classes were merged by using ArcGIS model plate tool to generate a new classified image with enhanced accuracy. Finally, the comparison between both supervised and COC hybrid unsupervised classes was made and better results are seen in hybrid unsupervised classification. Therefore, application of this new approach in land use/land cover studies, ground cover mapping, forest management, water resources management, sustainable urban development, agricultural studies, natural resources management and manmade resources development management planning change deduction etc. will provide better results as compared to other classification approaches techniques.