Open    Access



Land Use and Land Cover Mapping Based on Band Ratioing with Subpixel Classification by Support Vector Machine Techniques (A Case Study on Ngamoeyeik Dam Area, Yangon Region)



Author(s)

Khin Mar Yee, Khine Phoo Wai, Bak Jinhyung and Choi Chul Uong

Full-Text PDF XML     1020 Views

DOI:10.17265/2328-2193/2015.03.002

Making map of LULC (Land Use and Land Cover) is crucially important for the sustainable development of the environment. However, the exactly data on how environmental factors influence the LULC situation at the various scales because the nature of the natural environment is naturally composed of non-homogeneous surface features, so the features in the satellite data also have the mixed pixels. Band ratioing with subpixel classification is an enhancement process in which the digital number value of one band is divided by that of any other band in the sensor array. The main objective of this study is to increase classification accuracy of LULC mapping based on band ratioing with subpixel classification by Support Vector Machines (SVMs). This process was applied with a soft approach at allocation as well as at a testing stage and to minimize the shadow and the topographic effects. The result shows the overall accuracy is increased from 61.18% of without band ratioing to 90.35% of band ratioing. The error matrix and confidence limits led to the validation of the result for LULC mapping.

Band ratioing, Support Vector Machines, change detection.