An improved semiautomatic segmentation approach to land cover mapping for identification of land cover change and trend

Abstract

Worldwide, land cover change is monitored by conventional land cover mapping techniques using satellite imagery. Index method ends with assigning positive values to indicate vegetation, wetland and built-up area. However, not all positive values up to a certain threshold specify desired land cover and might indicate other covers erroneously. Therefore, a threshold value must be determined above which land covers are mapped more accurately. In this research, we employed an improved land cover mapping technique to extract vegetation, wetland and built-up area using semiautomatic segmentation approach. We used double-window flexible pace search technique not only for built-up features but also for vegetation and wetland mapping to increase the accuracy. Study is based on Landsat Thematic Mapper images of 1989, 1999 and 2010 with spatial resolution of 30 m. Integration of simple recoding of derived index images prior to threshold identification entails increased accuracy. Accuracy assessment of land cover mapping is done using high-resolution Google Earth satellite image which substitutes expensive aerial photography and time-consuming ground data collection. Error matrix presents 82.46, 96.83 and 90 % user’s accuracy of mapping built-up area, vegetation and wetland, respectively. Trend analysis discloses an average loss of vegetation and wetland by 2,664.6 and 5,328.8 acres per year, respectively, in study area from 1989 to 2010. Expectantly, future land cover mapping in similar researches will be greatly assisted with the diligent technique used in this study.