LU/LC Change Detection Using NDVI & MLC Through Remote Sensing and GIS for Kadapa Region
This research letter considered land use/land cover (LU/LC) changes in Kadapa region from 2001 to 2016 by using GIS (Geographical Information Systems) LANDSAT 7 and 8 images level-1 data of ETM+ sensor were collected for the years 2001 and 2016 to estimate the NDVI values. Based on index values study area is classified into five classes like water bodies, built-up area, barren land, sparse vegetation and dense vegetation. The proposed method performs two-stage classification. From the results it is observed that, increase in barren land of 6.23%, built-up area of 24.74% and decrease of water resources of 2.87%, sparse vegetation of 2.62% and dense vegetation/forest land of 25.47% in the Kadapa region. Finally, the classification algorithm was assessed by the confusion matrix method. As NDVI is used basis for classification process vegetation and water resources classification is 100% and 86% built up and barren lands are classification, i.e., some of built-up areas classified as barren land and barren land as built-up area. Compared to existing classification algorithms based on Principal Component Analysis (PCA) and False Color Composite (FCC) the proposed NDVI histogram and Maximum Likelihood Classifier (MLC) multiple classification gives the best results to estimate the change detection. The work was carried out by using ArcGIS software.
KeywordsNormalized Difference Vegetation Index (NDVI) Maximum Likelihood Classifier (MLC) Change detection Remote sensing GIS Multispectral image
Authors would like to thank USGS Earth Explorer for providing LANDSAT images to carry out the present research work.
- 1.Das, K.: NDVI and NDWI based change detection analysis of Bordoibam Beelmukh Wetlandscape, Assam using IRS LISS III data. ADBU-J. Eng. Technol. 6(2), 17–21 (2017). ISSN: 2348-7305Google Scholar
- 2.Xue, J., Su, B.: Significant remote sensing vegetation indices: a review of developments and applications. J. Sensors 2017, Article Id 1353691 (Hindawi) (2017)Google Scholar
- 3.Taufik, A., Ahmad, S.S.S., Ahmad, A.: Classification of LANDSAT 8 satellite data using NDVI thresholds. J. Telecommun. Electron. Comput. Eng. 8(4), 37–40 (2016). ISSN: 2180-1843 e-ISSN: 2289-8131Google Scholar
- 4.Jeevalakshmi, D., Narayana Reddy, S., Manikiam, B.: Land cover classification based on NDVI using LANDSAT 8 time series: a case study Tirupati region. In: International Conference on Communication and Signal Processsing (ICCSP) (2016)Google Scholar
- 6.Mallupattu, P.K., Reddy, J., Reddy, S.: Analysis of land use/land cover changes using remote sensing data and GIS at an urban area, Tirupati, India. Sci. World J. (Hindawi Publishing corporation) (2013)Google Scholar
- 7.Bhandari, A.K., Kumar, A., Singh, G.K.: Feature extraction using normalized difference vegetation index (NDVI): a case study of Jabalpur city. In: 2nd International Conference on Communication. Computing and Security [ICCCS-2012], Procedia Technol. 6, 612–621 (Elsevier) (2012)Google Scholar
- 8.Hayes, D.J., Sader, S.A.: Comparison of change detection techniques for monitoring tropical forest clearing and vegetation regrowth in a time series. Photogramm. Eng. Remote Sens. 67, 1067–1075 (2001)Google Scholar
- 10.Singh, A.: Digital change detection techniques using remotely sensed data. Int. J. Remote Sens. 10, 989–1003 (1989)Google Scholar