Please use this identifier to cite or link to this item:
|Title:||A new technique for seasonal land-cover change analysis using directional brightness differencing||Contributor(s):||Sinha, Priyakant (author); Kumar, Lalit (author)||Publication Date:||2012||Open Access:||Yes||Handle Link:||https://hdl.handle.net/1959.11/10759||Open Access Link:||http://dl6.globalstf.org/index.php/jet/article/view/728||Abstract:||Due to seasonal spectral variability in land-cover of cool temperate climatic conditions, the method that suits best for seasonal land-cover change identification remains uncertain. The study tested 11 different binary change detection methods and compared their capability in detecting land-cover change/no-change information in different seasons. Multi-date Thematic Mapper (TM) data pertaining to different seasons were used for a wide set of change image generation. A relatively new approach was applied for optimal threshold value determination for separation of change/no-change areas. Research indicated that irrespective of the method used, the results using vegetation index change images, particularly Normalized Difference Vegetation Index (NDVI)-based change images outperformed all other tested techniques in change detection process (overall accuracy> 90% and Kappa value> 0.85 for all six change periods).||Publication Type:||Journal Article||Source of Publication:||The GSTF Journal of Engineering Technology, 1(1), p. 61-66||Publisher:||Global Science and Technology Forum (GSTF)||Place of Publication:||Singapore||ISSN:||2251-3701
|Field of Research (FOR):||090905 Photogrammetry and Remote Sensing||Socio-Economic Objective (SEO):||960504 Ecosystem Assessment and Management of Farmland, Arable Cropland and Permanent Cropland Environments||Peer Reviewed:||Yes||HERDC Category Description:||C1 Refereed Article in a Scholarly Journal||Statistics to Oct 2018:||Visitors: 171
|Appears in Collections:||Journal Article|
School of Environmental and Rural Science
Files in This Item:
checked on Mar 3, 2019
Items in Research UNE are protected by copyright, with all rights reserved, unless otherwise indicated.