Open AccessSCS+C Topographic Correction to Enhance SVM Classification Accuracy
Author(s) -
Jwan Al-doski,
Shattri Mansor,
H`ng Paik San,
Zailani Khuzaimah
Publication year - 2020
Publication title -
journal of engineering technology and applied physics
Language(s) - English
Resource type - Journals
ISSN - 2682-8383
DOI - 10.33093/jetap.2020.x1.7
Subject(s) - terrain , remote sensing , land cover , support vector machine , mcnemar's test , radiance , topographic map (neuroanatomy) , geology , cartography , artificial intelligence , computer science , geography , land use , mathematics , psychology , statistics , civil engineering , posterior parietal cortex , engineering , cognitive psychology
The topographic impact may change the radiance values captured by the spacecraft sensors, resulting in distinct reflectance value for similar land cover classes and mischaracterization. The problem can be more clearly seen in rugged terrain landscapes than in flat terrains, such as the mountainous areas. In order to minimize topographic impacts, we suggested the implementation of Modified Sun-Canopy-Sensor Correction (SCS+C) technique to generate land cover maps in Gua Musang district which is located in a rugged mountainous terrain area in Kelantan state, Malaysia using an atmospherically corrected Landsat 8 imagery captured on 22 April 2014 by Support Vector Machine (SVM) algorithm. The results showed that the SCS+C method reduces the topographic effect particularly in such a steep and forested terrain with classification accuracy improvement about 4% which was statistically significantly with the McNemar test value Z and P measured 6.42 and 0.0001 on the corrected image classification90.1%accuracy compared to the uncorrected image86.2%for the test area. Thus, the topographic correction is suggested to be the main step of the data pre-processing stage in mountainous terrain before SVM image classification