Citation

AL-Doski, Jwan and Mansor, Shattri and H'ng, Paik San and Khuzaimah, Zailani (2020) SCS+C Topographic Correction to Enhance SVM Classification Accuracy. Journal of Engineering Technology and Applied Physics, 2. pp. 32-37. ISSN 26828383

Text 296 - Published Version Restricted to Repository staff only Download (2kB)

Abstract

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 classification 90.1 % accuracy compared to the uncorrected image 86.2 % 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.

Item Type:	Article
Uncontrolled Keywords:	Support Vector Machine, modified Sun-Canopy-Sensor Correction (SCS C) Technique, land cover, landsat 8 imagery
Subjects:	G Geography. Anthropology. Recreation > GB Physical geography (General) > GB3-5030 Physical geography > GB400-649 Geomorphology. Landforms. Terrain T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK7800-8360 Electronics > TK7871 Electronics--Materials
Divisions:	Others
Depositing User:	Mr. MUHAMMAD AZRUL MOSRI
Date Deposited:	18 Jul 2024 03:03
Last Modified:	18 Jul 2024 03:03
URII:	http://shdl.mmu.edu.my/id/eprint/12662

Downloads

Edit (login required)