Delineation of wetland areas from high resolution WorldView-2 data by object-based method

8th International Symposium of the Digital Earth

地球科学;计算机科学

Hassan, N.^1 ; Hamid, J.R.A.^1 ; Adnan, N.A.^1 ; Jaafar, M.^1

Centre of Studies Surveying Science and Geomatics, Faculty of Architecture, Planning and Surveying, Universiti Teknologi MARA, 40450 Shah Alam, Malaysia^1

关键词: Classification methods;    Classification technique;    High resolution satellites;    Imaging sensor system;    Land cover classification;    Object-based analysis;    Object-based methods;    Spatial resolution;   

Others  :  https://iopscience.iop.org/article/10.1088/1755-1315/18/1/012017/pdf
DOI  :  10.1088/1755-1315/18/1/012017

学科分类：计算机科学（综合）

来源: IOP

【 摘 要 】

Various classification methods are available that can be used to delineate land cover types. Object-based is one of such methods for delineating the land cover from satellite imageries. This paper focuses on the digital image processing aspects of discriminating wetland areas via object-based method using high resolution satellite multispectral WorldView-2 image data taken over part of Penang Island region. This research is an attempt to improve the wetland area delineation in conjunction with a range of classification techniques which can be applied to satellite data with high spatial and spectral resolution such as World View 2. The intent is to determine a suitable approach to delineate and map these wetland areas more appropriately. There are common parameters to take into account that are pivotal in object-based method which are the spatial resolution and the range of spectral channels of the imaging sensor system. The preliminary results of the study showed object-based analysis is capable of delineating wetland region of interest with an accuracy that is acceptable to the required tolerance for land cover classification.