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

• Published in: IOP Conference Series: Earth and Environmental Science
• Main Author: Hassan N.; Hamid J.R.A.; Adnan N.A.; Jaafar M.
• Format: Conference paper
• Language: English
• Published: Institute of Physics Publishing 2014
• Online Access: https://www.scopus.com/inward/record.uri?eid=2-s2.0-84902324533&doi=10.1088%2f1755-1315%2f18%2f1%2f012017&partnerID=40&md5=bcf5a4e7e4b2249b5ebff65c4720a4bd
• ISSN: 17551307
• DOI: 10.1088/1755-1315/18/1/012017

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. © Published under licence by IOP Publishing Ltd.