Pixel misclassification is a common problem when satellite imagery extracts land-use and land cover classes. Accurate image classification for mangrove areas is essential for management and monitoring to preserve the mangrove ecosystem and expedite the mangrove area delineation process. Therefore, this study aims to i) identify suitable segmentation parameters value to delineate the mangrove area and ii) classify young and mature mangrove trees using the object-based classification (OBIA) approach at Tuba Island, Langkawi, Malaysia. This research applied Support Vector Machine (SVM) based on an object-based method using Sentinel-2A image and segmentation parameters value of scale, compactness, shape, and Gray Level Co-occurrence Matrix (GLCM) mean were tested. Measured tree diameter at breast height (DBH) is used to verify the mangrove tree delineated on the Sentinel-2A image. Segmentation parameters setting of shape (0.2), compactness (0.2), and scale (50) shows minimum errors with mangrove delineation 9.279% as compared to the Global Forest Watch (GFW) data while GLCM mean appropriate to determine the young and mature mangrove tree. The finding of this study will help the Department of Fisheries Malaysia and agritourism to maintain the mangrove ecosystem and enhance the fisheries industry.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.