Hierarchical image classification threshold on mangrove

• Main Author: Mohd, Othman
• Format: Thesis
• Language: English; English
• Published: 2015
• Subjects: T Technology (General); TA Engineering (General). Civil engineering (General)
• Online Access: http://eprints.utem.edu.my/id/eprint/16773/1/Hierarchical%20Image%20Classification%20Threshold%20On%20Mangrove.pdf; http://eprints.utem.edu.my/id/eprint/16773/2/Hierarchical%20image%20classification%20threshold%20on%20mangrove.pdf; http://eprints.utem.edu.my/id/eprint/16773/; https://plh.utem.edu.my/cgi-bin/koha/opac-detail.pl?biblionumber=96200

Mangrove area is an important coastal ecosystem in a tropical region. Managing mangrove is challenging and complex. In order to balance between protection the ecosystem and providing the natural resources that benefits to human being. In addition traditional classification and identification of mangrove tree species require an expert inspector working manually. A demand for accurate and automatic of mangrove species estimation has arose especially for ecological, environmental and economical values. Economically, the knowledge of tree species information is important. In order to meet the mangrove forest planning requirements, the satellite remote sensing with high spatial resolution has been specifically designed for tree species classification to improve accuracy and able to locate preferred tree species. However the main issue in remote sensing is image classification that required to determine an appropriate threshold between species in producing accurate classification map. An image classification on satellite imagery is a complex process and requires consideration of accurate classification system. A pixel in the satellite image may possibly cover more than one object on the ground. A threshold has to be set to classify an overlap of two or more associated spectral properties. Therefore the aim of this study is to determine the optimal threshold value for object classes to ensure the misclassification of image pixels kept as low as possible by analyzing the classification of satellite images at different hierarchical level. Then the optimal threshold will be proposed on satellite image classification for mangrove species with the help of expert inspector from the ground. An evaluation on the accuracy of the proposed threshold value in identifying mangrove shall be made. A hierarchical threshold is expected to significant improvement result on an image classification final map for mangrove species.