(SEMI AUTOMATION BUILDING AREA EXTRACTION USING HIGH RESOLUTION AERIAL PHOTO USING TRANSFERABLE GEOSPASIAL OBJECT BASED IMAGE ANALYSIS (GEOBIA) RULESET)

Abstract

Residential area diversity became a challenge in building area information extraction especially when associated with the extensive space of residential areas formed in Indonesia. Using high resolution RGB aerial photographs with nDSM height data support, transferable GEOBIA developed to overcome the challenges and problems. Master rulesets arranged in the main area and applied to several test areas to compliment the characteristics as well as the stability of accuracy that can be produced. Segmentation and classification multilevel technique adapted in master ruleset to achieve best results with the lightest processing load. Transferable GEOBIA ruleset proved to provide accurate information of reliable building area on various characteristics of residential area. In the main area, the accuracy value reaches 91.25% while in other test areas the accuracy exceeds 85% which is 92.22%, 86.19% and 92.73%.