Comparative Analysis of Object-Based and Pixel-Based Classification of High Resolution Remote Sensing Images for Mapping Coral Reef Geomorphic Zones : A Case Study in Karimunjawa
M LUTFI MA (a), Gatot Winarso (b)
(a) Informatic Management Department,
STMIK Bina Patria
(b) Remote Sensing Application Center, National Institute of Aeronautics and Space
(LAPAN)
Abstract
Coral reefs ecosystem have great value in terms of economy, culture, and biology for the global society and the most productive and diverse biological ecosystem in the world (Wilkinson, 2001). Earth observation from space so called remote sensing technology by using high-resolution Satellite, offers powerful capabilities for understanding, forecasting, managing, monitoring and decision making about coral reefs ecosystem. This study focuses on the comparison analisys between Object Base and Pixel Base image classifications of remote sensing imagery for Mapping Coral Reef Geomorphic Zones in the Karimunjawa National Park. The accuracy of each method was assessed using reference data sets derived from high-resolution satellite images, aerial photograph and field investigation. The accuracy of geomorphology zone mapping used Object Base Classification technique indicates that the overall accuracy (OA) was 88,62%. while the pixel-based classification produce the low overall accuracy was 73%. This research suggest that the object-based technique could be a promise approach for mapping coral reef geomorphic zones, where the information obtained from this research was more accurate. In paper, we observed that the object-based technique shows higher accuracy in classification process than the pixel-based technique because pixel based can-t satisfy the high resolution satellite data properties and it produced data redundancy.
Keywords: Remote Sensing, OBIA, Pixel Base Classification, Object Base Classification, Karimunjawa, Coral Reefs, World View-2 Satellite
Topic: Information Engineering