Extraction of Shrimp Ponds Using Object Oriented Classification vis-a- vis Pixel Based Classification

摘要

Rapid expansion of coastal aquaculture/shrimp farming in several countries has necessitated the inventory and monitoring of shrimp farms. These are essential tools for decision making with regard to aquaculture development, including regulatory laws, environmental protection, and revenue collection. In the context of aquaculture development policies of respective governments, much attention is focused on the identification and classification of shrimp farms, which are often located in remote areas. This study examines the classification of shrimp farms using pan sharpened IRS LISS-III images of the Kandleru creek area of Andhra Pradesh, India. IRS satellite images are subjected to pixel- based classification versus object-oriented classification for improving the identification of shrimp farms in the area.