Detecting Marine Oil Spill Pollution Based on Borda Count Method of Ocean Water Surface Image

摘要

When marine oil spilled in the ocean, it initially spreads in the water and primary on the surface. This paper proposes an approach of distinguishing oil spill from clean water based on using the Borda count method. First already known aerial remote sensing images are annotated and corresponding texture features are extracted. Secondly, the mapping from the feature data to raw sensing image data are built in the database; Finally, features of suspicious patches are matched with those features in the database, and Borda count method is employed to determine whether it is a real oil spill patch or not. The efficiency of the algorithm is demonstrated by a preliminary experiment with 278 training patches and 112 testing patches.