SAR Oil Spill Detection System through Random Forest Classifiers
| Autor: | Jose Lopes, André Telles da Cunha Lima, Mainara Biazati Gouveia, Marcos Reinan Assis Conceição, Milton José Porsani, Luis Felipe Ferreira de Mendonça, Rodrigo Nogueira de Vasconcelos, Carlos A. D. Lentini |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Synthetic aperture radar
010504 meteorology & atmospheric sciences Computer science Feature vector Science 0211 other engineering and technologies Feature selection Terrain 02 engineering and technology 01 natural sciences feature selection Radar imaging oil spills image segmentation 021101 geological & geomatics engineering 0105 earth and related environmental sciences business.industry Pattern recognition Image segmentation Thresholding Random forest General Earth and Planetary Sciences Artificial intelligence business random forest synthetic aperture radar |
| Zdroj: | Remote Sensing, Vol 13, Iss 2044, p 2044 (2021) Remote Sensing Volume 13 Issue 11 Pages: 2044 |
| ISSN: | 2072-4292 |
| Popis: | A set of open-source routines capable of identifying possible oil-like spills based on two random forest classifiers were developed and tested with a Sentinel-1 SAR image dataset. The first random forest model is an ocean SAR image classifier where the labeling inputs were oil spills, biological films, rain cells, low wind regions, clean sea surface, ships, and terrain. The second one was a SAR image oil detector named “Radar Image Oil Spill Seeker (RIOSS)”, which classified oil-like targets. An optimized feature space to serve as input to such classification models, both in terms of variance and computational efficiency, was developed. It involved an extensive search from 42 image attribute definitions based on their correlations and classifier-based importance estimative. This number included statistics, shape, fractal geometry, texture, and gradient-based attributes. Mixed adaptive thresholding was performed to calculate some of the features studied, returning consistent dark spot segmentation results. The selected attributes were also related to the imaged phenomena’s physical aspects. This process helped us apply the attributes to a random forest, increasing our algorithm’s accuracy up to 90% and its ability to generate even more reliable results. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|