Oil spill detection using GLCM and MRF

This paper presents a study for oil spill detection in three steps. The first one considers the texture as a two dimensions array, and to describe the statistics iteration between pixels the algorithm computes a textural feature related with the Gray Level Co-occurrence Matrix (GLCM). After, the original image and the textural feature images are segmented using Markov Random Field (MRF). Each pixel can be classified in two classes: {oil, not-oil}. To determine the class we optimized the a posteriori energy function by means of simulated annealing. The segmentation result contains different levels of information, in order to improve the oil spill detection; we propose a data fusion stage. The result obtained is binary and shows in detail the oil spill in the analysis zone.