Oil Spill Detection Based on Multiscale Multidimensional Residual CNN for Optical Remote Sensing Imagery
Seyd Teymoor Seydi, Mahdi Hasanlou, Meisam Amani, Weimin Huang
Abstract
Oil Spill (OS), as one of the main pollutions in the ocean, is a serious threat to the marine environment. Thus, timely and accurate OS Detection (OSD) is necessary for ocean management. In this regard, Remote Sensing (RS) plays a key role due to multiple advantages over large and remote ocean environments. In this study, a new OSD framework based on a deep learning algorithm was developed for optical RS imagery. The proposed method was based on a multi-Scale multi-dimensional residual kernel Convolution Neural Network (CNN). The proposed method investigated the deep features by the two-dimensional (2D) multi-scale residual blocks and, then, utilized them at one-dimensional (1D) multi-scale residual blocks. In this study, Landsat-5 satellite imagery acquired over the Gulf of Mexico was applied to evaluate the performance of the proposed method. The Overall Accuracy (OA) of the proposed method was more than 95%, and the Miss Detection (MD) and False Alarm (FA) rates were less than 5%, indicating its high potential for OSD. Moreover, it was observed that the proposed method had better performance compared to other OSD algorithms that were investigated in this study.