Osdes_net: oil spill detection based on efficient_shuffle network using synthetic aperture radar imagery
Nastaran Aghaei, Gholamreza Akbarizadeh, Abdolnabi Kosarian
Abstract
Synthetic Aperture Radar (SAR) imagery can be beneficial for segmenting oil spills, which are a common environmental hazard. Oil spill detection in SAR imagery faces several challenges, including speckle noise, heterogeneous backgrounds, blurred edges, and a lack of comprehensive datasets with multiple images. ShuffleNet is one of the deep networks, which has never been used for oil spill segmentation. In this article, ShuffleNet blocks are used to detect oil spills in SAR images, which is more effective than other methods. Besides, the main network design, six other blocks were evaluated, and the most valuable one was selected. We use group convolutions, shuffle channels, and atrous convolutions in this model with a minimum number of layers of ReLU. The methods are evaluated based on the Intersection Over Union (IoU) parameter so that the proposed method improved the mIoU by 7.1% over the best results of some previous methods.