CBENet: contextual and boundary-enhanced network for oil spill detection via microwave remote sensing

Από RemoteSensing Wiki

Article title: "CBENet: contextual and boundary-enhanced network for oil spill detection via microwave remote sensing"
Authors: Mengmeng Di , Xinnan Di , Huiyao Xiao , Ying Gao and Yongqing Li
Source: https://doi.org/10.1007/s44295-025-00056-5
Date: 27 February 2025

Summary and Introduction

Oil spills can be a major issue in marine environments, which is why it is important to be able to detect them early. Detection typically entails the use of microwave remote sensing images, specifically synthetic aperture radar (SAR). This technique uses radar pulses from aircraft and can identify oil spills with high-resolution imagery, nonstop, and is resistant to weather conditions such as precipitation and fog. SAR is often paired with deep learning models to increase its effectiveness. The researchers listed various models that were tested in previous studies, as well as the issues they overcame. Some of the technologies they mentioned are deep convolutional neural networks (DCNNs), U-shaped networks, multiscale conditional adversarial network (MCAN), generative adversarial networks (GANs), and many other models and methodologies for detecting oil spills. This paper created a contextual and boundary-enhanced network (CBENet) to analyze the SAR images. The goal of this technique is to address certain issues regarding the quality of the SAR images. For example, the images don’t identify oil spills well at varied scales. Additionally, boundaries of the spills are often blurry, affecting the accuracy of detecting them. The paper finds that CBENet is an effective technique and was validated via various qualitative and quantitative evaluations.
Methods

CBENet was developed as an encoder-decoder architecture. What this means is that an encoder takes apart spatial features from the oil spill image while simultaneously learning and understanding them. The decoder has a similar architecture to the encoder and takes the fused contextual features and produces a detection result as an oil spill image. The general idea of how this architecture works is shown in Figure 1. Between the encoder and decoder is the contextual fusion model which is a vital connection. Essentially this takes the inputs from the encoder and is able to provide “context” to the features extracted. This doesn’t only look at individual pixels but rather are larger areas simultaneously. The fused contextual features are then given to the decoder.

The following section highlights the formulations used to train CBENet. “Lbe” was defined as the boundary-enchanced loss function, which ensures higher accuracy when detecting the boundaries of an oil spill. It combines two parameters: pixel-level loss values, which is the error of all pixels in the image, and boundary-level loss values, which computes errors of the pixels on the border of the spill. CBENet is effective for three reasons, the first being that it can create a multiscale representation of oil spill features. The second is that the architecture enhances the fusion of contextual features. Lastly, detection becomes more accurate when the boundary-enhanced loss function is included.