Key Laboratory of Marine Environment and Ecology, Ministry of Education of China, Ocean University of China, Qingdao 266100, China; CNOOC Energy Technology & Services Limited, Safety & Environmental Protection Branch, Tianjin 300450, China; School of Hydraulic Engineering, Ludong University, Yantai, China.
CNOOC Energy Technology & Services Limited, Safety & Environmental Protection Branch, Tianjin 300450, China.
Mar Pollut Bull. 2022 Jul;180:113795. doi: 10.1016/j.marpolbul.2022.113795. Epub 2022 Jun 9.
Sunken oil incidents have occurred multiple times in the Bohai Sea over the past ten years. Currently, quick and effective sunken oil detection and classification remains a difficult problem. In this study, sonar detection experiments are conducted to obtain acoustic image samples using a multibeam echosounder (MBES) in a large seawater tank at the bottom of the area where the sunken oil is located. A series of MBES data corrections are constructed to generate backscatter strength images that can reflect the target characteristics directly. Meanwhile, eight-dimensional features are extracted, and a support vector machine (SVM) classification framework is built to classify the sunken oil and other interference targets. The results indicate that the MBES backscatter images provide an alternative approach for detecting and classifying sunken oil. The overall target classification accuracy reaches 88.5% by the SVM algorithm. Thus, this study provides a basis for further investigation of detecting sunken oil.
过去十年，渤海发生了多次溢油事故。目前，快速有效地检测和分类溢油仍然是一个难题。本研究利用位于溢油区域海底的大型水槽中的多波束回声探测仪（MBES）进行声纳探测实验，获取声学图像样本。构建了一系列 MBES 数据校正，以生成可直接反映目标特征的反向散射强度图像。同时，提取了 8 维特征，并建立了支持向量机（SVM）分类框架来对溢油和其他干扰目标进行分类。结果表明，MBES 反向散射图像为检测和分类溢油提供了一种替代方法。SVM 算法的总体目标分类准确率达到 88.5%。因此，本研究为进一步研究检测溢油提供了依据。
