当前位置: X-MOL 学术J. Mar. Sci. Eng. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Oil Spill Detection Using LBP Feature and K-Means Clustering in Shipborne Radar Image
Journal of Marine Science and Engineering ( IF 2.7 ) Pub Date : 2021-01-10 , DOI: 10.3390/jmse9010065
Jin Xu , Xinxiang Pan , Baozhu Jia , Xuerui Wu , Peng Liu , Bo Li

Oil spill accidents have seriously harmed the marine environment. Effective oil spill monitoring can provide strong scientific and technological support for emergency response of law enforcement departments. Shipborne radar can be used to monitor oil spills immediately after the accident. In this paper, the original shipborne radar image collected by the teaching-practice ship Yukun of Dalian Maritime University during the oil spill accident of Dalian on 16 July 2010 was taken as the research data, and an oil spill detection method was proposed by using LBP texture feature and K-means algorithm. First, Laplacian operator, Otsu algorithm, and mean filter were used to suppress the co-frequency interference noises and high brightness pixels. Then the gray intensity correction matrix was used to reduce image nonuniformity. Next, using LBP texture feature and K-means clustering algorithm, the effective oil spill regions were extracted. Finally, the adaptive threshold was applied to identify the oil films. This method can automatically detect oil spills in shipborne radar image. It can provide a guarantee for real-time monitoring of oil spill accidents.

中文翻译:

基于LBP特征和K均值聚类的舰载雷达图像溢油检测

漏油事故严重损害了海洋环境。有效的漏油监测可以为执法部门的应急响应提供有力的科学技术支持。事故发生后,可立即使用船载雷达监视溢油情况。本文是由教学实习船Yukun收集的原始舰载雷达图像以2010年7月16日大连发生漏油事故为例的大连海事大学为研究数据,提出了一种基于LBP纹理特征和K-means算法的漏油检测方法。首先,使用拉普拉斯算子,Otsu算法和均值滤波器来抑制同频干扰噪声和高亮度像素。然后使用灰度强度校正矩阵来减少图像不均匀性。接下来,使用LBP纹理特征和K-means聚类算法,提取有效的溢油区域。最后,将自适应阈值应用于识别油膜。该方法可以自动检测船载雷达图像中的溢油。它可以为漏油事故的实时监控提供保证。
更新日期:2021-01-10
down
wechat
bug