遥感图像污染监测分析的Grab-Cut算法实现  

Implementation of the Grab-Cut Algorithm for Monitoring and Analyzing Marine Sewage in the Bohai Bay with Remote Sensing Images

作　　者：宋占杰 汤杨[1] 王兵振 张东亮[3] 田震[3] 

机构地区：[1]天津大学数学学院,天津300354 [2]天津大学电视与图像信息研究所,天津300072 [3]国家海洋技术中心,天津300112

出　　处：《海洋技术学报》2017年第6期16-21,共6页Journal of Ocean Technology

基　　金：国家自然科学基金资助项目(61379014);天津自然科学基金资助项目(16JCYBJC15900)

摘　　要：长期以来,监测天津市附近渤海湾的污染状况,数据获取均依靠人力租船进行,此方法耗时费力。文中主要利用美国卫星遥感图像,借助改进的Grab-Cut图像分割算法分析天津市附近渤海湾的污染情况变化,结果表明近3年海洋污染状况严重,但天津市附近3个重要的排污口的排污情况近1年已得到明显的改善。此外,文中将改进的Grab-Cut算法与其它一些常见的图像分割算法的分割效果进行比对,结果显示改进的Grab-Cut算法在很少的用户标记下能够很快分割出目标区域,是分割效果最好的方法之一。For a long period of time, obtaining data by monitoring the pollution status of the Bohai Bay near Tianjin depends mainly on human chartering. However, this method is time-consuming and labor-intensive. In this paper, the improved Grab-Cut image segmentation algorithm is used to analyze the pollution situation in the Bohai Bay near Tianjin with the US satellite remote sensing images. The conclusion is that the situation of marine sewage in recent three years is severe, fortunately, three important sewage outlets of which has been significantly improved in the past year. In addition, this paper compares the improved Grab-Cut algorithm with other common segmentation algorithms. The results show that the improved Grab-Cut algorithm is superior to the others in segmenting object zone with less user interaction.

关 键 词：海洋污染 遥感图像 Grab-Cut算法 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置]