基于改进的Hough变换ASAR图像船只尾迹自动识别算法  

Ship wake automatic identification algorithm in ASAR image based on improved Hough transform

作　　者：巩彪[1] 黄韦艮[2] 陈鹏[2] 

机构地区：[1]上海卫星工程研究所,上海200240 [2]国家海洋局第二海洋研究所卫星海洋环境动力学国家重点实验室,浙江杭州310012

出　　处：《热带海洋学报》2014年第3期33-39,共7页Journal of Tropical Oceanography

摘　　要：文章提出了一种基于改进的Hough变换先进合成孔径雷达(ASAR)图像船只尾迹自动识别算法。算法首先检测出船只并将船只部分用图像灰度均值代替,然后设定阈值修正Hough变换域中的峰值检测,再通过改进的Hough变换自动实现了船只尾迹的检测和识别,最后利用约束条件来确定尾迹的起点和终点。实验结果表明,文中算法能够自动检测到船只尾迹,并且能识别出尾迹的类型,反演出尾迹的起始点,对海洋监测和管理具有重要的意义。A ship wake automatic identification algorithm based on improved Hough Transform is proposed in this paper. First, the algorithm detects the ship and replaces the pixels’ gray value of the detected ship with the gray mean value of the image. Second, the peaks are modified in the Hough transform filed through setting a threshold. Third, ship wake detection and identification are realized automatically with improved Hough transform. Finally, it confirms the beginning and the end of the ship wake with constraint conditions. The experiment of wake detection in the advanced synthetic aperture radar image showed that the algorithm can detect ship wake, identify the kind of ship wake automatically and derive the beginning and end of the wake, which is significant for marine monitoring and management.

关 键 词：HOUGH变换 合成孔径雷达 先进合成孔径雷达图像 尾迹检测 自动识别 

分 类 号：P714.89[天文地球—海洋科学] P733.39