首页 | 期刊介绍 | 编委会 | 道德声明 | 投稿指南 | 常用下载 | 过刊浏览 | In English
引用本文:
【打印本页】   【下载PDF全文】   查看/发表评论  下载PDF阅读器  关闭
←前一篇|后一篇→ 过刊浏览    高级检索
本文已被:浏览 49次   下载   
分享到: 微信 更多
基于K-means聚类与数学形态学的侧扫声呐图像目标轮廓自动提取方法
王涛, 潘国富, 张济博
自然资源部第二海洋研究所
摘要:
针对侧扫声呐图像斑点噪声强、背景海底散射干扰严重,海底目标轮廓自动提取困难的问题,提出了一种基于K-means聚类与数学形态学相结合的海底目标轮廓自动提取算法。为克服噪声干扰,该算法首先利用中值滤波去除侧扫声呐图像中的强斑点噪声;然后采用K-means聚类算法对侧扫声呐灰度图像进行分割,并二值化,除去大部分海底背景噪声,初步提取出目标;接着利用数学形态学运算去除提取结果中的孤立噪点,并填充目标内部孔洞,得到连续化、圆滑的目标边缘;最后对处理后的侧扫声呐图像进行边缘检测,提取出目标轮廓。实验结果表明:该算法思想简单易行,具有很强的克服背景噪声的能力,自动提取的目标轮廓连续性较好,结果准确可靠。
关键词:  侧扫声呐图像  K-means聚类  数学形态学  边缘检测  自动提取
DOI:10.11759/hykx20181217001
分类号:
基金项目:国家自然科学基金项目(面上项目,重点项目,重大项目)
Automatic extracting target contour of side scan sonar image by uniting K-means clustering with mathematical morphology
wang tao, pan guofu, zhang jibo
Second Institute of Oceanography,MNR
Abstract:
Aiming at the problems of strong speckle noise and severe scattering interference of seabed background in side scan sonar images and difficulty in automatic extraction of seabed target contour, an automatic extraction algorithm of seabed target contour based on K-means clustering and mathematical morphology is proposed. Firstly, the algorithm uses median filtering to remove strong speckle noise in sonar image. Secondly, K-means clustering algorithm is used to segment the side-scan sonar image, and binarization is used to remove most of the seabed background noise and preliminary extraction of the target. Thirdly, mathematical morphology is used to remove the isolated noise in the extraction result, and the internal hole of the target is filled to obtain the continuous and smooth target edge. Finally, edge detection is performed on the processed side-scan sonar image, and the target contour is extracted. The experimental results show that the proposed algorithm is simple and easy to implement, and has a strong ability to overcome background noise. The automatic extraction of target contour has good continuity and the result is accurate and reliable.
Key words:  side scan sonar image  K-means clustering  mathematical morphology  edge detection  automatic extraction
版权所有 《海洋科学》编辑部 Copyright©2008 All Rights Reserved
主管单位:中国科学院 主办单位:中国科学院海洋研究所
地址:青岛市南海路七号  邮编:266071  电话:0532-82898755  E-mail:bjb@qdio.ac.cn
技术支持:北京勤云科技发展有限公司