李美霖1,,
曹旭1,,
李润林1,,
秦先祥2,
1.国防科技大学电子科学学院 长沙 410073
2.空军工程大学信息与导航学院 西安 710077
基金项目:国家自然科学基金(62071474, 41601436)
详细信息
作者简介:邹焕新(1973–),男,广东人,现任国防科技大学电子科学学院教授,硕士生导师,主要研究方向为SAR图像解译、多源信息融合、计算机视觉、图像处理、模式识别等。E-mail: hxzou2008@163.com
李美霖(1995–),女,山西人,现为国防科技大学电子科学学院博士生,主要研究方向为极化SAR图像解译、模式识别等。E-mail: limeilin@nudt.edu.cn
曹旭:曹 旭(1996–),男,天津人,现为国防科技大学电子科学学院硕士生,主要研究方向为SAR图像和光学图像目标检测分类与识别。E-mail: 1135459767@qq.com
李润林(1995–),男,新疆人,现为国防科技大学电子科学学院硕士生,主要研究方向为SAR图像和光学图像目标检测分类与识别。E-mail: lrl1995@vip.qq.com
秦先祥(1986–),男,广西人,现任空军工程大学信息与导航学院讲师,主要研究方向为SAR图像解译。E-mail: qinxianxiang@126.com
通讯作者:邹焕新 hxzou2008@163.com
责任主编:殷君君 Corresponding Editor: YIN Junjun中图分类号:TN957
计量
文章访问数:716
HTML全文浏览量:209
PDF下载量:158
被引次数:0
出版历程
收稿日期:2020-08-31
修回日期:2020-11-20
网络出版日期:2020-12-03
Superpixel Segmentation for PolSAR Images Based on Geodesic Distance
ZOU Huanxin1,,,LI Meilin1,,
CAO Xu1,,
LI Runlin1,,
QIN Xianxiang2,
1. College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China
2. School of Information and Navigation, Air Force Engineering University, Xi’an 710077, China
Funds:The National Natural Science Foundation of China (62071474, 41601436)
More Information
Corresponding author:ZOU Huanxin, hxzou2008@163.com
摘要
摘要:针对传统的极化SAR(PolSAR)图像超像素分割算法中采用的距离度量对相似性表征能力不足的问题,该文提出了一种基于测地线距离的极化SAR图像快速超像素分割算法。首先,对图像进行正六边形初始化与不稳定点初始化;其次,利用实对称Kennaugh矩阵之间的测地线距离来度量当前不稳定点与其搜索范围内其他聚类中心点之间的相似度,以便更准确地为当前不稳定点分配标签,从而快速减少不稳定点的数量;最后,利用后处理步骤消除孤立像素点以生成最终的超像素。利用仿真极化SAR数据验证了初始化方法的有效性和测地线距离度量的高效性,并利用仿真和实测数据将该文算法与其他4种算法进行对比分析。实验结果表明,该文方法生成的超像素具有更规则的形状并且能够准确地贴合真实地物边缘,同时具有更高的运算效率。
关键词:极化SAR图像/
超像素分割/
Kennaugh矩阵/
测地线距离/
正六边形
Abstract:Considering the lack of similarity capabilities of the distance metric used in the traditional Polarimetric Synthetic Aperture Radar (PolSAR) image superpixel segmentation algorithm, a novel PolSAR image superpixel segmentation algorithm based on geodesic distance is proposed in this paper. First, the PolSAR image is initialized as a hexagonal distribution, and all pixels are initialized as unstable pixels. Thereafter, the geodesic distance between two real symmetric Kennaugh matrices is used to measure the similarity between the current unstable point and another cluster point in the search region to more accurately assign labels to unstable points, thereby effectively reducing the number of unstable points. Finally, the postprocessing procedure is used to remove small, isolated regions and generate the final superpixels. To verify the effectiveness of the initialization method and the high efficiency of the geodesic distance, extensive experiments are conducted using simulated PolSAR images. Moreover, the proposed algorithm is analyzed and compared with four other algorithms using simulated and real-world images. Experimental results show that the superpixels generated using the proposed method exhibit higher computational efficiency and a more regular shape that can more accurately fit the edges of real objects compared with those using the four other algorithms.
Key words:PolSAR image/
Superpixel segmentation/
Kennaugh matrix/
Geodesic distance/
Hexagon
PDF全文下载地址:
https://plugin.sowise.cn/viewpdf/198_e294edb3-7389-422a-b78a-9e15e9d49a20_R20121