SAR海冰图像分割研究.pdf

第 39 卷第 2 期 2017 年 3 月 Vol.39 No.2 Journal of Tangshan Normal University Mar. 2017 计算机科学与自动化技术 SAR 海冰图像分割研究 1,2 3 1 赵庆平 ，于力刚 ，朱 芳 （1. 淮北师范大学 物理与电子信息学院，安徽 淮北 235000 ；2. 淮北师范大学 信息学院，安徽 淮北 235000 ； 3. 淮北师范大学 实验室与设备管理处，安徽 淮北 235000 ） 摘 要：海冰绘图对理解极地气候系统和在冬季船舶安全导航是必不可少的。由于采集的合成孔径雷达数 据量很大，期望能利用计算机对数据自动分割。探讨了基于阈值和非监督的分割方法以及SAR 海冰图像分割的 分割评价标准，指出了SAR 海冰图像分割今后的研究方向。 关键词：SAR；分割；海冰；评价标准 TP751.1 A 1009-9115(2017)02-0049-04 中图分类号： 文献标识码： 文章编号： DOI ：10.3969/j.issn.1009-9115.2017.02.015 Research on Segmentation of SAR Sea Ice Image 1,2 3 1 ZHAO Qing-ping , YU Li-gang , ZHU Fang (1. School of Physics and Electronic Information, Huaibei Normal University, Huaibei 235000, China; 2. Information College, Huaibei Normal University, Huaibei 235000, China; 3. Laboratory Equipment Management Department, Huaibei Normal University, Huaibei 235000, China) Abstract: Sea ice mapping is essential for understanding of the polar climate system and for the safety of ships navigating in winter. Due to the acquisition of a large amount of synthetic aperture radar data, computer automatic segmentation is expected. In this paper, we introduce a threshold segmentation and unsupervised segmentation method as well as SAR sea ice image segmentation evaluation criteria, and finally point out the research direction of SAR sea ice image segmentation. Key Words: SAR; segmentation; sea ice