合成孔径雷达图像水体目标的提取

贺飞跃; 贺兴时; 丁小丽; 刘婷婷

doi:doi:10.3969/j.issn.1671-637x.2018.11.004

电光与控制, 2018, 25 (11): 21, 网络出版: 2018-11-25

合成孔径雷达图像水体目标的提取

Extracting Water Bodies from Synthetic Aperture Radar Images

论文大纲

贺飞跃贺兴时丁小丽刘婷婷

作者单位

西安工程大学理学院, 西安 710048

合成孔径雷达水体目标提取分水岭区域生长马尔可夫随机场 synthetic aperture radar water body target extraction watershed region growing Markov random field

摘要

针对合成孔径雷达(SAR)图像水体目标的筛选和边缘模糊问题, 根据SAR图像的成像特点, 给出了一种基于区域生长和马尔可夫随机场(MRF)模型的水体目标提取方法。首先, 利用SAR图像中水体表面呈现为均匀的低强度区域特点, 采用分水岭方法进行过分割, 确定具有较大面积的区块作为水体的种子区域; 然后, 利用水体的种子区域统计特征进行区域生长, 得到初始水体目标; 最后, 利用融合观测图像局部均匀性特征的MRF模型对初始分割图像进行精确的目标提取。实验结果显示所提方法能正确地提取SAR图像中的水体目标并精确定位目标边缘。

Abstract

Aiming at the imaging characteristics of the water bodies of synthetic aperture radar images, and to solve the problem of blurred edges, a water body target extraction method based on region growing and Markov Random Field (MRF) was proposed.Firstly, considering that the water surface in SAR image is a uniform and low-intensity region, we used watershed method for segmentation, and defined the blocks with large area as the seeded region of water body.Then, region growing was carried out using the statistical characteristics of the region, and the initial water body targets were obtained.Finally, the precise water bodies were extracted from the initially segmented images by the MRF model that combines the local uniformity characteristics of observed image.The experimental results show that the proposed method can accurately extract the water body targets in SAR images and accurately locate the target edges.

参考文献

[1] 熊伟,徐永力,姚力波,等.基于频谱残差视觉显著计算的高分辨SAR图像舰船检测算法［J］.电光与控制,2018,25(4):7-11,49.

[2] 李廷元.基于稀疏表示和拉伸变换的SAR图像目标识别［J］.电光与控制,2018,25(5):50-55.

[3] 冯颖,贺兴时,薛箐箐,等.基于NSCT的SAR与可见光图像融合算法［J］.电光与控制,2018,25(3):23-27.

[4] 郭莹,贺兴时.基于混合布谷鸟算法的图像阈值分割［J］.西安工程大学学报,2017,31(1):141-146.

[5] 夏雨薇,贺飞跃,张敏,等.贝叶斯优化的RSF模型脑肿瘤图像分割新方法［J］.西安工程大学学报,2018,32(2):237-242.

[6] MAURIZIO S, URS W.Mult-temporal synthetic aperture radar metrics applied to map open water bodies［J］.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2014, 7(8):3225-3238.

[7] 安成锦,牛照东,李志军,等.典型Otsu算法阈值比较及其SAR图像水域分割性能分析［J］.电子与信息学报,2010,32(9):2215-2219.

[8] 安成锦,陈曾平.基于Otsu和改进CV模型的SAR图像水域分割算法［J］.信号处理,2011,27(2):221-225.

[9] 魏航.多源遥感图像水体信息提取方法的研究［D］.北京:北京理工大学,2016.

[10] 曹哲,张弓,戴为龙.结合二次OTSU和SIFT的光学和SAR水域图像快速配准［J］.计算机辅助设计与图形学学报,2017,29(11):1963-1970.

[11] SILVEIRA M, HELENO S.Separation between water and land in SAR images using region-based level sets［J］.IEEE Geoscience and Remote Sensing Letters, 2009, 6(3):471-475.

[12] 侯彪,胡育辉,焦李成.SAR图像水域的改进Shearlet边缘检测［J］.中国图象图形学报,2010,15(10):1549-1554.

[13] 徐川,华凤,眭海刚,等.多尺度水平集SAR影像水体自动分割方法［J］.武汉大学学报:信息科学版,2014,39(1):27-31.

[14] 蔡强,刘亚奇,曹健,等.一种基于自适应标记与区域间近邻传播聚类的分水岭图像分割算法［J］.电子学报,2017,45(8):1911-1918.

[15] 沈夏炯,吴晓洋,韩道军.分水岭分割算法研究综述［J］.计算机工程,2015,41(10):26-30.

[16] 苏腾飞,张圣微,李洪玉.基于纹理特征与区域生长的高分辨率遥感影像分割算法［J］.国土资源遥感,2017,29(2):72-81.

[17] 徐蔚波,刘颖,章浩伟.基于区域生长的图像分割研究进展［J］.北京生物医学工程,2017,36(3):317-322.

[18] 陈志国.高分辨率SAR卫星影像洪水区域提取应用研究［D］.武汉:武汉大学,2017.

[19] SASCHA K, BJORN W, SILVIA V, et al.Automatic detection of rivers in high-resolution SAR data［J］.IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2012, 5(5):1364-1368.

[20] 吴戌,叶伟.复杂场景下的SAR图像水域边缘特征提取［J］.兵器装备工程学报,2017,38(8):136-139.

[21] 贺飞跃,赵伟.含水体的合成孔径雷达图像配准［J］.光学学报,2017,37(9):295-303.

[22] LEI X G, LI Y, ZHAO N, et al.Fast segmentation approach for SAR image based on simple Markov random field［J］.Journal of Systems Engineering and Electro-nics, 2010, 21(1):31-36.

[23] 曹志民,吕秀丽,吴云,等.基于渐进核图割的SAR图像自动分割［J］.光学技术,2016,42(4):357-360,366.

贺飞跃, 贺兴时, 丁小丽, 刘婷婷. 合成孔径雷达图像水体目标的提取[J]. 电光与控制, 2018, 25(11): 21. HE Fei-yue, HE Xing-shi, DING Xiao-li, LIU Ting-ting. Extracting Water Bodies from Synthetic Aperture Radar Images[J]. Electronics Optics & Control, 2018, 25(11): 21.

合成孔径雷达图像水体目标的提取

关于本站 Cookie 的使用提示

全站搜索

合成孔径雷达图像水体目标的提取

相关论文

相关资讯

关于本站 Cookie 的使用提示

全站搜索