欢迎访问《图学学报》 分享到:

图学学报

• 视觉与图像 • 上一篇    下一篇

基于NSST 和改进数学形态学的遥感图像目标边缘提取

  

  1. 1. 南京航空航天大学电子信息工程学院,江苏 南京 211106;
    2. 浙江大学CAD&CG 国家重点实验室,浙江 杭州 310058;
    3. 城市空间信息工程北京市重点实验室,北京 100038;
    4. 南京水利科学研究院港口航道泥沙工程交通行业重点实验室,江苏 南京 210024;
    5. 黄河水利委员会黄河水利科学研究院水利部黄河泥沙重点实验室,河南 郑州 450003;
    6. 哈尔滨工业大学城市水资源与水环境国家重点实验室,黑龙江 哈尔滨 150090
  • 出版日期:2017-08-31 发布日期:2017-08-10
  • 基金资助:
    国家自然科学基金项目(61573183);CAD&CG国家重点实验室开放基金项目(A1519);城市空间信息工程北京市重点实验室开放基金项目
    (2014203);港口航道泥沙工程交通行业重点实验室开放基金项目;水利部黄河泥沙重点实验室开放基金项目(2014006);城市水资源与水
    环境国家重点实验室开放基金项目(LYPK201304);江苏高校优势学科建设工程资助项目

Target Edge Extraction of Remote Sensing Images Based on Non-Subsampled Shearlet Transform and Improved Mathematical Morphology

  1. 1. College of Electronic and Information Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing Jiangsu 211106, China;
    2. State Key Laboratory of CAD&CG, Zhejiang University, Hangzhou Zhejiang 310058, China;
    3. Beijing Key Laboratory of Urban Spatial Information Engineering, Beijing 100038, China;
    4. Key Laboratory of Port, Waterway and Sedimentation Engineering of the Ministry of Transport, Nanjing Hydraulic Research Institute,
    Nanjing Jiangsu 210024, China;
    5. Key Laboratory of the Yellow River Sediment of Ministry of Water Resource, Yellow River Institute of Hydraulic Research,
    Yellow River Water Resources Commission, Zhengzhou Henan 450003, China;
    6. State Key Laboratory of Urban Water Resource Environment, Harbin Institute of Technology, Harbin Heilongjiang 150090, China
  • Online:2017-08-31 Published:2017-08-10

摘要: 为了从遥感图像中提取出更为准确完整的目标边缘,提出一种基于无下采样
Shearlet 模极大值和改进数学形态学的目标边缘提取方法。首先采用无下采样Shearlet 变换
(NSST)将图像分解成边缘细节丰富的高频分量和边缘细节较少的低频分量;然后结合不同分解
程度下边缘像素点处的系数关系,对高频分量的各个子带进行模极大值检测,再经过双层掩膜
筛选后得到高频边缘提取结果;对低频分量采用改进的数学形态学方法,得到低频边缘提取结
果;最后将上述两部分融合,使用区域连通方法去除孤立点,得到最终的目标边缘图像。大量
实验结果表明,与Canny 以及其他4 种同类边缘提取方法相比,本文方法所得边缘定位准确、
完整清晰、细节丰富,且抗噪能力强,为后续遥感图像目标特征提取与识别奠定更好基础。

关键词: 目标边缘提取, 遥感图像, 无下采样Shearlet 变换, 数学形态学, 区域连通

Abstract: In order to extract edges of target area more completely and accurately from remote sensing
images, a method of target edge extraction is proposed based on improved mathematical morphology
and modulus maxima of non-subsampled Shearlet transform. Firstly, the image is decomposed into
high-frequency components with more edges and details and low-frequency component with fewer
edges and minutiae through non-subsampled Shearlet transform. Then considering the property of
coefficients of edge points under different decomposing conditions, the modulus maximum detection is
performed for each sub-band of high-frequency components and the double-layer mask is adopted
afterwards so as to get the high-frequency edge extraction result. Moreover, the low-frequency
component is processed through the improved mathematical morphology method to get the
low-frequency edge extraction result. Finally, the above two parts are fused and the final target edge
image is obtained after removing the isolated points according to the regional connectivity. A large
number of experimental results show that, compared with Canny method and four similar edge
extraction methods, the detected edges by the proposed method are accurate, clear, complete and with
abundant details. The method has strong anti-noise performance, which lays a better foundation for the
following target feature extraction and recognition of remote sensing images.

Key words: target edge extraction, remote sensing images, non-subsampled Shearlet transform;
mathematical morphology,
regional connectivity