此页面上的内容需要较新版本的 Adobe Flash Player。

获取 Adobe Flash Player

Edge detection method for remote sensing image based on morphological variable structuring element


YAO Li-juan,WANG Xiao-peng,WANG Wei, MA Wen-gang


School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China)


 

Abstract: There are problems such as incomplete edges and poor noise suppression when a single fixed morphological structuring element is used to detect the edges in remote sensing images. For this reason, a morphological edge detection method for remote sensing image based on variable structuring element is proposed. Firstly, the structuring elements with different scales and multiple directions are constructed according to the diversity of remote sensing imagery targets. In order to suppress the noise of the target background and highlight the edge of the image target in the remote sensing image by adaptive Top-hat and Bottom-hat transform, the corresponding adaptive morphological operations are constructed based on variable structuring elements; Secondly, adaptive morphological edge detection is used to obtain multiple images with different scales and directional edge features; Finally, the image edges are obtained by weighted summation of each direction edge, and then the least square is used to fit the edges for accurate location of the edge contour of the target. The experimental results show that the proposed method not only can detect the complete edge of remote sensing image, but also has high edge detection accuracy and superior anti-noise performance. Compared with classical edge detection and the morphological edge detection with a fixed single structuring element, the proposed method performs better in edge detection effect, and the accuracy of detection can reach 95%.


Key words: edge detection; remote sensing image; variable structuring element; least squares method


 

CLD number: TN911.73Document code: A


Article ID: 1674-8042(2018)03-0233-08  doi: 10.3969/j.issn.1674-8042.2018.03.005


 

References


1]Jia K, Li Q Z, Tian Y C, et al. A review of classification methods of remote sensing imagery. Spectroscopy and Spectral Analysis, 2011, 31(10): 2618-2623.

2]Huang Q Y, Xiao P F, Feng X Z, et al. Edge detection from high resolution remote sensing image combining phase congruency with total variation model. Journal of Image and Graphics, 2014, 19(3): 439-446.

3]Xu S, Zhang L, Li Z, et al. A fast adaptive interpolation algorithm of high spatial resolution remote sensing image. Acta Optica Sinica, 2014, 34(13): 131-136.

4]Huang Z J. An adaptive scale segmentation for remote sensing image based on visual complexity. Journal of Electronics & Information Technology, 2013, 35(8): 1786-1792.

5]Thouraya M M, Malika B, Bachir B. Mathematical morphology for TOFD image analysis and automatic crack detection. Ultrasonics, 2014, 54(6): 1642-1648.

6]Zhou D, Li G, Wang D, et al. Method of destriping stripe noise of aerial images based on total variation. Acta Optica Sinica, 2014, 34(11): 322-328.

7]Wang A, Chen S, Wang X. Adaptive remote sensing image fusion based on HIS and wavelet transform. Opto Electronic Engineering, 2016, 43(8): 76-83.

8]Ye X, Qin Q M, Wang J, et al. Relief tent detection from high-resolution remote sensing image based on mathematical morphology and multi-angle template matching. Bulletin of Surveying and Mapping, 2015, (1): 86-89.

9]Wang K, Gu X F, Yu T, et al. Segmentation of high-resolution remotely sensed imagery combining spectral similarity with phase congruency. Journal of Infrared and Millimeter Waves, 2013, 32(1): 73-79.

10]Li H, Xiao P F, Feng X Z, et al. Multiscale edge detection in multispectral remotely sensed imagery based on vector field model. Acta Geodaetica et Cartographica Sinica, 2012, 41(1): 100-107.

11]Xiong Y, Li J, Zuo X, et al. Research on an edge detection algorithm of remote sensing image based on wavelet enhancement and morphology. Journal of Computers, 2014, 9(5): 1247-1252.

12]Yue A Z, Yang J Y, Zhang C, et al. Multi-scale morphological filter for image segmentation of very high resolution satellite imagery. Transactions of the Chinese Society of Agricultural Engineering, 2013, 29(S1): 89-95.

13]Huang Z, Zhang J, Xu F. A novel multi-scale relative salience feature for remote sensing image analysis. Optik-International Journal for Light and Electron Optics, 2014, 125(1): 516-5 20.

14]Chen J X, Wang J G. Improved watershed segmentation algorithm for medical image. Application Research of Computers, 2013, 30(8): 2557-2560.

15]Chen S T, Wang H. High resolution remote sensing image classification based on multi-scale and multi-feature fusion. Chinese Journal of Quantum Electronics, 2016, 33(4): 420-426.

16]Shi W, Zhu X F, Zhu G. Adaptive edge detection algorithm of MRI image based on morphology. Chinese Journal of Scientific Instrument, 2013, 34(2): 408-414.

17]Deng C X, Chen Y, Bi H, et al. The improved algorithm of edge detection based on mathematics morphology. International Journal of Signal Processing, Image Processing and Pattern Recognition, 2014, 7(5): 309-322.

18]Liu J, Wang D J, Jia P, et al. Point target detection based on omnidirectional morphological filtering and local characteristic criterion. Acta Optica Sinica, 2017, 37(11): 19-30.

19]Cheng G, Guo L, Han J W, et al. Infrared dim small target detection based on morphological band-pass filtering and scale space theory. Acta Optica Sinica, 2012, 32(10): 152-159.

20]Li X L, Pan J X, Liu B, et al. Symmetric axis detection for images based on Hough algorithm. Journal of Measurement Science and Instrumentation, 2015, 6(4): 342-346.

21]Xiong W Z, Sun M C. Improving focal output accuracy of zoom lens through least square method. Chinese Journal of Scientific Instrument, 2014, 35(S1): 151-154.


 

基于形态学可变结构元素的遥感图像边缘检测方法


姚丽娟, 王小鹏, 王伟, 麻文刚


(兰州交通大学 电子与信息工程学院, 甘肃 兰州 730070)


摘要:利用单一结构元素对遥感图像进行形态学边缘检测时, 可能会出现边缘不完整、 抑制噪声能力差等问题。 为此, 提出了一种基于可变结构元素的遥感图像形态学边缘检测方法。 首先,依据遥感图像目标的多样性, 构造不同尺度和包含多方位的结构元素, 以此可变结构元素为基础, 构建相应的形态学运算, 对遥感图像进行Top-hat和Bottom-hat变换, 抑制目标背景中的噪声,突出图像目标边缘; 然后利用构造的可变结构元素进行形态学边缘检测, 获得多幅具有不同尺度和方位边缘特征的图像; 最后对各个方向边缘进行加权求和得到图像边缘, 运用最小二乘法对其边缘进行拟合, 从而精确地定位出目标边缘轮廓。 实验结果表明, 本文方法能够检测到完整的遥感图像边缘信息, 边缘检测精度较高, 抗噪性能优越, 相比经典边缘检测算子和单一结构元素的形态学边缘检测方法, 图像边缘检测效果较好, 检测精度达到95%。

关键词:边缘检测; 遥感图像; 可变结构元素; 最小二乘法


 

引用格式:YAO Li-juan, WANG Xiao-peng, WANG Wei, et al. Edge detection method for remote sensing image based on morphological variable structuring element. Journal of Measurement Science and Instrumentation, 2018, 9(3): 233-240. [doi:10.3969/j.issn.1674-8042.2018.03.005]


[full text view]