多方向小波变换高分影像边缘提取

doi:10.6046/gtzyyg.2019.01.02

摘要
图/表
参考文献
相关文章
Metrics

全文: PDF(4352 KB)

HTML
输出: BibTeX | EndNote (RIS)

摘要

由于小波变换方向分辨率较低,而高分影像中地物几何结构丰富,边缘存在于各个方向,导致了图像小波变换的频率系数仅被分解到水平、垂直和对角3个方向子带上,使得小波变换对具有复杂几何结构的地物边缘提取存在不足。为此提出一种Directionlet变换理论结合模极大值法的高分影像边缘提取方法。首先,对原始影像进行基于格的分解获得任意方向一维线集合,再进行小波变换并恢复图像格式得到高频方向子带; 然后,利用改进模极大值法和双阈值法对系数进行处理得到边缘结果; 最后,采用数学形态学方法对边缘提取结果进行细化连接等后处理,从而实现对高分影像边缘的提取。实验结果表明,该方法与传统边缘检测方法和小波变换相比,边缘提取更加完整,定位精度更高。

	服务

	把本文推荐给朋友
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	李军军
	曹建农
	廖娟
	程贝贝

关键词 ：边缘提取, 小波变换, Directionlet变换, 模极大值法

Abstract：

In view of the low resolution in direction of wavelet transform,the rich geometric structure of high spatial resolution remote sensing imagery (HSR) and the existence of edge in various directions which causes shortcomings in edge extraction of wavelet transform on objects with complex geometric structure, the authors proposed a HRS image edge extraction method of multi-direction wavelet transform based on Directionlet theory and modulus maximum method. The method first decomposes original image based lattice to obtain one-dimensional line set, then carries out wavelet transform and obtains the high frequency directional sub-band by restore image format. The edge result is obtained by using improved module maximum and the dual threshold method. Finally, the mathematical morphology is used to refine and connect edge results. Experiment result shows that the proposed method can get more complete edge compared with traditional method and standard two-dimensional wavelet transform.

Key words： edge extraction wavalet transform Directionlet transform modulus maximum method

收稿日期: 2017-10-25 出版日期: 2019-03-15

P23

基金资助:国家自然科学基金面上项目“高分辨率遥感影像信息提取的特征结构化多尺度分析方法研究”(41571346);自然资源部退化及未利用土地整治工程重点实验室项目“退化土地影像检测”共同资助(SXDJ2017-2016KCT-23)

通讯作者: 曹建农

作者简介: 李军军(1992-),男,博士研究生,主要从事遥感图像分析方面的研究。Email: ljj19921592@163.com。

引用本文:

李军军, 曹建农, 廖娟, 程贝贝. 多方向小波变换高分影像边缘提取[J]. 国土资源遥感, 2019, 31(1): 8-15.
Junjun LI, Jiannong CAO, Juan LIAO, Beibei CHENG. High spatial resolution remote sensing imagery edge extraction based on multi-direction wavelet transform. Remote Sensing for Land & Resources, 2019, 31(1): 8-15.

链接本文:

https://www.gtzyyg.com/CN/10.6046/gtzyyg.2019.01.02 或 https://www.gtzyyg.com/CN/Y2019/V31/I1/8

Fig.1 影像方向性小波变换

Fig.2 格与陪线

Fig.3 高分影像不同方向小波变换结果

Fig.4 多方向梯度分量

Fig.5 2个最大梯度分量方向的位置关系

Fig.6 高分影像与非极大值抑制后的结果

Fig.7 多方向小波变换的高分影像边缘提取流程

Fig.8 实验结果

[1]	谭媛, 黄辉先, 徐建闽 , 等. 基于改进Sobel算子的遥感图像道路边缘检测方法[J]. 国土资源遥感, 2016,28(3):7-11.doi: 10.6046/gtzyyg.2016.03.02. doi: 10.6046/gtzyyg.2016.03.02
	Tan Y, Huang H X, Xu J M , et al. Road edge detection from remote sensing image based on improved Sobel operator[J]. Remote Sensing for Land and Resources, 2016,28(3):7-11.doi: 10.6046/gtzyyg.2016.03.02.
[2]	白婷婷, 邓彩霞, 耿英 . 基于小波变换与Canny算子融合的图像边缘检测方法[J]. 哈尔滨理工大学学报, 2010,15(1):44-47,51. doi: 10.3969/j.issn.1007-2683.2010.01.010
	Bai T T, Deng C X, Geng Y . Image edge detection based on wavelet transform and Canny operator[J]. Journal of Harbin University of Science and Technology, 2010,15(1):44-47,51.
[3]	Canny J . A computational approach to edge detection[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1986,8(6):679-698. doi: 10.1109/TPAMI.1986.4767851
[4]	Zeng J, Li D. An improved Canny edge detector against impulsive noise based on CIELAB space [C]//International Symposium on Intelligence Information Processing and Trusted Computing. Huanggang:IEEE, 2010: 520-523.
[5]	Guo L Y, Nan J C. Canny edge detection algorithm based on wavelet transform and RAMF [C]//International Conference on Computational Problem-Solving.Lijiang:IEEE, 2010: 344-346.
[6]	李俊山, 马颖, 赵方舟 , 等. 改进的Canny图像边缘检测算法[J]. 光子学报, 2011,40(s1):50-54. doi: 10.3788/gzxb201140s1.0050
	Li J S, Ma Y, Zhao F Z , et al. A novel arithemtic of image edge detection of Canny operator[J]. Acta Photonica Sinica, 2011,40(s1):50-54.
[7]	赵凌, 张祖荫, 郭伟 . 基于数学形态学的毫米波图像边缘检测方法[J]. 国土资源遥感, 2006,18(4):19-22.doi: 10.6046/gtzyyg.2006.04.05. doi: 10.3969/j.issn.1001-070X.2006.04.005
	Zhao L, Zhang Z Y, Guo W . A mathematical morphological for edge detection in millimeter wave radiometric images[J]. Remote Sensing for Land and Resources, 2006,18(4):19-22.doi: 10.6046/gtzyyg.2006.04.05.
[8]	Mallat S G . A theory for multiresolution signal decomposition:The wavelet representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1989,11(7):674-693. doi: 10.1109/34.192463
[9]	徐继友, 朱耆祥 . 小波变换在图象边缘提取中的应用[J]. 光电工程, 1998,25(4):28-34.
	Xu J Y, Zhu Q X . The application of wavelet transform to image edge extracting[J]. Opto-Electronic Engineering, 1998,25(4):28-34.
[10]	高国荣, 刘冉, 羿旭明 . 一种改进的基于小波变换的图像边缘提取算法[J]. 武汉大学学报(理学版), 2005,51(5):615-619. doi: 10.3321/j.issn:1671-8836.2005.05.020
	Gao G R, Liu R, Yi X M . A revised image edge detection method based on wavelet[J]. Journal of Wuhan University (Natural and Science Edition), 2005,51(5):615-619.
[11]	章国宝, 叶桦, 陈维南 . 基于正交小波变换的多尺度边缘提取[J]. 中国图象图形学报, 1998,3(8):651-654. doi: 10.11834/jig.199808202
	Zhang G B, Ye H, Chen W N . A multiscale edge detector based on orthogonal wavelet transform[J]. Journal of Image and Graphics, 1998,3(8):651-654.
[12]	Emmanuel J C, Donoho D L. Curvelets:A surprisingly effective nonadaptive representation for objects with edges[M] //Cohen A, Rabut C,Schumaker L.Curves and Surfaces Fitting.Nashville:Vanderbilt University Press, 2000: 105-120.
[13]	Candes E J . Ridgelets:Theory and Applications[D]. Stanford:Stanford University, 1998.
[14]	Do M N, Vetterli M . The Contourlet transform:An efficient directional multiresolution image representation[J]. IEEE Transactions on Image Processing, 2005,14(12):2091-2106. doi: 10.1109/TIP.2005.859376 pmid: 16370462
[15]	Meyer F G, Coifman R R . Brushlets:A tool for directional image analysis and image compression[J]. Applied and Computational Harmonic Analysis, 1997,4(2):147-187. doi: 10.1006/acha.1997.0208
[16]	赵振兵, 金思新, 刘亚春 . 基于NSCT的航拍绝缘子图像边缘提取方法[J]. 仪器仪表学报, 2012,33(9):2045-2052. doi: 10.3969/j.issn.0254-3087.2012.09.018
	Zhao Z B, Jin S X, Liu Y C . Aerial insulator image edge extraction method based on NSCT[J]. Chinese Journal of Scientific Instrument, 2012,33(9):2045-2052.
[17]	Jin R J, Yin J J, Zhou W, et al. Edge detection in polarimetric SAR images based on the nonsubsampled ontourlet transform [C]//IEEE Radar Conference(RadarCon).Arlington:IEEE, 2015: 0319-0323.
[18]	Zhou G Y, Cui Y, Chen Y L , et al. SAR image edge detection using Curvelet transform and Duda operator[J]. Electronics Letters, 2010,46(2):167-169. doi: 10.1049/el.2010.2888
[19]	吴一全, 曹照清, 陶飞翔 . 结合多尺度几何分析和KICA的遥感图像变化检测[J]. 遥感学报, 2015,19(1):126-133. doi: 10.11834/jrs.20153254
	Wu Y Q, Cao Z Q, Tao F X . Change detection of remote sensing images by multi-scale geometric analysis and KICA[J]. Journal of Remote Sensing, 2015,19(1):126-133.
[20]	Velisavljevic V, Beferull-Lozano B, Vetterli M , et al. Directionlets:Anisotropic multidirectional representation with separable filtering[J] IEEE Transactions on Image Processing, 2006,15(7):1916-1933. doi: 10.1109/TIP.2006.877076 pmid: 16830912
[21]	Chan T S, Yip R K K.Line detection algorithm [C]//13th International Conference on Pattern Recognition.Vienna:IEEE, 1996: 126-130.
[22]	江宇博, 刘波 . 小波模极大值法与数学形态学边缘检测细化结果[J]. 计算机测量与控制, 2017,25(3):165-168. doi: 10.16526/j.cnki.11-4762/tp.2017.03.045
	Jiang Y B, Liu B . Wavelet modulus maxima method and mathematical morphology edge detection thinning results[J]. Computer Measurement and Control, 2017,25(3):165-168.
[23]	Zhang Z, Ma S L, Liu H , et al. An edge detection approach based on directional wavelet transform[J]. Computers and Mathematics with Applications, 2009,57(8):1265-1271. doi: 10.1016/j.camwa.2008.11.013
[24]	张志强, 宋海生 . 应用Otsu改进Canny算子的图像边缘检测方法[J]. 计算机与数字工程, 2014,42(1):122-128,141. doi: 10.3969/j.issn.1672-9722.2014.01.032
	Zhang Z Q, Song H S . Application of Otsu to improve image edge detection method in Canny algorithm[J]. Computer and Digital Engineering, 2014,42(1):122-128,141.
[25]	梁光明, 唐朝京, 刘东华 , 等. 基于分割评价的多层次自适应双阈值分割算法[J]. 电子学报, 2009,37(4):750-752,763. doi: 10.3321/j.issn:0372-2112.2009.04.014
	Liang G M, Tang C J, Liu D H , et al. A multi-level and adaptive dual threshold segmentation algorithm based on evaluation[J]. Acta Electronica Sinica, 2009,37(4):750-752,763.
[26]	周绍光, 孙金彦, 凡莉 , 等. 高分辨率遥感影像的建筑物轮廓信息提取方法[J]. 国土资源遥感, 2015,27(3):52-58.doi: 10.6046/gtzyyg.2015.03.10. doi: 10.6046/gtzyyg.2015.03.10
	Zhou S G, Sun J Y, Fang L , et al. Extraction of building contour from high resolution images[J]. Remote Sensing for Land and Resources, 2015,27(3):52-58.doi: 10.6046/gtzyyg.2015.03.10.

[1]	周超凡, 宫辉力, 陈蓓蓓, 雷坤超, 施轹原, 赵宇. 联合WT-RF的津保高铁沿线地面沉降预测[J]. 自然资源遥感, 2021, 33(4): 34-42.
[2]	肖烨辉, 宋妮迪, 孟盼盼, 王培俊, 范胜龙. 模型集群分析策略联合ELM的土壤重金属Pb含量预测[J]. 自然资源遥感, 2021, 33(4): 143-152.
[3]	肖艳, 辛洪波, 王斌, 崔利, 姜琦刚. 基于小波变换和连续投影算法的黑土有机质含量高光谱估测[J]. 国土资源遥感, 2021, 33(2): 33-39.
[4]	王小兵. 融合提升小波阈值与多方向边缘检测的矿区遥感图像去噪[J]. 国土资源遥感, 2020, 32(4): 46-52.
[5]	胡华龙, 薛武, 秦志远. 基于小波纹理和基元合并的高分影像居民地提取[J]. 国土资源遥感, 2017, 29(1): 21-28.
[6]	梁若飞, 杨风暴, 王毅敏, 孟颖晨, 卫红. 一种类矩形引导的玉米田遥感图像分割算法[J]. 国土资源遥感, 2016, 28(3): 53-59.
[7]	张倩. 基于双重离散小波变换的遥感图像去噪算法[J]. 国土资源遥感, 2015, 27(4): 14-20.
[8]	李文静, 温文鹏, 王清和. 基于Contourlet变换的遥感图像融合方法研究[J]. 国土资源遥感, 2015, 27(2): 44-50.
[9]	孟强强, 杨桄, 童涛, 张俭峰. 基于小波变换的多聚焦图像融合算法[J]. 国土资源遥感, 2014, 26(2): 38-42.
[10]	李迁, 肖春蕾, 陈洁, 杨达昌. 基于机载LiDAR点云和建筑物轮廓线构建DSM的方法[J]. 国土资源遥感, 2013, 25(2): 95-100.
[11]	吴寿江, 李亮, 宫本旭, 龚梅. GeoEye-1遥感图像去雾霾方法比较[J]. 国土资源遥感, 2012, 24(3): 50-53.
[12]	董张玉, 赵萍, 刘殿伟, 王宗明, 汤旭光, 刘婧怡. 一种改进的小波变换融合方法及其效果评价[J]. 国土资源遥感, 2012, 24(3): 44-49.
[13]	于浩孙卫东常玲甘甫平. 基于双树复小波的CBERS-02B星遥感影像融合及评价[J]. 国土资源遥感, 2009, 21(1): 55-59.
[14]	范文婷, 傅平. 一种基于小波变换的遥感图像融合方法[J]. 国土资源遥感, 2008, 20(3): 24-26.
[15]	张大明, 李璐, 符茂胜, 罗斌. 基于小波变换的全色和多光谱遥感图像融合[J]. 国土资源遥感, 2008, 20(1): 50-54.

Viewed

Full text

Abstract

Cited

Shared

Discussed