单极化合成孔径雷达图像颜色特征编码与分类

doi:10.11772/j.issn.1001-9081.2017112780

摘要/Abstract

摘要： 针对目前单极化合成孔径雷达（SAR）伪彩色编码方法存在的细节信息和可视性不强的问题，提出一种颜色特征编码方法。该颜色特征编码方法首先对单极化SAR图像提取纹理特征；然后将每一个特征量化到0到255；其次对每一个灰度级赋予一个RGB颜色，编码成颜色特征图；最后对随机森林计算得到的特征重要性进行排序，每3维特征对应为R、G、B通道生成伪彩图。基于该颜色特征编码方法，提出一种新的分类方法。该分类方法首先根据目视效果选择可分性最好的伪彩图；然后采用统计区域合并（SRM）分割算法对其分割；其次将所有RGB伪彩图作为分类的特征，以随机森林为分类器进行分类，得到初步的结果；最后对初步的结果进行相对多数投票，得到最终的分类结果。方法验证采用两组TerraSAR-X单极化SAR数据，与基于HIS的颜色编码方法对比，该颜色特征编码方法生成的伪彩图信息熵得到了很大提升，且两组数据每类地物的分类精度都大幅度提高，因此证明了所提算法保留了更多的细节信息，获取更多的颜色信息，更利于可视化和地物分类，从而表明提出的颜色特征编码方法是可行的。

关键词: 单极化合成孔径雷达图像, 颜色编码, 统计区域合并, 相对多数投票, 随机森林

Abstract: Aiming at the problem of poor detail and visibility in current color coding methods of single polarization Synthetic Aperture Radar (SAR), a color feature coding method was proposed. Firstly, texture features were extracted from a single-polarized SAR image. Secondly, each feature was quantized to 0 to 255. Then an RGB color was assigned to each gray level to generate a color feature map. Finally, the importance of features calculated by random forest was sorted; the pseudo-color graphs were generated by each three dimensional feature corresponding to the R, G, and B channels. Based on the presented color feature coding method, a new classification method was proposed. Firstly, the pseudo color map with the best geographical separability was selected according to the visual effect, and then segmented by the Statistical Region Merging (SRM) segmentation algorithm. Secondly, all the RGB pseudo color maps were used as the classification features, and a random forest was used as the classifier and obtain the preliminary results. At the end, a relative majority vote was made on the preliminary results and the final classification results were obtained. In the method verification, two sets of TerraSAR-X single-polarization SAR data were used. By comparing the corresponding grayscale image with HIS-based color coding method, the color image information entropy generated by the proposed color feature coding method was greatly improved, and the classification accuracy of each type of ground features for two data sets was greatly improved. It is demonstrated that the proposed algorithm preserves more details for more color information, and it is more conducive to visualization and terrain classification, which indicating the proposed color feature coding method is feasible.

Key words: single polarized Synthetic Aperture Radar (SAR) image, color coding, Statistical Region Merging (SRM), relative majority vote, random forest

中图分类号:

TP75
TN958

邓旭, 徐新, 董浩. 单极化合成孔径雷达图像颜色特征编码与分类[J]. 计算机应用, 2018, 38(7): 2056-2063.

DENG Xu, XU Xin, DONG Hao. Color feature coding and classification of single polarized synthetic aperture radar image[J]. Journal of Computer Applications, 2018, 38(7): 2056-2063.

参考文献

[1] 蒋建军.遥感技术应用[M].南京:江苏教育出版社,2010:10-20.(JIANG J J. Application of Remote Sensing Technology[M]. NanJing:Jiangsu Education Press, 2010:10-20.)
[2] 曲长文,何友,龚沈光.机载SAR发展概况[J].现代雷达,2002,24(1):1-10.(QU C W, HE Y, GONG S G. A survey of airborne SAR development[J]. Modern Radar, 2002, 24(1):1-10.)
[3] 曲长文,何友.空载SAR发展状况[J].遥感技术与应用,2001,16(4):242-247.(QU C W, HE Y. Development status of spaceborne SAR[J]. Remote Sensing Technology and Application, 2001, 16(4):242-247.)
[4] VENTURA A D, SCHETTINI R. Computer-aided color coding for data display[C]//Proceedings of the 11th International Conference of Pattern Recognition. Piscataway, NJ:IEEE, 1992:29-32.
[5] ZHOU X, ZHANG C. A perceptive uniform pseudo-color coding method of SAR images[C]//Proceedings of the 2007 International Conference on Radar. Piscataway, NJ:IEEE, 2007:1-4.
[6] 余磊,靳国旺,徐青,等.基于非线性编码和lαβ变换的SAR图像伪彩色增强[J].测绘科学技术学报,2012,29(3):192-195.(YU L, JIN G W, XU Q, et al. SAR image pseudo-color enhancement based on nonlinear coding and lαβ transformation[J]. Journal of Geomatics Science and Technology, 2012, 29(3):192-195.)
[7] 王众娇.基于正则化的单极化SAR图像伪彩色增强方法研究[D].葫芦岛:辽宁工程技术大学,2014:23-50.(WANG Z J. Research on single-polarization SAR images pseudo-color enhancement method based on regularization[D]. Huludao:Liaoning Technical University, 2014:23-50.)
[8] 卜丽静,张过,陈亚欣.二叉树分层和稀疏约束的SAR图像伪彩色编码[J].遥感信息,2017,32(2):38-42.(BU L J, ZHANG G, CHEN Y X. SAR image pseudo-color coding based on binary tree hierarchy and sparse constraints[J]. Remote Sensing Information, 2017, 32(2):38-42.)
[9] 阮秋琦.数字图像处理学[M].北京:电子工业出版社,2013:15-53.(RUAN Q Q. Digital Image Processing[M]. Beijing:Publishing House of Electronics Industry, 2013:15-53.)
[10] 王智文,刘美珍,蔡启先,等.基于小波分析和伪彩色的遥感图像增强[J].计算机工程与设计,2008,29(18):4771-4772.(WANG Z W, LIU M Z, CAI Q X, et al. Remote sensing image boosting based on wavelet analysis and fake chromatic processing[J]. Computer Engineering and Design, 2008, 29(18):4771-4772.)
[11] 李今秀,李均利,魏平.基于梯度的医学图像伪彩色编码[J].光学技术,2008,34(4):576-578(LI J X, LI J L, WEI P. Pseudocolor coding of medical images based on gradient[J]. Optical Technique, 2008, 34(4):576-578.)
[12] 陈国群,付冬梅,常晓辉.基于聚类算法的红外图像伪彩色增强[J].激光与红外,2007,37(4):384-385.(CHEN G Q, FU D M, CHANG X H. Infrared image pseudo-color enhancement based on clustering algorithm[J]. Laser & Infrared,2007, 37(4):384-385.)
[13] 赵向文,靳国旺,许竞轩,等.基于多阈值大津法直方图分割的SAR数据伪彩色量化方法[J].测绘科学技术学报,2012,29(6):445-449.(ZHAO X W, JIN G W, XU J X, et al. Pseudo-color quantization of SAR based on multi-threshold Otsu method of histogram segmentation[J]. Journal of Geomatics Science and Technology, 2012, 29(6):445-449.)
[14] 陈亚欣,武文波.基于Roberts梯度与HIS色彩空间的SAR图像伪彩色编码[J].测绘与空间地理信息,2017,40(4):85-88.(CHEN Y X, WU W B. Pseudo-color coding of SAR images based on Roberts gradient and HIS color space[J]. Gematics & Spatial Information Technology, 2017, 40(4):85-88.)
[15] 李宏,向遥,张卫,等.基于直方图映射和分层的图像迁移算法研究[J].小型微型计算机系统,2007,28(6):1110-1114.(LI H, XIANG Y, ZHANG W, et al. Colorization of gray images based on histogram mapping and image layers[J]. Journal of Chinese Computer Systems, 2007, 28(6):1110-1114.)
[16] 王世亮,徐岗,储清林,等.基于放缩系数和均值的多参数颜色迁移[J].中国图象图形学报,2013,18(11):1536-1541.(WANG S L, XU G, CHU Q L, et al. Color transfer with multiple parameters by combining the scaling and mean values[J]. Journal of Image and Graphics, 2013, 18(11):1536-1541.)
[17] 王晓颖,王众娇.基于颜色迁移的单极化SAR图像伪彩色增强[J].测绘与空间地理信息,2016,39(8):87-89.(WANG X Y, WANG Z J. Single polarization SAR images pseudo color enhancement based on color transfer[J]. Geomatics & Spatial Information Technology, 2016, 39(8):87-89.)
[18] 张砚,罗强一,刘东红,等.多尺度图像分割和颜色传递的遥感图像彩色化增强[J].测绘学报,2015,44(1):76-81.(ZHANG Y, LUO Q Y, LIU D H, et al. Remote sensing images enhancement based on color transfer and multi-scale image segmentation[J]. Acta Geodaetica et Cartographica Sinica, 2015, 44(1):76-81.)
[19] 卜丽静,吴畅,何志博,等.利用纹理特征的SAR与光学图像融合方法研究[J].测绘工程,2015,24(5):5-10.(BU L J, WU C, HE Z B, et al. Fusion of SAR and optical images based on texture characteristics[J]. Engineering of Surveying and Mapping, 2015, 24(5):5-10.)
[20] 邰建豪,潘斌,赵珊珊,等.基于Shearlet变换的SAR与多光谱遥感影像融合[J].武汉大学学报(信息科学版),2017,42(4):468-474.(TAI J H, PAN B, ZHANG S S, et al. SAR and multispectral remote sensing image fusion method using Shearlet transform[J]. Geomatics and Information Science of Wuhan University, 2017, 42(4):468-474.)
[21] SONG Q, XU F, JIN Y Q. SAR image colorization:converting single-polarization to fully polarimetric using deep neural networks[J]. arXiv Preprint, 2017, 2017:1707.07225.
[22] CHENG Z, YANG Q, SHENG B. Colorization using neural network ensemble[J]. IEEE Transactions on Image Processing, 2017, 26(11):5491-5505.
[23] 高程程,惠晓威.基于灰度共生矩阵的纹理特征提取[J].计算机系统应用,2010,19(6):195-198.(GAO C C, HUI X W. GLCM-based texture feature extraction[J]. Computer Systems & Applications, 2010, 19(6):195-198.)
[24] 苑丽红,付丽,杨勇,等.灰度共生矩阵提取纹理特征的实验结果分析[J].计算机应用,2009,29(4):1018-1021.(YUAN L H, FU L, YANG Y, et al. Analysis of texture feature extracted by gray level co-occurrence matrix[J]. Journal of Computer Applications, 2009, 29(4):1018-1021.)
[25] 王卫红,程栋,陈博.直方图在SAR图像处理中的应用研究[J].中国电子科学研究院学报,2017,12(1):90-95.(WANG W H, CHENG D, CHEN B. The application research of histogram of SAR images processing[J]. Journal of China Academy of Electronics and Information Technology, 2017, 12(1):90-95.)
[26] 余磊.极化SAR图像伪彩色增强与可视化方法研究[D].郑州:信息工程大学,2012:11-13.(YU L. Study on method of pseudo color enhancement and visualization for polarimetric SAR image[D]. Zhengzhou:Information Engineering University, 2012:11-13.)
[27] 张建龙,王斌.DSSRM级联分割的SAR图像变化检测[J].遥感学报,2017,21(4):614-621.(ZHANG J L, WANG B. SAR image change detection method of DSSRM based on cascade segmentation[J]. Journal of Remote Sensing, 2017, 21(4):614-621.)
[28] 王爱平,万国伟,程志全,等.支持在线学习的增量式极端随机森林分类器[J].软件学报,2011,22(9):2059-2074.(WANG A P, WAN G W, CHENG Z Q, et.al. Incremental learning extremely random forest classifier for online learning[J]. Journal of Software, 2011, 22(9):2059-2074.)