Remote sensing image segmentation with texture removal

doi:10.11772/j.issn.1001-9081.2017.11.3162

Abstract

Abstract: Focused on the issue that the precise segmentation of remote sensing images which contain complex textures is always difficult, a novel algorithm which combined remote sensing image segmentation with texture removal was proposed. Firstly, the method of texture removal with relative total variation was improved. A new norm constraint was introduced to the relative total variation algorithm, which helped to enhance the major structures in images while removing textures. Meanwhile, the improved texture removal method could assist the following image segmentation. Secondly, mean shift algorithm was used to segment remote sensing images after texture removal by unsupervised clustering. The proposed segmentation algorithm of remote sensing images was tested on different remote sensing images. The experimental results demonstrate that the proposed method can split the main objects from very high resolution remote sensing images. The proposed method obtains better results compared with other methods of remote sensing image segmentation which segmented images without texture removal or segmented remote sensing images combined with other texture removal methods. The proposed method can reduce the influence of texture on image segmentation and improve the accuracy of remote sensing image segmentation.

Key words: texture, relative total variation, mean shift, remote sensing image segmentation

摘要： 针对包含复杂纹理信息的遥感图像难以进行精准图像分割的问题，提出了一种结合纹理去除的遥感图像分割方法。首先，改进了相对全变差纹理去除方法，通过引入新的范数约束使相对全变差纹理去除方法可以在去除纹理信息的同时凸显图像中的主要结构，达到辅助分割的效果；然后，使用均值漂移算法对经过纹理去除的遥感图像进行无监督聚类，达到分割的目的；最后，提出的遥感图像分割算法在不同遥感图像上进行了测试。实验结果表明，在高分辨遥感图像的分割上，所提算法可以分割出遥感图像中的主要目标，和直接分割或者结合其他纹理去除方法相比取得了更好的分割结果。所提出的分割算法可以降低纹理信息对图像分割的影响，提高遥感图像分割的精度。

关键词: 纹理, 相对全变差, 均值漂移, 遥感图像分割

CLC Number:

TP751.1

ZHOU Mingfei, WANG Xili. Remote sensing image segmentation with texture removal[J]. Journal of Computer Applications, 2017, 37(11): 3162-3167.

周明非, 汪西莉. 结合纹理去除的遥感图像分割[J]. 计算机应用, 2017, 37(11): 3162-3167.

References

[1] YUAN Q, ZHANG L, SHEN H. Hyperspectral image denoising employing a spectral-spatial adaptive total variation model[J]. IEEE Transactions on Geoscience & Remote Sensing, 2012, 50(10):3660-3677.
[2] 郭玲玲, 张立国, 吴泽鹏,等. 基于受限全变差正则化的遥感图像去模糊方法[J]. 激光与光电子学进展, 2013, 50(11):88-93.(GUO L L, ZHANG L G, WU Z P, et al. Deblurring of remote sensing images based on constrained total-variation regularization[J]. Laser & Optoelectronics Progress, 2013, 50(11):88-93.)
[3] MUANGKOTE N, SUNAT K, CHIEWCHANWATTANA S. Multilevel thresholding for satellite image segmentation with moth-flame based optimization[C]//JCSSE 2016:Proceedings of the 2016 International Joint Conference on Computer Science and Software Engineering. Piscataway, NJ:IEEE, 2016:1-6.
[4] GROZAVU N, ROGOVSCHI N, CABANES G, et al. VHR satellite image segmentation based on topological unsupervised learning[C]//Proceedings of the 14th IAPR Conference on Machine Vision Applications. Piscataway, NJ:IEEE, 2015:543-546.
[5] GANESAN P, PALANIVEL K, SATHISH B S, et al. Performance of fuzzy based clustering algorithms for the segmentation of satellite images-a comparative study[C]//Proceedings of the 2015 IEEE Seventh National Conference on Computing, Communication and Information Systems. Piscataway, NJ:IEEE, 2015:23-27.
[6] PARE S, BHANDARI A K, KUMAR A, et al. Satellite image segmentation based on different objective functions using genetic algorithm:a comparative study[C]//Proceedings of the 2015 IEEE International Conference on Digital Signal Processing. Piscataway, NJ:IEEE, 2015:730-734.
[7] DEEPIKA N P, VISHNU K. Different techniques for satellite image segmentation[C]//Proceedings of the 2015 Online International Conference on Green Engineering and Technologies. Piscataway, NJ:IEEE, 2015:1-6.
[8] XU L, LU C, XN Y, et al. Image smoothing via L0 gradient minimization[J]. ACM Transactions on Graphics, 2011, 30(6):61-64.
[9] SHEN C T, CHANG F J, HUNG Y P, et al. Edge-preserving image decomposition using L1 fidelity with L0 gradient[C]//SIGGRAPH Asia 2012 Technical Briefs. New York:ACM, 2012:Article No. 6.
[10] CHENG X, ZENG M, LIU X. Feature-preserving filtering with L0 gradient minimization[J]. Computers & Graphics, 2014, 38(1):150-157.
[11] XU L, YAN Q, XIA Y, et al. Structure extraction from texture via relative total variation[J]. ACM Transactions on Graphics, 2012, 31(6):439-445.
[12] RUDIN L I, OSHER S, FATEMI E. Nonlinear total variation based noise removal algorithms[J]. Physica D:Nonlinear Phenomena, 1992, 60(1/2/3/4):259-268.
[13] OLIVEIRA J P, BIOUCAS-DIAS J M, FIGUEIREDO M A T. Adaptive total variation image deblurring:a majorization-minimization approach[J]. Signal Processing, 2009, 89(9):1683-1693.
[14] 吴晓旭, 刘秀平, 刘宇,等. 局部加权全变差下的盲去模糊[J]. 计算机辅助设计与图形学学报, 2014, 26(12):2173-2181.(WU X X, LIU X P, LIU Y, et al. Blind deblurring based on local weighted total variation[J]. Journal of Computer-Aided Design and Computer Graphics, 2014, 26(12):2173-2181.)
[15] 万洪林, 彭玉华, 曲怀敬. 全变差数字滤波器与Ridgelet变换相结合的图像去噪方法[J]. 电子学报, 2008, 36(1):90-94.(WAN H L, PENG Y H, QU H J. Image denoising method with combination of digital TV filter and Ridgelet transform[J]. Acta Electronica Sinica, 2008, 36(1):90-94.)
[16] WU H, TU S, WANG L, et al. Video Texture Smoothing based on Relative Total Variation and Optical Flow Matching[M]. Berlin:Springer, 2014:13-21.
[17] PARIS S, DURAND, F. A fast approximation of the bilateral filter using a signal processing approach[J]. International Journal of Computer Vision, 2009, 81(1):24-52.
[18] FARBMAN Z, FATTAL R, LISCHINSKI D. Edge-preserving decompositions for multi-scale tone and detail manipulation[J]. ACM Transactions on Graphics, 2008, 27(3):15-19.
[19] LIU Q, XIONG B, YANG D, et al. A generalized relative total variation method for image smoothing[J]. Multimedia Tools and Applications, 2016, 75(13):7909-7930.
[20] PARIS S, DURAND F. A topological approach to hierarchical segmentation using mean shift[C]//Proceedings of the 2007 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2007:1-8.