Unsupervised remote sensing image segmentation based on data sampling

Xuemei ZHAO; Yu LI; Quanhua ZHAO

doi:10.11834/jrs.20176410

Views : 0 下载量: 662 CSCD: 1

PDF
Export
Share
Collection
Album

Unsupervised remote sensing image segmentation based on data sampling
Vol. 21, Issue 5, Pages: 767-775(2017)
Received：23 November 2016，

Accepted：28 March 2017，

Published：2017-09
DOI： 10.11834/jrs.20176410
稿件说明：

移动端阅览

赵雪梅, 李玉, 赵泉华. 2017. 观测数据采样化的遥感影像非监督分割. 遥感学报, 21(5): 767–775 DOI： 10.11834/jrs.20176410.

Zhao X M, Li Y and Zhao Q H. 2017. Unsupervised remote sensing image segmentation based on data sampling. Journal of Remote Sensing, 21(5): 767–775 DOI： 10.11834/jrs.20176410.

摘要

为了实现影像的自动化分割，提出一种利用非监督方式将观测数据采样化的遥感影像分割方法。该方法利用欧氏空间的概率分布建模采样数据和观测数据，并将其映射到黎曼空间，通过不断将观测数据转换为采样数据的方式实现影像的自动采样化。每次采样过程只需计算观测数据点到采样点的测地线距离，将距采样点测地线距离最小的观测数据转化为采样数据，以保证采样数据不断趋于该类数据的真实分割结果，同时使算法能够有效分割具有不同像素数的类别。将算法应用于模拟影像和真实遥感影像分割，对其分割结果以及传统基于统计、基于模糊的非监督算法和基于神经网络的监督算法相应分割结果定性定量的对比分析验证了该算法的有效性及可行性。

Abstract

Image segmentation is a very common application in remote sensing

in which the number of classes is always given by users. To segment remote sensing images automatically

a sampling method which can transmit observed data into sample data is proposed based on the characteristics in Riemannian space. Therefore

this paper presents an unsupervised image segmentation algorithm which can automatically segment remote sensing images by sampling the detected data into samples. First

model the initial samples obtained by block sampling or artificial sampling through Gaussian probability distribution function (pdf). Second

to take the neighborhood system of the detected image into consideration

Gaussian pdf is also employed to depict the features of the pixel and its correlation between neighbor pixels. Then both the samples and the detected image are mapped to the Riemannian space. In the Riemannian space

the similarity between the points expressing the detected image and the points standing for samples are measured by geodesic

which is the least distance on the curve surface of a manifold. The nearest points standing for the detected image to each sample are transmitted to samples and then the models of the samples are updated according to the new ones. By continually sampling

the models of the samples are tending to their real models

which represents the real segmentation through sampling the detected data. In each sample process

only the nearest detected data are transformed into sample data to make sure the presented algorithm can distinguish different classes with different number of pixels in it. Geodesic employed in this paper evaluates the differences between the detected model and the sample model to improve the accuracy of sampling. The proposed algorithm is carried out on synthetic and real remote sensing images. Experiments on synthetic image shows the changes of samples both in the image and in feature space. Display of the sampling process demonstrate that the models characterizing each class trends to the real ones and the samples tends to the real data of each class in the feature space. Analysis on segmentation results of HMRF-CSA

GRM-FCM

neural network and the proposed algorithms on real remote sensing images validate the effectiveness of the proposed algorithm. The overall accuracy of the proposed algorithm can even reach to 98.9%

which is much higher than those of the compared algorithms. Experiments on synthetic image show the models of samples can tends to real ones

which validate that the proposed sampling process is able to fit the real distributions of each class. Experimental results on real remote sensing images demonstrate that the effectiveness of sampling operation can distinguish classes with different number of pixels. Quantitative and qualitative analysis on the segmentation results show that the presented algorithm can segment remote sensing images accurately and quickly. Besides

the proposed algorithm can be used both as an unsupervised image segmentation algorithm to realize the segmentation of remote sensing images or as sampling process in supervised image segmentation algorithm to provide reliable sample results.

关键词

Keywords

references

Amari S, Kurata K and Nagaoka H. 1992. Information geometry of Boltzmann machines. IEEE Transactions on Neural Networks, 3(2): 260–271

Amari S I. 1995. Information geometry of the EM and em algorithms for neural networks. Neural Networks, 8(9): 1379–1408

Amari S and Nagaoka H. 2000. Methods of Information Geometry. Providence, RI: American Mathematical Society

Blaiotta C, Cardoso M J and Ashburner J. 2016. Variational inference for medical image segmentation. Computer Vision and Image Understanding, 151: 14–28

Brody D C and Hook D W. 2009. Information geometry in vapour-liquid equilibrium. Journal of Physics A: Mathematical and Theoretical, 42(2): 023001

Gong M G, Liang Y, Shi J, Ma W P and Ma J J. 2013. Fuzzy c-means clustering with local information and kernel metric for image segmentation. IEEE Transactions on Image Processing, 22(2): 573–584

Li L, Fan W T, Du J X and Wang J. 2016. A novel image segmentation approach based on truncated infinite Student’s t-mixture model//Huang D S, Han K and Hussain A, eds. Intelligent Computing Methodologies. Cham: Springer: 271–281 [DOI: 10.1007/978-3-319-42297-8_26]

Li Y F and Feng X C. 2016. A multiscale image segmentation method. Pattern Recognition, 52: 332–345

Liu G Y, Zhang Y and Wang A M. 2015. Incorporating adaptive local information into fuzzy clustering for image segmentation. IEEE Transactions on Image Processing, 24(11): 3990–4000

Michel J, Youssefi D and Grizonnet M. 2015. Stable mean-shift algorithm and its application to the segmentation of arbitrarily large remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 53(2): 952–964

Niu S J, Chen Q, de Sisternes L, Ji Z X, Zhou Z M and Rubin D L. 2017. Robust noise region-based active contour model via local similarity factor for image segmentation. Pattern Recognition, 61: 104–119

Sun L, Wu Z B, Liu J J, Xiao L and Wei Z H. 2015. Supervised spectral-spatial hyperspectral image classification with weighted Markov random fields. IEEE Transactions on Geoscience and Remote Sensing, 53(3): 1490–1503

王春艳, 徐爱功, 李玉, 隋心. 2016. 融入空间关系的二型模糊模型高分辨率遥感影像分割. 遥感学报, 20(1): 103–113

Wang C Y, Xu A G, Li Y and Sui X. 2016. Segmentation of high-resolution remote sensing images with type-2 fuzzy model based on spatial relationship. Journal of Remote Sensing, 20(1): 103–113

于波, 孟俊敏, 张晰, 纪永刚. 2013. 结合凝聚层次聚类的极化SAR海冰分割. 遥感学报, 17(4): 887–904

Yu B, Meng J M, Zhang X and Ji Y G. 2013. Segmentation method for agglomerative hierarchical-based sea ice types using polarimetric SAR data. Journal of Remote Sensing, 17(4): 887–904

Zhang M X, Jiao L C, Ma W P, Ma J J and Gong M G. 2016. Multi-objective evolutionary fuzzy clustering for image segmentation with MOEA/D. Applied Soft Computing, 48: 621–637

Zhang T, Xia Y and Feng D D. 2014. Hidden Markov random field model based brain MR image segmentation using clonal selection algorithm and Markov chain Monte Carlo method. Biomedical Signal Processing and Control, 12: 10–18

Zhao W Z and Du S H. 2016. Spectral-spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach. IEEE Transactions on Geoscience and Remote Sensing, 54(8): 4544–4554

赵雪梅, 李玉, 赵泉华. 2014. 结合高斯回归模型和隐马尔可夫随机场的模糊聚类图像分割. 电子与信息学报, 36(11): 2730–2736

Zhao X M, Li Y and Zhao Q H. 2014. Image segmentation by fuzzy clustering algorithm combining hidden Markov random field and Gaussian regression model. Journal of Electronics and Information Technology, 36(11): 2730–2736

Alert me when the article has been cited

提交

Research on cloud detection for HY-1C CZI remote sensing images collected over lands

Segmentation of high-resolution remote sensing images with type-2 fuzzy model based on spatial relationship