This paper proposes a supervised image segmentation algorithm for high resolution remote sensing images by introducing the Gaussian Mixture Model (GMM) with spatial relationship in order to solve the problem of the increasing dissimilarity in the same object and the decreasing of dissimilarity between two different objects. The proposed algorithm takes samples according to the segmentation areas and uses the least squared method to fit the histogram. GMMs are established to describe the complex spectral characteristic in each area accurately. Then spatial relationships are taken consider into the probability measures in GMMs to make the dissimilarities of pixels in a window is determined by all the pixels in the same window. Overall the GMMs can describe the spatial relationships between the pixels in high resolution remote sensing images. Finally the segmentation result is obtained by maximum probability principle. To verify the feasibility and the effectively of the proposed algorithm, the algorithm is performed on real high resolution remote sensing and synthetic images and compared the results with that of FCM and HMRF-FCM based segmentation algorithm. Qualitative and quantitative results prove that the proposed algorithm could improve the accuracy of segmentation.
王春艳,徐爱功,孙川,赵雪梅. 融入空间关系的GMM全色高分辨率遥感影像监督分割方法[J]. 电子与信息学报, 2017, 39(5): 1071-1078.
WANG Chunyan, XU Aigong, SUN Chuan, ZHAO Xuemei. Surpervised Segmentation Algorithm Based on GMM with Spatial Relationship for High Resolution Ranchromatic Remote Sensing Image. JEIT, 2017, 39(5): 1071-1078.
BRUZZONE L and CARLIN L. A multilevel context-based system for classification of very high spatial resolution images [J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(9): 2587-2600. doi: 10.1109/TGRS.2006.875360.
[2]
ACAR E and SELIM A. Anomaly detection with sparse unmixing and Gaussianmixture modeling of hyperspectral images[C]. IEEE Conference Publications, Italy, Milan, 2015: 5035-5038. doi: 10.1109/IGARSS.2015.7326964.
[3]
BRYAN P and DANIEL W. Bliss estimation information bounds using the I-MMSE formula and Gaussian mixture models[C]. Annual Conference on Information Science and Systems, Princeton, NJ, 2016: 274-279. doi: 10.1109/CISS. 2016.7460514.
[4]
WANG Xiaoyan, WANG Yangsheng, and FENG Xuetao, et al. Adaptive gaussian mixture models mased facial actions tracking[C]. International Conference on Computer Science and Software Engineering, Wuhan, China, 2008, 2: 923-926. doi: 10.1109/CSSE.2008.648.
[5]
WILSON S, KURUOGLU E, and SALERNO E. Fully bayesian source separation of astrophysical images modelled by mixture of gaussians[J]. IEEE Journal of Selected Topics in Signal Processing, 2008, 2(5): 685-696. doi: 10.1109/ JSTSP.2008.2005320.
[6]
AVI M and YUVAL B S. Gaussian mixture models for speaker-recognition[J]. IET Journals & Magazines, 2014, 8(8): 860-867. doi: 10.1049/iet-spr.2013.0270.
[7]
ZIVKOVIC Z. Improved adaptive gaussian mixture model for background subtraction[C]. Proceedings of International Conference on Pattern Recognition, 2004, 2: 28-31. doi: 10. 1109/ICPR.2004. 1333992.
[8]
TAO Wenbing and SUN Kun. Robust point sets mtching by fusing feature and spatial information using nonuniform gaussian mixture models[J]. EEE Transactions on Image Processing, 2015, 24(11): 3754-3767. doi: 10.1109/TIP.2015. 2449559.
[9]
SFIKAS G, NIKOU C, and HEINRICH C, et al. Spatially varying mixtures incorporating line processes for image segmentation[J]. Journal of Marhematical Imaging and Vision, 2010, 36(2): 91-110. doi: 10.1007/s10851-009-0174-x.
[10]
MITRA S. Gaussian mixture models for human face recognition under illumination variations[J]. Applied Mathematics, 2012, 3: 2071-2079. doi: 10.4236/am.2012. 312A286.
[11]
Nadia Z, Hayet B, HAYET B, et al. Voice interaction using Gaussian mixture models for augmented reality applications[C]. 2015 4th International Conference on Electrical Engineering, Boumerdes, Algeria, 2015: 1-4. doi: 10.1109/INTEE.2015.7416773.
[12]
GROOSS R, YANG J, and WAIBEL A. Growing Gaussian mixture models for pose invariant face recognition[C]. Proceedings 15th International Conference on Pattern Recognition, Barcelona, Spain, 2000, 1: 1088-1091. doi: 10.1109/ICPR.2000.905661.
[13]
MONTAZERI GHAHJAVERESTAN M, MASOUDI S, SHAMSOLLAHI M B, et al. Coupled hidden markov model-based method for apnea bradycardia detection[J]. IEEE Journal of Biomedical and Health Informatics, 2016, 20(2): 527-538. doi: 10.1109/JBHI.2015.2405075.
[14]
GEMAN D and GEMAN D. Stochastic relaxation, gibbs distributions and the bayesian restoration of images[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1984, 6(6): 721-741. doi: 10.1109/TPAMI.1984.4767596.
ZHAO Xuemei, LI Yu, and ZHAO Quanhua. Image segmentation by fuzzy clustering algorithm combining hidden markov random field and Gaussian regression model[J]. Journal of Electronics and Information Technology, 2014, 36(11): 2730-2736. doi: 10.3724/SP.J.1146.2013.01751.
[16]
CHOI H S, HARNOR D R, and KIM Y. Partial volume tissue classification of multichannel magnetic resonance imagesA mixel model[J]. IEEE Transactions on Medical Imaging, 1991, 10(3): 395-407. doi: 10.1109/42.97590.
[17]
AMIR H and JOSEP P. A doubly hierarchical dirichlet process hidden markov model with a non-ergodic structure[J]. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2016. 24(1): 174-184. doi: 10.1109/TASLP.2015. 2500732.
[18]
NGUYEN T M, WU Q M, and AHUJA S. An extension of the standard mixture model for image segmentation[J]. IEEE Transactions on Neural Networks, 2010, 21(8): 1326-1338. doi: 10.1109/TNN.2010.2054109.
XIONG Tao, JIANG Wanlin, and LI Lelin. Gauss mixtre model based semi supervised classifiction for remote rensing image[J]. Geomatics and Information Science of Wuhan University, 2011, 36(1): 108-112.
