融入空間關(guān)系的GMM全色高分辨率遙感影像監(jiān)督分割方法

王春艷; 徐愛功; 孫川; 趙雪梅

doi:10.11999/JEIT160798

融入空間關(guān)系的GMM全色高分辨率遙感影像監(jiān)督分割方法

doi: 10.11999/JEIT160798 cstr: 32379.14.JEIT160798

1.
(遼寧工程技術(shù)大學(xué)礦業(yè)技術(shù)學(xué)院葫蘆島 125105) ②(遼寧工程技術(shù)大學(xué)測繪與地理科學(xué)學(xué)院阜新 123000) ③(阜新市國土資源局阜新 123000)

基金項(xiàng)目:

遼寧省教育廳一般項(xiàng)目(LJYL036, LJYL012)，教育部高等學(xué)校博士學(xué)科點(diǎn)專項(xiàng)科研基金(20122121110007)

計量
- 文章訪問數(shù): 1570
- HTML全文瀏覽量: 167
- PDF下載量: 303
- 被引次數(shù): 0
出版歷程
- 收稿日期: 2016-07-26
- 修回日期: 2017-01-10
- 刊出日期: 2017-05-19

Surpervised Segmentation Algorithm Based on GMM with Spatial Relationship for High Resolution Ranchromatic Remote Sensing Image

1.
(School of Mining Industry and Technology, Liaoning Technical University, Huludao 125105 China)
2.
(School of Geomatics, Liaoning Technical University, Fuxin 123000, China)

Funds:

The General Science Research Project of Education Bureau of Liaoning Province (LJYL036, LJYL012), The Research Fund for the Doctoral Program of Higher Education of China (20122121110007)

摘要

摘要: 為了解決高分辨率遙感影像中相同地物目標(biāo)異質(zhì)性和空間破碎性增大及不同地物目標(biāo)的相似性增強(qiáng)所帶來的分割新問題，該文提出一種融入空間關(guān)系的高斯混合模型(GMM)高分辨遙感影像監(jiān)督分割方法。該方法首先按分割區(qū)域進(jìn)行監(jiān)督采樣，并通過最小二乘法進(jìn)行直方圖擬合，對影像中的每個類別區(qū)域建立GMM用來精確表征高分辨遙感影像每個分割區(qū)域復(fù)雜的地物光譜特征；然后在GMM的概率測度域融入空間關(guān)系，使每個像素的區(qū)域所屬由該像素鄰域窗口內(nèi)所有像素概率測度共同決定，以刻畫高分辨率遙感影像中像素間的空間相關(guān)性；最后按照最大概率測度原則完成對高分辨率遙感影像的分割。為了驗(yàn)證文中算法的可行性與有效性分別對合成影像及真實(shí)高分辨率遙感影像進(jìn)行分割實(shí)驗(yàn)，并和經(jīng)典的FCM方法及HMRF-FCM方法進(jìn)行對比，定量與定性的結(jié)果證明了文中方法能夠提高分割精度。
- 高分辨率遙感影像 /
- 高斯混合模型 /
- 空間關(guān)系 /
- 監(jiān)督分割
Abstract: 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.
- High resolution remote sensing image /
- Gaussian Mixture Model (GMM) /
- Spatial relationship /
- Supervised segmentation

HTML全文

參考文獻(xiàn)(21)

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

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.

趙雪梅, 李玉, 趙泉華. 結(jié)合高斯回歸模型和隱馬爾可夫隨機(jī)場的模糊聚類圖像分割[J]. 電子與信息學(xué)報, 2014, 36(11): 2730-2736. doi: 10.3724/SP.J.1146.2013.01751.

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.

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.

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.

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.

熊濤, 姜萬壽, 李樂林. 基于高斯混合模型的遙感影像半監(jiān)督分類[J]. 武漢大學(xué)學(xué)報(信息科學(xué)版), 2011, 36(1): 108-112.

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.

相關(guān)文章

施引文獻(xiàn)

資源附件(0)

訪問統(tǒng)計