A New Automatic Selection Method of Optimal Segmentation Scale for High Resolution Remote Sensing Image

Full Text (PDF, 741KB), PP.14-20

Views: 0 Downloads: 0


Jin Huazhong 1,* Zhiwei Ye 1 Zhengbing Hu 2

1. School of Computer Science, Hubei university of Technology

2. School of Education Information Technology, Central China Normal University

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2017.03.02

Received: 11 Nov. 2016 / Revised: 23 Dec. 2016 / Accepted: 7 Feb. 2017 / Published: 8 Mar. 2017

Index Terms

Optimal segmentation scale, High resolution remote sensing image, Multi-scale MRF model, Belief propagation


Multi-scale segmentation is one of the most important methods for object-oriented classification. The selection of the optimal scale segmentation parameters has become difficult and hot in current research certainly. This paper takes aerial images and IKONOS images as the experimental objects and proposes an automatic selection method of optimal segmentation scale for high resolution remote sensing image based on multi-scale MRF model. This method introduces the region feature into the object, and obtains the hierarchical structure of the image from the bottom up through the message propagation between the objects. Finally, the optimal segmentation scale is obtained automatically by computing the marginal probabilities of the objects in each scale image. Experimental results show that this method can effectively avoid the subjectivity and sidedness of the segmentation process, and improve the accuracy and efficiency of high resolution segmentation. 

Cite This Paper

Jin Huazhong, Ye zhiwei, Hu Zhengbing,"A New Automatic Selection Method of Optimal Segmentation Scale for High Resolution Remote Sensing Image", International Journal of Image, Graphics and Signal Processing(IJIGSP), Vol.9, No.3, pp.14-20, 2017. DOI: 10.5815/ijigsp.2017.03.02


[1]Huang Huiping. Scale Issues in object-oriented Image Analysis [D]. Beijing: Institute of Remote Sensing Applications Chinese Academy of Sciences, 2003.

[2]Wang LU, Liu Qingyuan. The Methods Summary of optimal segmentation Scale Selection in High-Resolution Remote sensing Images Multi-Scale Segmentation[J], 2015,38(3):166-169..

[3]Sun Bozhong. Multi-scale Segmentation Technique in High Resolution Image Information Extraction Application Research [D]. Xi'an: Xi'an University of Science and Technology, 2011.

[4]J M Laferte, P Perez, F Heitz. Discrete Markov image modeling and inference on the quadtree [J]. IEEE Transactions on Image Processing, 2000, 9(3):390-404.

[5]WANG Xili, Liu Fang, Jiao Licheng. Unsupervised Image Segmentation Based on Incomplete Hierarchical MRF [J]. ACTA ELECTRONICA SINICA, 2004, 32(7):1086-1089. 

[6]YANG Q X,WANG L. Stereo matching with color-weighted correlation, hierarchical belief propagation, and occlusion handling [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(3):1-12.

[7]TODOROVIC S,NECHYBA M C. Dynamic trees for unsupervised segmentation and matching of image regions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,2005,27(11):1762-1777.

[8]G. Poggi, G. Scarpa and J. B. Zerubia. Supervised Segmentation of Remote Sensing Images Based on a Tree-Structured MRF Model [J]. IEEE Transaction on Geoscience and Remote Sensing, 2005:43(8):1901-1911.

[9]X.LAN, S. Roth, D. P. Huttenlocher, et al., Efficient Belief propagation with learned higher-order Markov random fields [C]. European Conference on Computer Vision, Berlin: Springer-verlag, 2006:269-282.

[10]LIU Guanghui, REN Qingchang, MENG Yuebo. Image Segmentation Based on Multiscale Local Region Belief Propagation Algorithm [J]. Journal of Beijing University of Technology, 2014, 40(7):1105-1109.

[11]J. Besag. Spatial interactions and the statistical analysis of lattice systems [J]. Journal of Royal Statistical Society: Series B, 1974, 36(2):192-236.

[12]J.S. Yedidia, W.T. Freeman, Y. Weiss. Understanding Belief Propagation and Its Generalizations [M].Exploring Artificial Intelligence in the New Millennium, Chap. 8, 2003:239-269.

[13]D.P. Young, J.M. Ferryman. PETS Metrics: On-Line Performance Evaluation Service [C]. Visual Surveillance and Performance Evaluation of Tracking and Surveillance. Beijing: IEEE, 2005:317-324.