Road Extraction Based on the Algorithms of MRF and Hybrid Model of SVM and FCM

Author

Zhu Da-Ming ; Wen Xiang ; Ling Chun-Li

Author_Institution

Fac. of Land Resource Eng., Kunming Univ. of Sci. & Technol., Kunming, China

fYear

2011

fDate

9-11 Aug. 2011

Firstpage

1

Lastpage

4

Abstract

Information extraction is the prerequisite of remote sensing image segmentation, which is the key procedure of image analysis. In this paper we establish MAP-MRF framework using Markov random field (MRF),adopt the sampler training, and get the factor of model, introducing the simulated annealing to segment the image and extract the road. On the other hand, Support Vector Machines (SVM) plus Fuzzy C-Mean (FCM) model was proposed and integrated together for remote sensing image segmentation. Firstly, we need use non-supervised clustering for remote sensing image by using FCM; then SVM is adopted for further classification, and extract the road. Finally the comparison with two proposed algorithm was carried out, and after experiment, SVM plus FCM model is much more accurate than Markov random fields.

Keywords

Markov processes; fuzzy set theory; geophysics computing; image classification; image segmentation; learning (artificial intelligence); object detection; remote sensing; roads; simulated annealing; support vector machines; FCM; MAP-MRF framework; Markov random field; SVM; fuzzy c-mean model; hybrid model; image analysis; image segmentation; information extraction; nonsupervised clustering; remote sensing; road extraction; sampler training; simulated annealing; support vector machines; Accuracy; Clustering algorithms; Image segmentation; Markov random fields; Remote sensing; Roads; Support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Image and Data Fusion (ISIDF), 2011 International Symposium on

Conference_Location

Tengchong, Yunnan

Print_ISBN

978-1-4577-0967-8

Type

conf

DOI

10.1109/ISIDF.2011.6024291

Filename

6024291