Automatic main road extraction from high resolution satellite imageries by means of self-learning fuzzy-GA algorithm

被引：6

作者：

Mohammadzadeh, A. ^{[1
]}

Valadan Zoej, M.J. ^{[1
]}

Tavakoli, A. ^{[2
]}

机构：

[1] Department of Remote Sensing, K.N. Toosi University of Technology, Tehran

[2] Department of Electrical Engineering, Amirkabir University, Tehran

来源：

Journal of Applied Sciences | 2008年 / 8卷 / 19期

关键词：

Continuous genetic algorithm; Fuzzy logic; IKONOS; Image segmentation; Mathematical morphology; Road centerline extraction;

D O I：

10.3923/jas.2008.3431.3438

中图分类号：

学科分类号：

摘要：

In this study, using few samples from road surface, a continuous genetic algorithm is applied to a fuzzy based mean calculation system to obtain road mean values in each band of high resolution satellite colour images. Then, the images are segmented using the calculated mean values from the self-learning fuzzy-GA system. The proposed self-learning fuzzy-GA algorithm calculated best mean value with sub grey level precision. The method is applied to simulated images where the calculated mean values are consistent with the hypothetic mean values. Application of the method to IKONOS satellite images has shown a prospective outcome. Mathematical morphology is subsequently used to extract an initial main road centerline from the segmented image. Then, small redundant segments are automatically removed. The quality of the extracted road centerline indicates the effectiveness of the proposed approach. © 2008 Asian Network for Scientific Information.

引用

页码：3431 / 3438

页数：7

共 11 条

[1]

Agouris P., Gyftakis S., Stefanidis A., Using a fuzzy supervisor for object extraction within an integrated geospatial environment, Int. Arch. Photogram. Remote Sens., 32, pp. 191-195, (1998)

[2]

Amini J., Saradjian M.R., Blais J.A.R., Lucas C., Azizi A., Automatic road-side extraction from large scale image maps, Int. J. Applied Earth Observ. Geoinform., 4, pp. 95-107, (2002)

[3]

Baltsavias E.P., Object extraction and revision by image analysis using existing geodata and knowledge: Current status and steps towards operational systems, ISPRS J. Photogrammetry Remote Sens., 58, pp. 129-151, (2004)

[4]

Haupt R.L., Haupt S.E., Practical Genetic Algorithms, (2004)

[5]

Mena J.B., State of the art on automatic road extraction for GIS update: A novel classification, Pattern Recog. Lett., 24, pp. 3037-3058, (2003)

[6]

Mena J.B., Malpica J.A., An automatic method for road extraction in rural and semi-urban areas starting from high resolution satellite imagery, Pattern Recognit. Lett., 26, pp. 1201-1220, (2005)

[7]

Mohammadzadeh A., Tavakoli A., Valadan Zoej M.J., Road extraction based on fuzzy logic and mathematical morphology from pan-sharpened IKONOS images, The Photogram. Record, 21, pp. 44-60, (2006)

[8]

Mokhtarzade M., Valadan Zoej M.J., Road detection from high resolution satellite images using artificial neural networks, Int. J. Applied Earth Observ. Geoinform., 9, pp. 32-40, (2007)

[9]

Mokhtarzade M., Ebadi H., Valadan Zoej M.J., Optimization of road detection from high-resolution satellite images using texture parameters in neural network classifiers, Can. J. Remote Sens., 33, pp. 481-491, (2007)

[10]

Quackenbush L.J., A review of techniques for extracting linear features from imagery, Photogram. Eng. Remote Sens., 70, pp. 1383-1392, (2004)

← 1 2 →