文章基本信息

标题：ROAD EXTRACTION IN A VERY HIGH RESOLUTION IMAGE BASED ON HOUGH TRANSFORMATION AND LOCAL BINARY PATTERNS
本地全文：下载
作者：ZAAJ IBTISSAM ; BRAHIM EL KHALIL CHAOUKI ; LHOUSSAINE MASMOUDI 等
期刊名称：Journal of Theoretical and Applied Information Technology
印刷版ISSN：1992-8645
电子版ISSN：1817-3195
出版年度：2016
卷号：91
期号：1
出版社：Journal of Theoretical and Applied
摘要：Recently, many approaches have been presented for automatic urban road extraction. Most of these approaches are based on line detecting algorithms. This paper present a new method of road extraction from high resolution image in urban areas, based on Hough Transformation and Local Binary Patterns. The Hough Transformation method has proven important results to straight line extraction, but it still not sufficient to distinguish between road and others objetcs are similar spectral reflectance (building, parking lots, square and other built-up areas) making road extraction intrinsically difficult. However the Local Binarry Patterns (LBP) seems to be a promising method, it compare the luminance level of a pixel with the levels of its neighbors. This therefore reflects information on regular patterns in the image what is called a texture. The main contribution of this work is using the LBP operator in the road extraction. We applied our system on a set of satellite imagery, the combination of the LBP operator and Hough transformation provide empirical results illustrating the effectiveness of our approach. Furthermore, we compared the proposed method with other existing method in the literature. We conclude that the proposed method can provide an effective means for extracting roads over densely populated urban areas from VHR satellite images.
关键词：Road detection; Local Binary Patterns; Hough transformation; Contour.