Road extraction from aerial images using a region competition algorithm

Abstract

In this paper, we present a user-guided method based on the region competition algorithm to extract roads, and therefore we also provide some clues concerning the placement of the points required by the algorithm. The initial points are analyzed in order to find out whether it is necessary to add more initial points, and this process will be based on image information. Not only is the algorithm able to obtain the road centerline, but it also recovers the road sides. An initial simple model is deformed by using region growing techniques to obtain a rough road approximation. This model will be refined by region competition. The result of this approach is that it delivers the simplest output vector information, fully recovering the road details as they are on the image, without performing any kind of symbolization. Therefore, we tried to refine a general road model by using a reliable method to detect transitions between regions. This method is proposed in order to obtain information for feeding large-scale Geographic Information System.

Road Feature Extraction from High Resolution Aerial Images Upon Rural Regions Based on Multi-Resolution Image Analysis and Gabor Filters

“…To extract roads from aerial images, Amo et al (2006) employ the region competition algorithm, a mixed approach which combines region growing techniques with active contour models. Region growing makes the first step faster and region competition delivers more accurate results.…”

Extracting roads from dense point clouds in large scale urban environment

“…For example, common algorithmic strategies include region growing (Amo et al, 2006;Bicego et al, 2003;Hu et al, 2007;Mena and Malpica, 2005;Tesser and Pavlidis, 2000), segmentation and clustering (Ferchichi and Wang, 2005;Wan et al, 2007), machine learning (Butenuth et al, 2003;Yager and Sowmya, 2003), multi-scale extraction and refinement (Baumgartner and Hinz, 2000;Heipke et al, 1995;Mayer et al, 1998;Steger, 1998), and active contours (Laptev et al, 2000;Peng et al, 2008). These methods tend to work well in rural environments, where color and intensity is relatively distinctive and consistent within roads, and in urban environments when assumptions can be made about the structure of roads (e.g., a semi-regular grid pattern (e.g., Hu et al, 2004;Youn and Bethel, 2004)) and/or a knowledge base and carefully tuned parameters can be provided (e.g., Hinz, 2004).…”

Extended Phase Field Higher-Order Active Contour Models for Networks

“…Lacoste et al (2005) used marked point processes to model road networks, but the models were appropriate for medium resolution images; the method has not been applied to VHR images. Amo et al (2006) proposed a region competition based method for providing large-scale GIS information. Hu et al (2007) detected roads based on shape classification, and then pruned a road tree using a Bayesian decision process.…”