Abstract
Abstract. Road databases are essential instances of urban infrastructure. Therefore, automatic road detection from sensor data has been an important research activity during many decades. Given aerial images in a sufficient resolution, dense 3D reconstruction can be performed. Starting at a classification result of road pixels from combined elevation and optical data, we present in this paper a fivestep procedure for creating vectorized road networks. These main steps of the algorithm are: preprocessing, thinning, polygonization, filtering, and generalization. In particular, for the generalization step, which represents the principal area of innovation, two strategies are presented. The first strategy corresponds to a modification of the Douglas-Peucker-algorithm in order to reduce the number of vertices while the second strategy allows a smoother representation of street windings by Bezir curves, which results in reduction – to a decimal power – of the total curvature defined for the dataset. We tested our approach on three datasets with different complexity. The quantitative assessment of the results was performed by means of shapefiles from OpenStreetMap data. For a threshold of 6 m, completeness and correctness values of up to 85% were achieved.
Highlights
AND RELATED WORKFor a large number of both civil and military applications, roads are an essential part of urban infrastructure
Minimum cost paths are formed between superpixels of very low data cost. This is done in order to identify potential roads even though a little number of paths’ superpixels is occluded and exhibits high data energy. These paths are input of the non-local optimization based on Conditional Random Fields (CRFs) which makes up the fourth, final step of the procedure
We presented a fully automatic approach for the road vectorization and generalization
Summary
For a large number of both civil and military applications, roads are an essential part of urban infrastructure. Hough transform is applied to extract arks from these pixels In this approach, the classification is considered during the step of ground points extraction, and in order to compute the features separating road pixels from the rest. In (Mena, 2006), starting from the binary image R representing road pixels, the road centerlines are supposed to have the same distance to at least two points of R This method is very sensitive to the classification results. Even the pioneering approach on road classification, stemming from (Wegner et al, 2015), cannot prevent that in final result, some trees occlude parts of roads Because of these two reasons, the second way, namely, a post-processing routine of the remaining roads appears to be a promising method.
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
