Title :
Hierarchical classification-based radon road extraction (HCBRRE)
Author :
Sellaouti, Aymen ; Rojbani, H. ; Hamouda, A. ; Wemmert, Cedric ; Deruyver, Aline
Author_Institution :
Lab. of Comput. in Program., Algorithmic & Heuristic, Campus Univ. Tunisia, Tunis, Tunisia
Abstract :
A hierarchical classification based road extraction approach is proposed in this paper. In order to extract road network, a spectral based-classification associates a confidence score to each region in the image. This score is used to extract road region and its constraints for each iteration of the hierarchy. Road localization is based on Radon transform and expert knowledge. The quality assessments in urban area images show the benefits of the introduced approach.
Keywords :
Radon transforms; feature extraction; image classification; roads; traffic engineering computing; HCBRRE; Radon transform; expert knowledge; hierarchical classification-based radon road extraction; quality assessments; road localization; road network extraction; road region extraction; spectral based-classification; urban area images; Accuracy; Equations; Feature extraction; Image resolution; Image segmentation; Roads; Transforms; Collaboration; Radon transform; Road extraction;
Conference_Titel :
Control Automation Robotics & Vision (ICARCV), 2012 12th International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
978-1-4673-1871-6
Electronic_ISBN :
978-1-4673-1870-9
DOI :
10.1109/ICARCV.2012.6485190
