UTILIZAÇÃO DE DADOS LASER E IMAGENS AÉREAS PARA A EXTRAÇÃO DE VIAS URBANAS

Abstract

The automatic feature extraction from digital aerial images is not a trivial solution due to occlusion problems, shadows and different viewpoints. To improve the extraction process we used laser data, which have additional information such as height and material type of objects on the surface. In this paper we performed the combination of digital image and laser data in order to improve the results of automatic extraction of urban roads. Urban roads were detected from the response of laser information. Then we applied two strategies to connect the disconnected road segments. The first one is based on the similarity of segment angle; the second one is performed by analysis of the wooded regions in the digital image. The results showed a higher sensitivity rate of 92% and positive predictive value greater than 67%.

Keywords

• Feature Extraction
• Urban Roads
• Laser Data