Road detection in the purpose of traffic micro simulationbased on support vector machines

Traffic micro simulation models simulate the behavior of individual vehicles within a predefined road andare used to predict the likely impact of changes in traffic patterns resulting from changes to traffic flow orchanges to the physical environment. In this paper we used Support Vector Machine (SVM) to detectroads in raster format, so it could be used in traffic micro simulation. Our features for training SVM wereproduced from digital aerial images and LiDAR data. Evaluation showed that the road in the test area wasdetected with 85% completeness.

کلیدواژه ها:

LiDAR ، Road detection ، SVM ، Traffic micro simulation