IMPROVEMENT OF MOBILE LIDAR DATA CLASSIFICATION OF URBAN ROAD ENVIRONMENT USING MACHINE LEARNING ALGORITHMS

Abstract

3D road mapping is essential for intelligent transportation system in smart cities. Road features can be utilized for road maintenance, autonomous driving vehicles, and providing regulations to drivers. Currently, 3D road environment receives its data from Mobile LIDAR Scanning (MLS) systems. MLS systems are capable of rapidly acquiring dense and accurate 3D point clouds, which allow for effective surveying of long road corridors. They produce huge amount of point clouds, which require automatic features classification algorithms with acceptable processing time. Machine learning (ML) algorithms are widely used for predicting the future or classifying information to help policymakers in making necessary decisions. This prediction comes from a pre-trained model on a given data consisting of inputs and their corresponding outputs of the same characteristics. In this research, an attempt to extract some road features from MLS point cloud using proper ML classifier, and evaluation of different steps entire the method