Abstract
Abstract. The demand for 3D maps of cities and road networks is steadily growing and mobile laser scanning (MLS) systems are often the preferred geo-data acquisition method for capturing such scenes. Because MLS systems are mounted on cars or vans they can acquire billions of points of road scenes within a few hours of survey. Manual processing of point clouds is labour intensive and thus time consuming and expensive. Hence, the need for rapid and automated methods for 3D mapping of dense point clouds is growing exponentially. The last five years the research on automated 3D mapping of MLS data has tremendously intensified. In this paper, we present our work on automated classification of MLS point clouds. In the present stage of the research we exploited three features – two height components and one reflectance value, and achieved an overall accuracy of 73 %, which is really encouraging for further refining our approach.
Highlights
Point clouds acquired by mobile laser scanning (MLS) are attribute poor
We propose an approach of further exploring the height component by considering that off-ground points of urban scenes collected by a mobile laser scanner (MLS) are usually part of objects which extend in the vertical direction
To evaluate the classification results a confusion matrix was computed by confronting the class assignments to the individual points with the labels of the benchmark dataset
Summary
Point clouds acquired by MLS are attribute poor. In addition to the 3D coordinates in a local, national or regional reference system, usually only the reflectance value of each point is available in a point cloud data set. Many classification approaches rely on enriching the attribute set with RGB values from imagery, which may not always be available, and on examining the local geometric structure of a set of neighbouring points. The latter approach is based on the observation that many objects differ in shape. In a previous tentative research which aimed at exploring the height component we used the height above ground level (Zheng et al, 2017) It appeared that the height value of a point does not discriminate enough among the different classes. A building facade varies in range which may start at eight meter, or higher, depending on the urban area, while the height of a traffic sign mounted on a pole from ground level upwards does usually not exceed 3.0 metres
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
