Descrizione della tesi

See IRALAB website.

The project involves the insertion of the point cloud generated by Velodyne in Openstreetmap maps. The activity is aimed at improving the location of the vehicle itself within the map, taking advantage of the Road Layout Estimation framework proposed by the IRALAB research group. The work proves the adaptation and implementation of the algorithm proposed in the work “Leveraging the OSM building data to enhance the localization of an urban vehicle” and “Vehicle localization using 3D building models and Point Cloud matching”. As far as the sensory data are concerned, an initial phase is envisaged which foresees the use of data from the reference dataset KITTI and a subsequent data collection within the university campus through the use of LIDAR sensors. As far as the training objectives are concerned, the student is expected to acquire the ability to understand how to insert the point cloud in the maps using appropriate simulation systems, as well as to design a support for a LIDAR / Velodyne sensor to be mounted on the vehicle.

Tutor: Augusto Luis Ballardini
Advisor: Domenico Giorgio Sorrenti
Completion Date: 2018
University link