V této práci řešíme problém správné registrace mraků bodů z LIDARu do společné reprezentace scény, což je důležité pro navigaci autonomních vozidel. Přicházíme s novou reprezentací 3D scény vhodnou pro agregování dat z LIDARu, která je založena na diskrétní distribuci pravděpodobnosti bodů v prostoru. Představujeme online algoritmus pro robustní registraci mraků bodů za účelem zpřesnění egomotion. Poté je tato metoda otestována na dvou datasetech z reálných jízd.In this thesis, we investigate the problem of registering LIDAR point clouds to a common representation of a scene. This is necessary for autonomous vehicle navigation. A representation of a 3D scene suitable for aggregation of LIDAR data is proposed, based on discrete probability d...
In the race for autonomous vehicles and advanced driver assistance systems (ADAS), the automotive in...
With its prospects of reducing vehicular accidents and traffic in highly populated urban areas by ta...
Intelligent vehicles require perception systems with high performances. Usually, perception system c...
When 3D laser scanning (LIDAR) is used for navigation of autonomous vehicles operated on unstructure...
In this paper we propose an end-to-end, automatic, online camera-LIDAR calibration approach, for ap...
In this paper we propose an end-to-end, automatic, online camera-LIDAR calibration approach, for app...
Proceedings of: 2019 IEEE Intelligent Transportation Systems Conference (ITSC)LiDAR devices have bec...
A key component for automated driving is 360◦ environment detection. The recognition capabilities of...
The registration of point clouds in urban environments faces problems such as dynamic vehicles and p...
In this paper we present a novel approach to quickly obtain detailed 3D reconstructions of large sca...
The current state of the art of traffic tracking is based on the use of video, and requires extensiv...
Navrhli jsme dvě lokální metody pro rozšíření datasetu: Vložení a Simulace pohybu. Vložení přidává d...
Autonomous vehicles (AVs) must perceive and understand the 3D environment around them. Modern autono...
3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can gener...
As technology advances, cities are getting smarter. Smart mobility is the key element in smart citie...
In the race for autonomous vehicles and advanced driver assistance systems (ADAS), the automotive in...
With its prospects of reducing vehicular accidents and traffic in highly populated urban areas by ta...
Intelligent vehicles require perception systems with high performances. Usually, perception system c...
When 3D laser scanning (LIDAR) is used for navigation of autonomous vehicles operated on unstructure...
In this paper we propose an end-to-end, automatic, online camera-LIDAR calibration approach, for ap...
In this paper we propose an end-to-end, automatic, online camera-LIDAR calibration approach, for app...
Proceedings of: 2019 IEEE Intelligent Transportation Systems Conference (ITSC)LiDAR devices have bec...
A key component for automated driving is 360◦ environment detection. The recognition capabilities of...
The registration of point clouds in urban environments faces problems such as dynamic vehicles and p...
In this paper we present a novel approach to quickly obtain detailed 3D reconstructions of large sca...
The current state of the art of traffic tracking is based on the use of video, and requires extensiv...
Navrhli jsme dvě lokální metody pro rozšíření datasetu: Vložení a Simulace pohybu. Vložení přidává d...
Autonomous vehicles (AVs) must perceive and understand the 3D environment around them. Modern autono...
3D LiDAR scanners are playing an increasingly important role in autonomous driving as they can gener...
As technology advances, cities are getting smarter. Smart mobility is the key element in smart citie...
In the race for autonomous vehicles and advanced driver assistance systems (ADAS), the automotive in...
With its prospects of reducing vehicular accidents and traffic in highly populated urban areas by ta...
Intelligent vehicles require perception systems with high performances. Usually, perception system c...