Abstract
Dynamic objects appearing on the road without notice can cause serious accidents. However, the detection ranges of roadside unit and CCTV that collect current road information are very limited. Moreover, there are a lack of systems for managing the collected information. In this study, a dynamic mapping system was implemented using a connected car that collected road environments data continuously. Additionally, edge-fog-cloud computing was applied to efficiently process large amounts of road data. For accurate dynamic mapping, the following steps are proposed: first, the classification and 3D position of road objects are estimated through a stereo camera and GPS data processing, and the coordinates of objects are mapped to a preset grid cell. Second, object information is transmitted in real time to a constructed big data processing platform. Subsequently, the collected information is compared with the grid information of an existing map, and the map is updated. As a result, an accurate dynamic map is created and maintained. In addition, this study verifies that maps can be shared in real time with IoT devices in various network environments, and this can support a safe driving milieu.
Highlights
Traffic accidents or the appearance of unpredictable dynamic objects on the road are a major threat to safe driving
This study proposes a system for managing dynamic object information on roads based on the edge-fog-cloud computing platform was proposed
Accurate dynamic maps were obtained by collecting information on connected cars that sense changes in the road environment in real time and performing grid-based mapping
Summary
Traffic accidents or the appearance of unpredictable dynamic objects on the road are a major threat to safe driving. Several other researchers have created roadmaps that process raw data from sensors Their information, which was collected at each coordinate system using multiple vehicles, could not be integrated into a single map. To solve this problem, we propose an edge-fog-cloud computing-based road dynamic object-mapping system. Dynamic map information stored in the fog database is transmitted to connected cars located in the same area so that multiple drivers can be updated in advance with road environment information that can enhance safe driving and the ability to respond to changes in road conditions. A grid-based information mapping method is proposed to display dynamic objects collected from a heterogeneous vehicle into a single map. This method makes real-time location estimation possible with onboard systems because this approach is simple compared to fusing LiDAR camera data
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
