Map generation method and system based on crowdsourcing data open scene

Abstract

The invention provides a map generation method and system based on a crowdsourcing data open scene, and the method comprises the steps: carrying out the time synchronization of extracted semantic information and gps track information, and generating a track line; performing big data aggregation processing on a lane line in the semantic information to generate a lane boundary line and a road boundary line; grouping the lane side lines through the track lines and the road boundary lines to generate road intervals; detecting an intersection interval according to the relative position relationshipbetween the trajectory and the road interval; constructing a road-level topological relation based on the information that the trajectory passes through the road section, and generating a road vector; generating a lane-level topological relation according to the road section; performing big data aggregation processing on the traffic facilities in the semantic information according to the attributes and the position information to generate accurate positions and attributes; and associating the aggregated traffic facility information to a generated road network to obtain a map. The method has the advantages of being low in cost, rapid in composition and more accurate in topological information at the intersection.

Description

Technical field [0001] The present invention relates to the field of transportation technology, and more specifically, to a map generation method and system based on crowdsourced data open scenarios. Background technique [0002] For the lane markings, stop lines, crosswalks, traffic signs, traffic lights and other roadside and roadside traffic facilities that are included in the high-precision map data used by autonomous vehicles, as well as the connectivity relationship between roads, the horizontal and horizontal alignment between lanes Information used for path planning and driving decision-making, such as the longitudinal relationship and the relationship between traffic facilities and roads / lanes, etc.; in order to generate the above information, the existing technology usually uses traditional surveying and mapping methods, which are not only expensive in collection, but also have a long production cycle. At the same time, the topological connectivity between roads at inte...

AI Technical Summary

Problems solved by technology

[0002] Lane markings, stop lines, crosswalks, traffic signs, traffic lights and other road and roadside real traffic facilities included in the high-precision map data used by autonomous vehicles, as well as the connectivity relationship between roads, the horizontal and Information used for route planning and driving decision-making, such as vertical correlation and the correlation between traffic facilities and roads / lanes; in order to generate the above information, the existing technology usually uses traditional surveying and mapping methods, which not only have high acquisition costs, but also have a long production cycle. At the same time, the topological connection relationship between roads at the intersection is often inconsistent with the actual situation.

Images