Map data calibration method and device and computer equipment

Abstract

The invention provides a map data calibration method and device and computer equipment, and the method comprises the steps of: acquiring data points on a plurality of lane center lines in different geographic grids and respective endpoint data and other to-be-calibrated map data, then according to a lane driving direction, matching the near-end endpoint data on the lane center lines in two adjacent geographic networks, determining a connection relationship among a plurality of lane center lines in different geographic grids, and for a to-be-calibrated lane center line in the plurality of lane center lines with the connection relationship, and automatically calibrating an original guide line by using a plurality of adjacent data points on the to-be-calibrated lane center line. Therefore, the guide line in the finally obtained target map data is smooth, manual screening of defect map data is not needed, real vehicle testing is not needed, the labor, time and capital cost is greatly reduced, the method is not restricted by an implementation site any more, and the map data calibration efficiency and precision are improved.

Description

technical field [0001] This application mainly relates to the application field of intelligent driving, and more specifically relates to a map data calibration method, device and computer equipment. Background technique [0002] With the popularization of intelligent driving, the problem of traffic congestion has been greatly improved, and production efficiency and traffic efficiency have been improved. In the actual driving process of the vehicle, it is usually based on high-precision map data to assist in guiding the vehicle's driving route, such as generating a corresponding navigation route based on the driving start position and end position, and during driving on the navigation route, especially Especially in special scenarios such as encountering a fork in the road, turning around, etc., the map can also generate corresponding guide lines, which can more intuitively and clearly guide the driving direction of the vehicle and avoid taking the wrong route, which is very ...

AI Technical Summary

Problems solved by technology

At present, manual screening and actual vehicle inspection are usually used to determine defective map data, such as data points that cause the corners of the guide line to be hard and not smooth, etc., the labor, time and capital costs are high, and the map data is calibrated The efficiency and accuracy are very low, and other equipment is needed to cooperate to realize it, which leads to great limitations in the implementation process

Images