A camera-based automated precision road map generation system and method

Abstract

A camera-based automated precision road map generation system according to one embodiment is disclosed in the present document. An object recognition unit recognizes a road facility object including at least one of a GCP object and a general object and an attribute in units of frames of the road image; a feature point extraction unit extracts feature points of at least one or more road facility objects from the road image; a feature point tracking unit matches and tracks the feature points in successive frames of the road image; a coordinate determination unit acquires the relative space coordinates of the feature points so as to minimize the difference between the camera attitude information predicted from the tracked feature points and the calculated camera attitude information; when the GCP object is recognized, the correction unit corrects the target space coordinates of the feature point on the basis of the coordinate point of the GCP object, the absolute space coordinates of which are known, so as to acquire the absolute space coordinates of the feature point.

Description

technical field [0001] Various embodiments disclosed in this document relate to techniques for automatically generating and updating sophisticated road maps based on cameras for autonomous driving. Background technique [0002] For safe autonomous driving, an autonomous vehicle can recognize the surrounding environment of the vehicle and the position of the vehicle, and based on the recognized information, generate a route that enables the vehicle to travel safely and efficiently. Additionally, the autonomous vehicle can control the steering and speed of the vehicle according to the generated path. [0003] Self-driving vehicles can use onboard sensors (for example, cameras, laser scanners, radars, GNSS (Global Navigation Satellite System), IMU (Inertial Measurement Unit), etc.) to monitor the surrounding environment of the vehicle (for example, road facilities such as lanes and signal lights) or landmarks) and generate a path based on the recognized surrounding environment...

AI Technical Summary

Problems solved by technology

It will consume a lot of manpower and cost when using this MMS device to build and update the precise route map

In particular, when the state of the road changes, the precise route map cannot be updated quickly, so it becomes a safety hazard for vehicles that rely on the precise route map for automatic driving

Images