HD Map Updating from 2D Vehicle Images and Local Landmark Maps
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for updating high definition maps for autonomous driving are inefficient, requiring expensive equipment and time-consuming processes to reflect changes in road infrastructure and traffic policies.
Innovation Solution
A method and apparatus using a normal vehicle equipped with a general image photographing device, such as a camera, to capture two-dimensional images of target areas, generate three-dimensional local landmark maps, and update the high definition map, eliminating the need for high-performance equipment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a mobile mapping system vehicle with high definition sensors is used to update the high definition map, then the map accuracy is improved, but the time and effort required for updates increases significantly
Solution Approach 1:
The patent uses two-dimensional images captured by ordinary cameras to create copies or representations of the three-dimensional road environment. By processing these 2D images through coordinate transformation and feature point matching, the system generates update information for the HD map without requiring physical presence of specialized mapping vehicles at the update location
Solution Approach 2:
The patent replaces the mechanical system of physical vehicle traversal with high-definition sensors with an optical-computational system using ordinary cameras. Instead of mechanically moving specialized equipment to capture 3D data, the system uses 2D image capture followed by computational processing to achieve map updates
2Manufacturing precision
If a mobile mapping system vehicle with high definition sensors is used to update the high definition map, then the map accuracy is improved, but the equipment cost increases
Solution Approach 1:
The patent employs inexpensive, readily available camera equipment instead of expensive high-definition sensors mounted on specialized mapping vehicles. The system uses ordinary photographing devices that can be found in most vehicles, eliminating the need for costly specialized equipment while still achieving effective map updates through computational processing
3Manufacturing precision
If the MMS vehicle travels around the position to generate the high definition map again, then the map accuracy is maintained, but the operational complexity increases
Solution Approach 1:
The patent enables ordinary vehicles to contribute to HD map updates using their existing camera systems. Instead of requiring specialized MMS vehicles to physically traverse update locations, any vehicle equipped with a camera can capture images that are processed into map update information, allowing the system to self-update using data from regular traffic
4Ease of manufacture
If two-dimensional images are used to generate three-dimensional local landmark maps, then the equipment requirement is reduced, but the measurement precision may be affected
Solution Approach 1:
The patent transforms two-dimensional image data into three-dimensional spatial information through coordinate system transformations. By capturing images at multiple positions and orientations, the system reconstructs 3D landmark positions from 2D projections, effectively adding dimensional information through computational methods rather than physical 3D sensing equipment
Data Source
AI summary
A method for updating a high definition map according to one embodiment comprises: obtaining a two-dimensional image that captures a target area corresponding to at least a part of an area expressed by a three-dimensional high definition map, generating a three-dimensional local landmark map of the target area from a position of a landmark in the two-dimensional image, based on a position and an orientation of a photographing device which has captured the two-dimensional image and updating the high definition map with reference to the local landmark map corresponding to the target area of the three-dimensional high definition map.