Map Geometry Generation via Object Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing digital maps face challenges in accurately generating and updating road and lane geometry due to missing or erroneous data, which can impact route guidance and semi-autonomous vehicle control.
Innovation Solution
The method involves receiving a rasterized image representing map geometry, applying an object detection model such as YOLO to identify bounding boxes and classes of objects, and generating map data from these detections to update a map database.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manual verification and correction methods are used for map geometry, then accuracy can be maintained, but productivity is reduced and time consumption increases
Solution Approach 1:
The patent replaces manual mechanical verification processes with an automated computer vision system. The object detection model automatically identifies and corrects map geometry errors by processing images of roadways, substituting human operators with an automated detection and correction system that maintains accuracy while significantly improving productivity
Solution Approach 2:
The map geometry correction system performs self-verification through automated object detection and validation algorithms. The system independently identifies errors, generates corrections, and validates results without requiring continuous manual intervention, enabling the system to maintain high accuracy while operating at automated speed scales
2Reliability
If manual verification and correction methods are used for map geometry, then accuracy can be maintained, but time consumption increases
Solution Approach 1:
The patent replaces time-consuming manual verification with automated object detection technology. The system processes map geometry data through computer vision algorithms that rapidly identify and correct errors, reducing the time required for map updates while maintaining the accuracy that previously required extensive manual review
Solution Approach 2:
The system performs preliminary automated detection and correction of map geometry errors before final map publication. By pre-identifying and correcting potential issues through object detection, the system eliminates the need for time-consuming post-publication manual verification, thereby reducing overall update time while maintaining high accuracy standards
Data Source
AI summary
A method is provided to automatically create road and lane geometry from images representing map geometry within a geographical area using object detection. Methods may include: receiving a rasterized image representative of map geometry within a geographic area, where each pixel of the rasterized image includes a property representing at least one component of the map geometry; applying an object detection model to the rasterized image; generating a list of the bounding boxes together with classes of objects within the bounding boxes based on the object detection model; generating map data from the list of bounding boxes and the classes of objects within the bounding boxes; and updating a map in a map database with the map data.