Electronic Map Updating with Image Matching for Precise Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for updating electronic maps for autonomous driving face challenges in achieving high precision and comprehensive coverage, with traditional on-site surveying providing limited coverage and slow update speed, while data collection from vehicles results in low precision due to lack of specialized equipment and reliance on low-end image collection.
Innovation Solution
The solution involves collecting images and characteristics of map elements using special surveying and mapping vehicles or equipment, which are then processed to create a visual layer of the electronic map, incorporating inter-group and intra-group matching to improve positioning precision and enable continuous updates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional on-site surveying and mapping is used, then mapping precision is high, but coverage is limited and update speed is slow
Solution Approach 1:
The patent combines the advantages of both traditional surveying (high precision through specialized equipment) and vehicle-based data collection (wide coverage and fast update) into a unified system. The surveying vehicle collects high-precision reference data while regular vehicles provide coverage data, and these are integrated through the matching module to achieve both precision and speed.
Solution Approach 2:
The patent introduces a computing device as an intermediary that processes and matches data from multiple sources. The computing device performs inter-group matching between surveying vehicle data and regular vehicle data, and intra-group matching within regular vehicle data, acting as a mediator to reconcile precision requirements with coverage needs.
2Productivity
If data is collected from vehicles traveling on roads, then update speed is fast and coverage is wide, but precision is low
Solution Approach 1:
The patent implements a feedback mechanism where regular vehicle data is continuously collected and matched against high-precision surveying vehicle reference data. The matching module provides feedback by identifying discrepancies and using the precise reference data to correct and validate the regularly collected data, thereby improving precision while maintaining fast update speeds.
Solution Approach 2:
The patent changes the parameters of regular vehicles by equipping them with image collecting entities and enabling them to participate in the mapping process. By transforming regular vehicles from passive traffic participants to active data collectors with image capture capabilities, the system improves precision without sacrificing the speed and coverage advantages of using existing vehicle traffic.
3Measurement precision
If specialized surveying and mapping equipment is used, then mapping precision is high, but device complexity and cost increase
Solution Approach 1:
The patent segments the mapping system into two distinct components: a surveying vehicle with specialized high-precision equipment that collects reference data, and regular vehicles with simpler image collecting entities that provide coverage data. This segmentation allows the complex equipment to be used only where necessary for establishing precision benchmarks, while the majority of the system uses simpler, more affordable components.
Data Source
Figure 1
Figure 2
Figure 3~5
AI summary
Illustrative embodiments according to the disclosure provide a method, apparatus, and computer readable storage medium for updating an electronic map. A method for updating an electronic map includes: acquiring a group of collected images collected by a collection entity and associated with a target map element in the electronic map, the target map element having a target image and a target location; executing inter-group matching between the group of collected images and the target image; executing intra-group matching among the group of collected images; and updating a location of a to-be-updated map element associated with the target map element based on the inter-group matching, the intra-group matching and the target location. In this way, the positioning precision of map elements can be improved.