Dynamic Database Construction for Vehicle Positioning
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current vehicle positioning methods, such as GPS and visual positioning, face inaccuracies due to external environment changes, leading to mismatches in scenario key points and descriptor information, resulting in inaccurate positioning.
Innovation Solution
A database construction method that selects target image sets based on preset coincidence degree requirements, determines scenario key point information, and updates the database with second scenario key point information to ensure accurate matching and positioning, using 3D coordinates, pixel coordinates, and dynamic descriptor information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If visual positioning is performed using a database with scenario key points and descriptor information, then positioning capability is provided, but positioning precision deteriorates when external environment changes cause descriptor information to change
Solution Approach 1:
The patent applies dynamics by making the database structure adaptable to environmental changes. Instead of using static descriptor information, the system dynamically updates the database with new descriptor information extracted from real-time images when environmental conditions change. This allows the positioning system to maintain precision by adapting to varying natural conditions while preserving positioning capability.
Solution Approach 2:
The patent changes the parameter of descriptor information from static to dynamic. When external environment changes are detected, the system extracts new descriptor information from current images and updates the database accordingly. This parameter change enables the system to maintain both positioning capability and precision under varying environmental conditions.
2Productivity
If scenario key point matching is performed without considering natural condition variations, then processing speed is maintained, but positioning precision deteriorates due to mismatches
Solution Approach 1:
The patent applies preliminary action by pre-processing images to extract descriptor information and building the database before actual positioning operations. When environmental changes occur, the system performs preliminary updates to the database with new descriptor information, ensuring that subsequent positioning operations can proceed quickly with accurate matching without sacrificing precision.
Data Source
AI summary
A database construction method includes determining a target image set that meets a preset image coincidence degree requirement, obtaining a scenario key point information set based on the target image set and natural condition information corresponding to each image, determining, in the scenario key point information set, first scenario key point information corresponding to a scenario key point whose life value on a single mobile terminal is greater than a first preset life value threshold, determining, in the first scenario key point information, second scenario key point information corresponding to a scenario key point whose life value on a plurality of mobile terminals is greater than a second preset life value threshold, and when the second scenario key point information does not match preset scenario key point information in a database, constructing the database based on the second scenario key point information.