Vehicle Image Positioning With Marker-Based Drift Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
In environments with varying backgrounds, such as factories and warehouses, it is challenging to accurately determine the current position of a moving body using pre-created maps, as errors in position calculation cumulatively increase over time with Visual-SLAM systems.
Innovation Solution
A positioning apparatus equipped with a first calculator for relative position and attitude calculation based on captured images, a storage apparatus for marker information and map data, a second calculator for extracting markers and calculating absolute positions and attitudes, and a corrector that adjusts the relative position and attitude using the absolute data, while considering the reliability of the marker recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If Visual-SLAM is used to calculate relative position based on captured images, then the positioning system does not require wireless transmitters and can operate indoors, but cumulative errors increase with time
Solution Approach 1:
The system uses markers disposed at predetermined positions as feedback reference points. The image capturing apparatus periodically captures images of these markers, and the positioning apparatus calculates absolute position based on marker recognition, thereby correcting cumulative errors from relative position calculations
Solution Approach 2:
Markers serve as intermediary objects between the image capturing apparatus and the positioning calculation system. These markers with identifiable patterns enable the system to establish absolute position references without requiring direct complex environmental mapping
2Measurement precision
If markers are used for absolute position calculation, then positioning accuracy is improved, but the system becomes more complex
Solution Approach 1:
The markers are simple, inexpensive visual elements that can be easily disposed of or replaced. They use basic visual patterns rather than complex electronic components, reducing overall system complexity while maintaining positioning accuracy
Solution Approach 2:
The markers utilize visual distinguishability through color or pattern variations. This allows the system to identify and differentiate multiple markers using simple image processing based on color or pattern recognition, avoiding complex identification mechanisms
3Measurement precision
If the image capturing apparatus captures images at a high frequency to reduce positioning errors, then positioning accuracy is improved, but energy consumption increases
Solution Approach 1:
The image capturing apparatus captures images at periodic intervals rather than continuously. This periodic capture is synchronized with the movement of the moving body, capturing images at key moments when position updates are needed, thereby reducing energy consumption while maintaining positioning accuracy
Data Source
AI summary
A relative position calculator calculates relative position and attitude of a vehicle based on images captured by an image capturing apparatus on the vehicle. An absolute position calculator extracts a marker from an image captured by the image capturing apparatus, and calculates absolute position and attitude of the vehicle, based on position and attitude of the one extracted marker. A corrector calculates the corrected position and attitude, not using the absolute position and attitude calculated based on the position and attitude of the marker when a difference or ratio of an apparent height and width of the marker in the image is equal to or smaller than a threshold, but using the absolute position and attitude calculated based on the position and attitude of the marker when the difference or ratio is larger than the threshold.