Camera-Marker Vehicle Positioning for Indoor Drift Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing positioning systems for moving bodies, such as vehicles, struggle with accuracy in indoor environments due to the reliance on wireless signals or methods like Pedestrian Dead Reckoning, which lead to cumulative errors, especially in varying backgrounds like factories and warehouses.
Innovation Solution
A positioning apparatus using an image capturing apparatus with a first calculator to determine relative position and attitude, a storage apparatus for marker information, a second calculator to extract markers from images, and a corrector to adjust positions and attitudes based on reliable marker data, ensuring accurate positioning and attitude correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If Visual-SLAM is used to calculate relative position without wireless transmitters, then initial costs are reduced, but error accumulates with lapse of time
Solution Approach 1:
The patent introduces markers as intermediary objects placed in the environment to serve as reference points for position correction. These markers act as a mediator between the Visual-SLAM system and the actual position, allowing the system to correct cumulative errors without requiring a dense network of wireless transmitters. The markers provide absolute position references that reset the error accumulation cycle.
Solution Approach 2:
The system implements feedback by continuously comparing the position estimated by Visual-SLAM with the position calculated from marker observations. When markers are detected, the system uses this information to correct the accumulated error in the Visual-SLAM position estimate, creating a feedback loop that maintains long-term positioning accuracy without requiring additional infrastructure.
2Measurement precision
If markers are used to correct position, then positioning accuracy is improved, but device complexity increases
Solution Approach 1:
The system employs self-service by using the existing image capturing apparatus originally intended for Visual-SLAM to also detect and process marker information. The same camera and processing unit that perform visual navigation also automatically detect markers and calculate correction positions, eliminating the need for separate detection hardware and reducing overall system complexity.
Solution Approach 2:
The image capturing apparatus is designed with multi-functionality, serving both Visual-SLAM navigation and marker detection purposes. This universal approach allows a single device to perform multiple functions, avoiding the need for separate specialized hardware for each function and thereby reducing system complexity while maintaining positioning accuracy.
3Measurement precision
If markers at all positions are used for correction, then positioning accuracy is maximized, but calculation time increases
Solution Approach 1:
The system extracts and uses only the necessary subset of marker information for correction. Instead of processing data from all markers at all positions, the system selectively uses markers that are actually observed by the image capturing apparatus at each moment, extracting only the relevant correction data needed for current position estimation and discarding unnecessary information.
Solution Approach 2:
The system applies partial action by using only the portion of marker data that is currently observable and relevant, rather than processing complete information from all possible marker positions. This selective approach reduces calculation time by focusing computational resources on the subset of markers that actually contribute to the current position correction.
Data Source
AI summary
A first calculator calculates relative position and attitude of a vehicle based on images captured by an image capturing apparatus on the vehicle. A second calculator extracts one marker from a captured image, calculates absolute position and attitude of the vehicle based on a position and an attitude of the one extracted marker, and calculates an angle of a direction of the vehicle 1 with respect to a normal line to a plane of the one marker 4 based on a position and an attitude of the vehicle 1 in a marker coordinate system. A corrector generates a corrected position and attitude, not using the absolute position and attitude calculated based on the marker for which the angle is not larger than a first threshold, but using the absolute position and attitude calculated based on the marker for which the angle is larger than the first threshold.