AR Glasses Positioning via Cabin Boundary Feature Separation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing vehicle control systems using AR glasses struggle to accurately specify the position of the glasses due to the mixture of feature points from inside and outside the vehicle cabin, leading to insufficient accuracy in positioning.
Innovation Solution
A vehicle control device that includes an extraction unit to extract feature points from the detection range of a sensor in AR glasses, a determination unit to differentiate between feature points based on movement vector discontinuity when the vehicle moves, and a specifying unit to accurately determine the position of the AR glasses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all feature points extracted from the sensor detection range are used to specify the position of AR glasses, then the quantity of data for position calculation is increased, but the accuracy of specifying the position of AR glasses becomes significantly insufficient due to mixture of inside and outside cabin feature points
Solution Approach 1:
The patent divides the detection range into two distinct regions: a first region corresponding to the inside of the vehicle cabin and a second region corresponding to the outside of the vehicle cabin. This segmentation allows the system to separately process feature points from each region, using only the feature points from the second region (outside cabin) for AR glasses position calculation, thereby eliminating the negative impact of inside cabin feature points on positioning accuracy.
Solution Approach 2:
The determination unit extracts and identifies feature points that correspond to objects outside the vehicle cabin by analyzing movement vector discontinuities. This extraction process separates the useful feature points (from outside cabin) from the harmful feature points (from inside cabin), allowing the specifying unit to use only the extracted valid feature points for accurate position calculation.
2Ease of operation
If feature points from both inside and outside vehicle cabin are mixed in position calculation, then the system can operate with simpler processing, but the positioning accuracy becomes significantly insufficient
Solution Approach 1:
The detection range is segmented into inside-cabin and outside-cabin regions, allowing the system to automatically distinguish and separate feature points from each region. This segmentation maintains operational simplicity while improving accuracy by ensuring that only relevant outside-cabin feature points are used in position calculations.
Solution Approach 2:
The determination unit acts as an intermediary between the extraction unit and the specifying unit. It processes the raw feature points by identifying movement vector discontinuities to determine which feature points correspond to outside cabin objects, thereby filtering the data before passing it to the specifying unit for position calculation.
3Area of stationary object
If the sensor detection range includes both inside and outside vehicle cabin areas, then the coverage area is increased, but the reliability of position specification deteriorates due to feature point mixture
Solution Approach 1:
The patent maintains a wide sensor detection coverage that includes both inside and outside cabin areas, then segments the detected feature points into two categories based on their spatial location and movement characteristics. This allows the system to utilize the broad coverage for comprehensive scene understanding while ensuring that only reliable outside-cabin feature points contribute to position specification, thereby maintaining both coverage and reliability.
Data Source
AI summary
An extraction unit of a mobile terminal extracts a plurality of feature points from within a shooting range of a camera, based on shooting results of the camera provided on AR glasses. A determination unit determines a boundary between a first region corresponding to an inside of a vehicle cabin and a second region corresponding to an outside of the vehicle cabin within the shooting range of the camera based on discontinuity of movement vectors of the feature points when a vehicle moves. A specifying unit specifies a position of the AR glasses based on a determination result by the determination unit.