Visual-Inertial Eyewear Tracking with Adaptive Rolling-Shutter Camera Poses
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Rolling shutter cameras capture images with varying times due to scanning, leading to artifacts when there is relative movement between the camera and the scene, affecting the accuracy of visual-inertial tracking.
Innovation Solution
Adjust the number of poses calculated based on the movement of the eyewear device, using a rolling shutter camera, to optimize processing resources and maintain accurate tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the number of poses calculated is increased to improve tracking accuracy, then measurement precision improves, but use of energy increases
Solution Approach 1:
The system dynamically adjusts the number of poses calculated based on the detected movement magnitude. When movement is detected to be slow or minimal, the system reduces the number of poses calculated, conserving processing resources. When movement is significant, the system increases the number of poses to maintain tracking accuracy. This dynamic adaptation resolves the contradiction by making the computational effort proportional to the actual tracking needs.
Solution Approach 2:
The system changes the parameter of pose calculation quantity based on movement conditions. By detecting relative movement between the camera and scene, the system adjusts the number of poses calculated as a variable parameter. This allows the system to optimize between tracking accuracy and processing resource consumption by adapting the calculation intensity to the actual motion state.
2Measurement precision
If poses are calculated frequently to maintain tracking accuracy during movement, then measurement precision improves, but productivity decreases
Solution Approach 1:
The system implements periodic pose calculation adjusted by movement detection. Instead of calculating poses at every possible moment, the system periodically evaluates movement and only triggers intensive pose calculations when necessary. This periodic action with conditional triggering maintains tracking accuracy while improving overall processing efficiency by avoiding unnecessary computations during stable periods.
Solution Approach 2:
The system applies partial action by calculating only the necessary number of poses based on detected movement. When movement is slow or absent, fewer poses are calculated (partial action), conserving processing resources. When movement is significant, the system increases calculations to maintain accuracy. This selective approach optimizes the balance between tracking precision and processing productivity.
Data Source
AI summary
Visual-inertial tracking of an eyewear device using a rolling shutter camera(s). The device includes a position determining system. Visual-inertial tracking is implemented by sensing motion of the device. An initial pose is obtained for a rolling shutter camera and an image of an environment is captured. The image includes feature points captured at a particular capture time. A number of poses for the rolling shutter camera is computed based on the initial pose and sensed movement of the device. The number of computed poses is responsive to the sensed movement of the mobile device. A computed pose is selected for each feature point in the image by matching the particular capture time for the feature point to the particular computed time for the computed pose. The position of the mobile device is determined within the environment using the feature points and the selected computed poses for the feature points.