Selective Image Pyramid for Motion Blur in Visual Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High motion blur in visual tracking systems for AR and VR devices leads to degraded tracking performance and increased computational operations, especially during fast movements.
Innovation Solution
A method to mitigate motion blur by selectively applying the image pyramid process to select images based on an estimated motion blur level, using data from the IMU or VIO without analyzing image pixels, thereby reducing computational intensity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the image pyramid process is applied to all images to mitigate motion blur, then tracking accuracy is improved, but computational operations increase significantly
Solution Approach 1:
The patent applies the image pyramid process selectively rather than universally. It processes only those images that exhibit motion blur characteristics, determined by analyzing motion magnitude between consecutive frames. This partial application maintains tracking accuracy for problematic images while avoiding unnecessary computational overhead for clear images, directly resolving the contradiction between tracking precision and computational efficiency
2Manufacturing precision
If motion blur mitigation is applied continuously, then image quality is maintained, but processing time increases
Solution Approach 1:
The patent implements periodic assessment of motion blur conditions by calculating motion magnitude between consecutive image frames. The image pyramid process is activated only during periods when motion exceeds a threshold, rather than running continuously. This periodic evaluation and conditional activation maintains image quality when needed while minimizing processing time during normal operation
3Measurement precision
If high resolution images are processed continuously, then tracking precision is maintained, but energy consumption increases
Solution Approach 1:
The patent processes images at full resolution only when motion blur is detected through motion magnitude analysis. During periods of low or no motion, processing is reduced or skipped entirely. This selective high-resolution processing maintains tracking precision when necessary while significantly reducing energy consumption during steady-state operation
Data Source
AI summary
A method for mitigating motion blur in a visual tracking system is described. In one aspect, a method for selective motion blur mitigation in a visual tracking system includes accessing a first image generated by an optical sensor of the visual tracking system, identifying camera operating parameters of the optical sensor during the optical sensor generating the first image, determining a motion of the optical sensor during the optical sensor generating the first image, determining a motion blur level of the first image based on the camera operating parameters of the optical sensor and the motion of the optical sensor, and determining whether to downscale the first image using a pyramid computation algorithm based on the motion blur level.