Adaptive AR Image Processing With Dynamic Crop-and-Scale Ordering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image processing techniques for augmented reality (AR) devices are computationally expensive and may yield unsatisfactory results due to indiscriminate scaling or cropping of images, which can affect the accuracy of object tracking.
Innovation Solution
An adaptive image processing technique dynamically determines the crop-and-scale order based on object tracking parameters, such as historic tracking data and device motion, to generate optimized images for object tracking systems.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If indiscriminate scaling or cropping of images is performed, then image processing is simplified, but object tracking accuracy deteriorates
Solution Approach 1:
The patent implements dynamic determination of crop-and-scale order based on real-time object tracking parameters. The system switches between different processing orders (crop-then-scale vs. scale-then-crop) depending on current tracking conditions, making the image processing pipeline adaptive rather than static. This resolves the contradiction by allowing simplified processing when appropriate while maintaining accuracy when needed.
Solution Approach 2:
The system changes the processing parameters (order of crop and scale operations) based on object tracking parameters such as historic tracking data and device motion. By adjusting these parameters dynamically, the system optimizes the balance between processing simplicity and tracking accuracy for different scenarios.
2Productivity
If fixed crop-and-scale order is used, then image processing is faster, but adaptability to different tracking conditions deteriorates
Solution Approach 1:
The patent transforms the fixed crop-and-scale order into a dynamic decision process. The system evaluates current object tracking parameters and device motion state to determine the optimal processing order in real-time. This allows the system to maintain high processing speed for common scenarios while adapting to different tracking conditions when necessary.
Solution Approach 2:
The system dynamically changes the processing parameters based on tracked object characteristics and device motion. When objects are stable and tracking is reliable, the system uses faster fixed-order processing. When conditions change (e.g., rapid motion, new objects), the system switches to adaptive processing orders to maintain accuracy.
3Use of energy by moving object
If crop-then-scale order is always used, then computational resources are reduced, but image quality for tracking deteriorates
Solution Approach 1:
The system changes the processing parameters (crop-then-scale vs. scale-then-crop) based on object tracking parameters. When computational resources are abundant or tracking precision is critical, the system switches to scale-then-crop order which produces higher quality images. When resources are constrained and tracking is stable, crop-then-scale is used to save computational effort.
Solution Approach 2:
The system applies partial processing (crop-then-scale) when sufficient for the current tracking task, and excessive processing (scale-then-crop) when higher quality is needed. This selective application of processing intensity resolves the contradiction between computational efficiency and image quality by matching the processing level to the actual tracking requirements.
Data Source
AI summary
Examples describe adaptive image processing for an augmented reality (AR) device. An input image is captured by a camera of the AR device, and a region of interest of the input image is determined. The region of interest is associated with an object that is being tracked using an object tracking system. A crop-and-scale order of an image processing operation directed at the region of interest is determined for the input image. One or more object tracking parameters may be used to determine the crop-and-scale order. The crop-and-scale order is dynamically adjustable between a first order and a second order. An output image is generated from the input image by performing the image processing operation according to the determined crop-and-scale order for the particular input image. The output image can be accessed by the object tracking system to track the object.