Distributed AR Imaging System with Local Feature Matching
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Augmented Reality (AR) systems face challenges in balancing computational speed, bandwidth, latency, and power consumption, particularly in wearable devices, where design considerations such as size, weight, and visibility of sensors like cameras are critical, limiting the effectiveness of sensing and processing capabilities.
Innovation Solution
A distributed imaging system for AR devices that includes a computing module and multiple spatially distributed sensing devices, where a primary sensing device captures a wide field of view, and secondary devices capture smaller, overlapping views, which are processed to generate high-resolution images through local feature matching, optical flow computations, and neural network-based image fusion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple cameras are used to improve sensing capability and image resolution, then measurement precision and reliability are improved, but device complexity, weight, and power consumption increase
Solution Approach 1:
The patent divides the sensing system into a primary camera for wide-field capture and multiple secondary cameras for targeted high-resolution capture. This segmentation allows each camera to have specialized functions, improving overall measurement precision while managing device complexity through functional division rather than requiring all cameras to operate at full capability simultaneously.
Solution Approach 2:
The system selectively activates secondary cameras only when high-resolution imaging is needed in specific regions, rather than continuously operating all cameras at full capacity. This partial action approach maintains measurement precision when needed while reducing power consumption and thermal footprint during normal operation.
2Reliability
If multiple cameras operate continuously to maintain high sensing performance, then reliability is improved, but power consumption and heat generation increase
Solution Approach 1:
The system dynamically adjusts camera activation based on computational needs and scene requirements. The computing module determines when secondary cameras should be activated based on factors such as object tracking requirements, SLAM operations, and power availability, allowing the system to maintain reliability when needed while optimizing power consumption during normal operation.
Solution Approach 2:
Rather than continuous operation, the system employs periodic activation of secondary cameras triggered by specific events or computational requirements. This periodic action maintains sensing reliability for critical functions while significantly reducing average power consumption compared to continuous operation of all cameras.
3Measurement precision
If high-resolution imaging is achieved through multiple cameras, then measurement precision is improved, but computational load and processing time increase
Solution Approach 1:
The system applies different processing quality levels to different regions and cameras. Primary camera images undergo standard processing, while secondary camera images receive enhanced processing only when and where high resolution is needed. This local quality approach maintains measurement precision for critical regions while improving overall computational efficiency by avoiding uniform high-quality processing across all images.
Solution Approach 2:
The computing module performs preliminary assessment of imaging requirements before activating secondary cameras and initiating high-computation processing pipelines. By predicting when high-resolution imaging will be needed based on scene analysis and application requirements, the system can prepare computational resources in advance, reducing actual processing time when high-resolution output is required.
Data Source
AI summary
A distributed imaging system for augmented reality devices is disclosed. The system includes a computing module in communication with a plurality of spatially distributed sensing devices. The computing module is configured to process input images from the sensing devices based on performing a local feature matching computation to generate corresponding first output images. The computing module is further configured to process the input images based on performing an optical flow correspondence computation to generate corresponding second output images. The computing module is further configured to computationally combine first and second output images to generate third output images.