Distributed Sensor Module for AR/VR Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
AR/VR devices face challenges in minimizing power consumption and ensuring data security due to excessive data communication between sensors and central units, which can lead to power drain and potential data breaches.
Innovation Solution
A self-sufficient VIO-based SLAM tracking system with distributed sensor modules that share reference patches via a data link, allowing feature tracking without excessive communication with the central module, thereby reducing data transmission and enhancing security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If data is transmitted from cameras to central unit for localization and mapping, then tracking accuracy is improved, but power consumption increases and data security deteriorates
Solution Approach 1:
The system divides the tracking function into two segments: local feature extraction and matching at the camera module, and central unit processing for localization and mapping. The camera module performs self-contained VIO tracking using stored reference patches, eliminating the need to transmit all camera data to the central unit, thus reducing power consumption while maintaining tracking accuracy.
Solution Approach 2:
The camera module is designed to be self-sufficient by storing reference patches locally and performing feature tracking independently using VIO algorithms. This self-service capability allows the camera module to complete tracking tasks without continuous communication with the central unit, reducing power consumption and data transmission requirements.
2Measurement precision
If data is transmitted from cameras to central unit for localization and mapping, then tracking accuracy is improved, but data security deteriorates
Solution Approach 1:
The system extracts only the necessary tracking information (feature correspondences and reference patches) to be processed locally at the camera module, while transmitting minimal data to the central unit. This extraction approach reduces the amount of sensitive data that needs to be transmitted over networks, thereby improving data security while maintaining tracking accuracy.
Solution Approach 2:
The camera module acts as an intermediary that performs local processing and feature matching before any data is sent to the central unit. This intermediary role allows the system to process sensitive visual data locally, reducing the exposure of sensitive information during transmission and improving overall data security.
3Measurement precision
If frequent data communication is used between sensors and central unit, then tracking accuracy is improved, but power consumption increases
Solution Approach 1:
The system performs preliminary actions by pre-storing reference patches and feature information at the camera module before tracking begins. This preliminary preparation allows the camera module to conduct VIO tracking independently without frequent communication with the central unit, reducing power consumption while maintaining accurate tracking through local reference data.
Data Source
AI summary
In one embodiment, a method for tracking includes capturing a first frame of the environment using a first camera, identifying, in the first frame, a first patch that corresponds to the first feature, accessing a first local memory of the first camera that stores reference patches identified in one or more previous frames captured by the first camera, and determining that none of the reference patches stored in the first local memory corresponds to the first feature. The method further includes receiving, from a second camera through a data link connecting the second camera with the first camera, a reference patch corresponding to the first feature. The reference patch is identified in a previous frame captured by the second camera and of the second camera. The method may then determine correspondence data between the first patch and the reference patch, and tracks the first feature in the environment based on the determined correspondence data.