Feature Quality Information for AR Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately tracking and displaying augmented reality content in relation to a textured target across multiple images, especially when the device moves, due to difficulties in consistently locating features in varying environments.
Innovation Solution
The use of feature quality information, generated through similarity values and machine learning, to intelligently locate features in subsequent images, allowing for accurate tracking and display of augmented reality content in relation to a textured target, even as the device moves, by utilizing time-invariant values and characteristics of similarity values to determine matching blocks of pixels.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If feature tracking is performed across multiple images to enable augmented reality content display, then augmented reality content can be overlaid on textured targets, but accurate feature location becomes difficult when the device moves and environments vary
Solution Approach 1:
The system performs preliminary actions by generating feature quality information in advance from the initial image before device movement occurs. This pre-computed quality information (including similarity values and characteristics) is stored and later used to guide feature searching in subsequent images, enabling reliable tracking despite environmental changes and device motion.
Solution Approach 2:
Feature quality information serves as an intermediary between the initial image features and subsequent image matching. This intermediary contains pre-analyzed characteristics (similarity values, feature descriptors) that mediate the matching process, allowing the system to bridge the gap caused by device movement and environmental variation when locating features in new images.
2Measurement precision
If comprehensive image processing is performed to locate features accurately, then feature location precision improves, but processing time increases
Solution Approach 1:
The system performs comprehensive image analysis in advance by generating feature quality information from the initial image, including computing similarity values and characteristics for all candidate blocks. This preliminary processing shifts the computational burden to before device movement, so that subsequent feature location in new images requires only comparing against the pre-computed quality information, significantly reducing real-time processing time while maintaining high precision.
Data Source
AI summary
Techniques for searching in an image for a particular block of pixels that represents a feature are described herein. The techniques may include generating feature quality information indicating a quality of the feature with respect to blocks of pixels of the image. The feature quality information may be utilized to locate a block of pixels in a subsequent image that corresponds to the feature. For example, the feature quality information may be utilized to determine whether a block of pixels that has a threshold amount of similarity to the feature actually corresponds to the feature.