Contextual Object Storage for Head-Mounted Displays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for head-mounted devices equipped with scene cameras struggle to efficiently store and index information about identified objects in a user's environment, making it difficult to retrieve specific information related to objects and their contextual data.
Innovation Solution
A method and device that capture images of the environment, detect user engagement with objects, obtain information about the objects, gather contextual information such as time and location, and store these entries in a database for efficient retrieval.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If object information is stored without contextual information, then storage simplicity is improved, but information retrieval efficiency deteriorates
Solution Approach 1:
The patent implements a nested database structure where contextual information (location, time, activity) is stored within the same database entry as object information. The contextual data is nested as additional fields within the object record, allowing both simple storage and efficient contextualized retrieval without requiring separate database systems or complex joins.
2Loss of information
If all captured object information is stored, then information completeness is improved, but storage resource consumption increases
Solution Approach 1:
The patent applies local quality by selectively storing only those object detections that meet specific engagement criteria (e.g., user gaze duration, interaction type). Not all detected objects are stored uniformly; instead, storage is applied locally to only the relevant subset of detections that represent meaningful user engagement, reducing overall storage volume while preserving important information.
3Measurement precision
If contextual information is collected and stored for each object, then information retrieval accuracy is improved, but system complexity increases
Solution Approach 1:
The patent implements a multi-functional data collection system where the same sensing infrastructure (cameras, sensors) used for object detection also collects contextual information (location via GPS, time via system clock, activity via motion sensors). This universal approach allows multiple types of data to be gathered through a single integrated system rather than requiring separate specialized systems for each data type.
Data Source
AI summary
In one implementation, a method of storing object information in association with contextual information is performed at a device including an image sensor, one or more processors, and non-transitory memory. The method includes capturing, using the image sensor, an image of an environment. The method includes detecting a user engagement with an object in the environment based on the image of the environment. The method includes, in response to detecting the user engagement with the object, obtaining information regarding the object, obtaining contextual information, and storing, in a database, an entry including the information regarding the object in association with the contextual information.