Machine Learning Object Obscuring in Data Streams
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional systems fail to provide users with granular control over sharing objects in data streams, leading to privacy concerns and impersonal interactions in video conferencing and artificial reality sessions.
Innovation Solution
A data stream processing system using machine learning to recognize and categorize objects, allowing users to define preferences for sharing object categories or locations, and obscuring unwanted objects through blocking, blurring, or filtering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional systems share data streams without object-level control, then connectivity and sharing are improved, but privacy control and user autonomy deteriorate
Solution Approach 1:
The patent segments the data stream into individual objects using machine learning identification, allowing users to control sharing at the object level rather than treating the entire stream as a single unit. This enables selective sharing of specific objects while maintaining privacy for others, resolving the contradiction between versatile sharing control and reliable privacy protection.
2Reliability
If automatic obscuring is applied to all objects, then privacy protection is improved, but user control and personalization deteriorate
Solution Approach 1:
The system dynamically adjusts obscuring based on user preferences and contextual information. Users can specify which objects should be obscured, and the system adapts its behavior accordingly rather than applying static automatic obscuring to all objects. This maintains both privacy protection and user control through flexible, context-aware operation.
3Measurement precision
If machine learning object recognition is implemented, then object-level control precision is improved, but system complexity deteriorates
Solution Approach 1:
The patent introduces machine learning models as intermediary components that automatically perform object identification and categorization. These intermediaries handle the complex recognition tasks, allowing the user interface to remain simple while achieving high object identification accuracy. The machine learning layer mediates between the raw data stream and the user control mechanisms, absorbing the complexity.
4Reliability
If granular object sharing control is provided, then privacy control is improved, but processing complexity and computational load deteriorate
Solution Approach 1:
The system performs preliminary object identification and categorization using machine learning before the user needs to make sharing decisions. By pre-processing the data stream to identify and label objects, the system reduces the computational complexity during the actual sharing control phase, allowing granular privacy control without excessive processing burden during user interactions.
Data Source
AI summary
Aspects of the present disclosure are directed to obscuring objects in data streams using machine learning. A data stream captured at a client device associated with a principal user (e.g., video stream, artificial reality session, and the like) can be processed to recognize objects in the stream. Based on user preferences that define object sharing rules, one or more of the recognized objects can be obscured from the data stream. For example, when the principal user's data stream is displayed to the participant users, such as during a video conference, objects in the principal user's data stream can be obscured according to the object sharing rules. Different groups of object sharing rules (e.g., profiles) can be used for different participant users or session types. Machine learning can be used to learn trends and predict a profile for use with a current or future shared streaming data session.