Meta platforms technologies, llc (20240184922). Obscuring Objects and Faces in Shared Streaming Sessions simplified abstract
Contents
- 1 Obscuring Objects and Faces in Shared Streaming Sessions
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 Obscuring Objects and Faces in Shared Streaming Sessions - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Potential Commercial Applications
- 1.9 Possible Prior Art
- 1.10 Original Abstract Submitted
Organization Name
meta platforms technologies, llc
Inventor(s)
Eric Hammerle of Kirkland WA (US)
Vikramaditya Dangi of San Francisco CA (US)
This abstract first appeared for US patent application 20240184922 titled 'Obscuring Objects and Faces in Shared Streaming Sessions
Simplified Explanation
The present disclosure involves obscuring objects and faces in data streams using machine learning. A user's data stream captured at a client device can be processed to recognize objects, and based on user preferences, certain objects can be obscured from the data stream when shared with others. User preferences and sharing rules can be defined using a preview of the data stream and explicit input from the user.
- Machine learning used to recognize objects in data streams
- User preferences define object sharing rules for obscuring objects
- Objects can be obscured when data stream is shared with others
- User input and preview used to define preferences and rules
Potential Applications
This technology could be applied in video conferencing platforms, social media apps, and live streaming services to protect user privacy by obscuring objects and faces in real-time data streams.
Problems Solved
This technology addresses the issue of unwanted objects or faces appearing in shared data streams, providing users with control over what is visible to others.
Benefits
Users can maintain their privacy and control over their data streams by defining object sharing rules, ensuring that sensitive information is not inadvertently shared with others.
Potential Commercial Applications
This technology could be valuable for companies developing video sharing platforms, social media networks, and communication tools that prioritize user privacy and data protection.
Possible Prior Art
Prior art may include image editing software that allows users to blur or obscure specific objects or faces in photos or videos.
Unanswered Questions
How does the machine learning algorithm determine which objects to obscure in the data stream?
The algorithm likely uses a combination of object recognition techniques and user-defined preferences to identify and obscure specific objects in the data stream.
What level of granularity can users define when setting object sharing rules?
Users may be able to specify rules based on object size, location within the frame, motion, or other factors, but the exact level of granularity may vary depending on the implementation of the technology.
Original Abstract Submitted
aspects of the present disclosure are directed to obscuring objects and faces in data streams using machine learning. a data stream captured at a client device associated with a user can be processed to recognize objects in the data 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 user's data stream is displayed to other users, such as during a video broadcast, objects in the user's data stream can be obscured. user preferences and object sharing rules can be defined using a preview of the data stream and explicit input from the user with respect to recognized objects in the preview. other example user preferences and sharing rules include rules for recognized faces, rules relative to an object's location in the data stream, rules or objects in motion, etc.
