Region of Interest Video Stream Normalization for Conference Displays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional conferencing software displays participants from a conference room in a single user interface tile, leading to inconsistent sizing and quality issues due to varying distances from the camera, resulting in an undesirable user experience for remote participants.
Innovation Solution
Normalizing video stream resolutions based on regions of interest within the initial video stream captured by a camera in the conference room, ensuring that each participant is displayed at consistent sizes and quality levels across separate user interface tiles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single user interface tile is used to display all participants, then the device complexity is reduced, but the manufacturing precision of display quality is worsened due to inconsistent sizing
Solution Approach 1:
The patent divides the single user interface tile into multiple separate tiles, each dedicated to a specific participant. This segmentation allows each participant to be displayed in their own optimized region, eliminating the quality inconsistency caused by varying distances from the camera. The system creates individual video streams for each participant based on their region of interest, ensuring uniform display quality across all tiles.
2Manufacturing precision
If video streams are captured at different resolutions for different participants, then the manufacturing precision of individual participant quality is improved, but the loss of energy increases due to processing multiple streams
Solution Approach 1:
The patent dynamically adjusts the resolution parameter for each participant's video stream based on their specific needs and region of interest. Instead of using a fixed high resolution for all participants, the system optimizes the resolution for each individual stream, reducing overall processing energy while maintaining quality where needed. This parameter optimization allows the system to capture multiple video streams at normalized resolutions without excessive energy consumption.
3Manufacturing precision
If multiple video streams are captured concurrently for different participants, then the manufacturing precision of participant representation is improved, but the device complexity increases
Solution Approach 1:
The patent performs preliminary actions by first identifying regions of interest for each participant before capturing video streams. The system pre-processes the initial video stream to determine optimal regions and normalized resolutions for each participant, then uses this information to guide the concurrent video stream capture. This preliminary analysis simplifies the subsequent multi-stream processing by establishing clear parameters for each stream in advance.
Data Source
AI summary
A video capture device within a physical space captures an initial video stream of first and second conference participants within the physical space. Data indicative of first and second regions of interest of the initial video stream are transmitted to a computing device. The first and second regions of interest are respectively associated with the first and second conference participants. First and second video streams associated with the first and second regions of interest are captured at normalized resolutions according to instructions received from the computing device. The first and second video streams are transmitted for output within separate user interface tiles of a conferencing software user interface. The first and second video streams conform sizes and quality levels of the first and second conference participants respectively within first and second user interface tiles of the conferencing software user interface.