Video Conference Subtiling for Stable Auto-Cropping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current auto-cropping technologies in video conferencing systems require strict rules and are sequentially performed, leading to inefficiencies and competing decision factors, resulting in unpredictable and distracting adjustments of the field-of-view.
Innovation Solution
A method and system that determine optimal croppings and groupings based on user-defined preferences, using a sensor to generate video streams, detect objects, and adjust croppings based on total combined loss values and subtiling penalty values to ensure optimal presentation without unnecessary distractions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If sequential auto-cropping adjustments are performed to fix individual issues, then each specific problem is temporarily resolved, but new problems arise requiring additional iterations
Solution Approach 1:
The system performs preliminary evaluation of all cropping decisions simultaneously by calculating a total combined loss value that considers multiple factors (individual object cropping, object groupings, and subtiling) before making any adjustments. This prevents sequential iterations by establishing all cropping boundaries based on comprehensive loss evaluation upfront.
Solution Approach 2:
The patent merges multiple cropping decision factors into a unified total combined loss value that simultaneously evaluates individual object croppings, object groupings, and subtiling combinations. This consolidation allows all cropping decisions to be optimized together in a single operation rather than through sequential adjustments.
2Measurement precision
If strict rules are applied to detect and single out individuals within FOV, then cropping decisions are consistent, but the system becomes inflexible and requires complex rule sets
Solution Approach 1:
The system changes from fixed strict rules to flexible parameter-based evaluation by using loss values that can be adjusted based on user preferences. The total combined loss value incorporates weighted factors for different cropping aspects, allowing the system to adapt to different scenarios without requiring complex rule sets.
Solution Approach 2:
The patent introduces an intermediary evaluation mechanism (the loss function) that mediates between object detection and final cropping decisions. Instead of directly applying strict rules, the system uses loss value calculations to evaluate and compare different cropping options, providing a flexible intermediate step that simplifies the decision-making process.
3Adaptability or versatility
If multiple competing auto-cropping rules are used to handle different scenarios, then various cropping needs are addressed, but decision factors conflict and reduce processing speed
Solution Approach 1:
The patent combines multiple competing cropping rules into a single unified evaluation framework based on total combined loss value. Instead of applying separate rules for different scenarios, the system evaluates all cropping decisions simultaneously using a comprehensive loss function that considers individual croppings, groupings, and subtiling together.
Solution Approach 2:
The system changes from multiple discrete rules to a continuous parameter-based evaluation where user preferences are incorporated as weights in the loss function. This allows the system to adapt to different scenarios by adjusting parameter weights rather than switching between multiple rule sets, improving processing speed.
Data Source
AI summary
In one or more embodiments a computer implemented method includes generating, by a sensor, a video stream that comprises a series of frames that include a plurality of objects positioned within an environment, determining the objects captured within at least one frame of the video stream, determining one or more croppings for each of the objects in the at least one frame, determining a ranking of the one or more croppings based on a determined total combined loss value for each the one or more croppings, determining each subtiling combination for each of the one or more croppings, each subtiling combination comprising at least one subtile that includes at least one object; determining a total subtiling penalty value (TSPV) for each subtiling combination, and determining a preferred subtiled combination based on the total combined loss value of each the one or more croppings and the TSPV of each subtiling combination.