Face-Aware Auto-Framing Control to Reduce Video Image Shaking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Frequent auto-framing in camera modules for video-conferencing causes vertical, horizontal, and depth shaking, especially with multiple people in the frame, degrading user experience.
Innovation Solution
An information processing system that includes a camera, a face detection unit, a parameter setting unit, and a framing unit to adjust framing parameters based on the number of detected faces, slowing down framing reactions as the number of faces increases.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If frequent auto-framing is performed to track multiple people, then the framing responsiveness is improved, but the image shaking is worsened
Solution Approach 1:
The patent applies dynamics by making the framing reaction parameter variable rather than fixed. The system dynamically adjusts the reaction parameter based on the number of detected faces, allowing the framing behavior to adapt to different scene conditions. This resolves the contradiction by enabling fast response when needed (single person) while maintaining stability when multiple people are present.
Solution Approach 2:
The patent changes the parameter of framing reaction speed based on the number of detected faces. When one face is detected, a first reaction parameter (faster response) is applied, while when multiple faces are detected, a second reaction parameter (slower response) is applied. This parameter change strategy directly resolves the technical contradiction by adjusting system behavior according to operational conditions.
2Area of stationary object
If aggressive framing adjustments are made to include all people, then the framing coverage is improved, but the user experience is worsened due to shaking
Solution Approach 1:
The system changes the framing reaction parameter based on face count to balance coverage and stability. When multiple faces are detected, the second reaction parameter is applied which provides adequate coverage while reducing the harmful shaking effect that degrades user experience.
Data Source
AI summary
An information processing system includes a camera, a face detection unit that detects faces included in an image acquired by the camera, a parameter setting unit that sets a reaction parameter for framing according to the number of the detected faces, and a framing unit that performs framing of the image using the set reaction parameter. The parameter setting unit sets the reaction parameter, for example, so that the framing reaction is slower as the number of faces included in the image increases.