Multi-Person Exposure Control Using Face Orientation Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image capture systems struggle to properly expose multiple human bodies in varying orientations and movements, especially in challenging lighting conditions, leading to difficulty in analyzing faces effectively.
Innovation Solution
An information processing apparatus that detects human bodies in images, discriminates their parts and orientations, and calculates exposure amounts based on luminance measurements and weightings to optimize image capture, ensuring proper exposure and enhanced face recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a single exposure amount is used for the entire screen, then the overall image brightness is controlled, but faces of multiple human bodies in varying orientations cannot be properly exposed
Solution Approach 1:
The patent divides the image into multiple photometric areas corresponding to different human bodies and calculates separate exposure amounts for each area based on their luminance and orientation characteristics. This segmentation allows each face to be properly exposed even when human bodies are in varying orientations and positions.
Solution Approach 2:
The patent applies different exposure control strategies to different photometric areas. Each area receives a customized exposure amount calculated based on its specific luminance characteristics and the orientation of the human body, rather than applying a uniform exposure setting across the entire image.
2Measurement precision
If weighting is increased for face areas, then face exposure is improved, but other areas of the image may become underexposed
Solution Approach 1:
The patent dynamically calculates exposure amounts by changing the weighting parameter for each photometric area based on its luminance and the orientation of the human body. The weighting is not fixed but adapts to the specific characteristics of each area, allowing proper exposure without compromising overall image brightness.
Data Source
AI summary
An information processing apparatus includes a detection unit configured to detect a human body in an image, a discrimination unit configured to discriminate a part and an orientation of a detected human body in a case where a plurality of human bodies is detected by the detection unit, a photometry unit configured to, in a case where a plurality of human bodies is detected by the detection unit, measure a luminance of each of a plurality of photometric areas corresponding to the human bodies, a determination unit configured to determine a weighting for each photometric area in accordance with the part and orientation discriminated by the discrimination unit, and a calculation unit configured to calculate an exposure amount for capturing a moving image, from the luminance of each photometric area measured by the photometry unit and the weighting for each photometric area determined by the determination unit.