Parallax Image Disparity Calculation Using Average Ratios
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing image-capturing apparatuses face challenges in accurately determining disparity between left and right parallax images due to poor pattern matching in blur regions, leading to reduced accuracy in determining the depth of a subject relative to the focus position.
Innovation Solution
An image processing apparatus that calculates arithmetic and geometric averages, ratios, and derivatives of pixel values from left and right viewpoint images to distinguish whether a subject is in front of or behind the focus position, using a single optical system to produce parallax images, and generates disparity maps to determine depth information.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pattern matching is performed on edge portions of parallax images to determine disparity, then disparity information can be obtained, but accuracy deteriorates in blur regions where edge portions are weakened
Solution Approach 1:
The patent changes the parameter used for disparity calculation from edge-based pattern matching to a method based on arithmetic and geometric averages of pixel intensities. By using the relationship between arithmetic mean and geometric mean of corresponding pixels in left and right parallax images, the system can accurately determine disparity even in blur regions where traditional edge detection fails.
2Device complexity
If a single optical system is used to capture parallax images, then device complexity is reduced, but the ability to distinguish subjects in front of or behind focus position deteriorates
Solution Approach 1:
The patent segments the analysis into two distinct calculations: first calculating the arithmetic average of pixel intensities from left and right parallax images, then calculating the geometric average. The ratio between these two averages provides disparity information that enables depth determination. This segmentation of the calculation process allows accurate depth measurement while using a single optical system.
Solution Approach 2:
The patent introduces intermediate calculation steps using arithmetic and geometric averages as mediators between the raw parallax image data and the final disparity measurement. These intermediate values serve as bridges that transform the optical information into actionable depth data, enabling the single optical system to achieve depth discrimination capability.
Data Source
AI summary
An image processing apparatus includes a receiving unit configured to receive at least two parallax images that are obtained from a subject image captured via a single optical system, where the at least two parallax images include an image in a first viewpoint direction and an image in a second viewpoint direction, an average calculating unit configured to calculate, for each pixel, an arithmetic average and a geometric average between the image in the first viewpoint direction and the image in the second viewpoint direction, a ratio calculating unit configured to calculate, for each pixel, a ratio of the arithmetic average to the geometric average, and a disparity calculating unit configured to calculate, on a pixel-by-pixel basis, a disparity between the image in the first viewpoint direction and the image in the second viewpoint direction based on the ratio.