Single Detector Stereo Vision Disparity Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing stereo vision algorithms face limitations in determining disparity at large distances and accurately reconstructing three-dimensional surfaces, particularly beyond a certain distance where stereoscopic perception is impaired.
Innovation Solution
A method involving a single image detector that corrects distortion in stereoscopic color images using an image distortion correction model, identifies matching pixels, and determines disparity by analyzing color intensity distribution differences and vectorial gradients, allowing for accurate depth calculation and improved stereoscopic perception.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single image detector is used to capture stereoscopic images, then device complexity is reduced, but measurement precision of disparity deteriorates due to image distortion
Solution Approach 1:
An image distortion correction model is introduced as an intermediary processing step between image capture and disparity calculation. The model corrects radial and tangential distortions in the single-detector stereoscopic images, enabling accurate disparity measurement despite the simplified hardware configuration.
Solution Approach 2:
The patent replaces the mechanical solution of using two separate image detectors with a computational approach. By applying distortion correction algorithms and disparity calculation methods, the system achieves accurate depth measurement using only one physical detector, substituting mechanical complexity with information processing.
2Measurement precision
If distortion correction is applied to stereoscopic images, then measurement precision improves, but loss of time increases due to additional processing steps
Solution Approach 1:
The distortion correction model is established in advance based on the known optical characteristics of the image detector. By pre-calculating and storing the correction parameters, the actual image processing requires only applying these pre-prepared transformations, significantly reducing real-time processing time while maintaining high measurement precision.
3Measurement precision
If matching pixels are identified using color intensity distribution analysis, then measurement precision improves, but device complexity increases due to additional processing requirements
Solution Approach 1:
The patent transforms the pixel matching problem from a spatial correlation task to a color intensity distribution comparison task. By analyzing the distribution characteristics of color intensities around candidate matching pixels and comparing them with reference pixels, the system achieves robust and accurate matching even in challenging scenarios, balancing precision improvement with manageable processing complexity.
Data Source
AI summary
Method for determining a disparity value of a disparity of each of a plurality of points on an object, the method including the procedures of detecting by a single image detector, a first image of the object through a first aperture, and a second image of the object through a second aperture, correcting the distortion of the first image, and the distortion of the second image, by applying an image distortion correction model to the first image and to the second image, respectively, thereby producing a first distortion-corrected image and a second distortion-corrected image, respectively, for each of a plurality of pixels in at least a portion of the first distortion-corrected image representing a selected one of the points, identifying a matching pixel in the second distortion-corrected image, and determining the disparity value according to the coordinates of each of the pixels and of the respective matching pixel.