Distance Measuring Camera Epipolar Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional distance measuring cameras face challenges in accurately calculating distances to subjects, especially at near distances, due to the need for large optical system spacing for sufficient parallel disparity, which increases camera size, and the processing time for feature point detection is long when using image magnification ratios.
Innovation Solution
A distance measuring camera system with two optical systems that calculate distance based on image magnification ratios, where the search for feature points is limited to epipolar lines within a defined search area, reducing processing time by overlapping imaging areas and using epipolar geometry for efficient feature point detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If two optical systems are arranged so as to be largely spaced apart from each other in the direction perpendicular to the optical axis direction, then the parallel disparity between the subject images is sufficiently increased to improve distance measurement accuracy, but the size of the distance measuring camera increases
Solution Approach 1:
The patent changes the measurement parameter from parallel disparity to image magnification ratio. By using the ratio of magnifications of subject images formed by two optical systems with different magnification characteristics, the system achieves accurate distance measurement without requiring large optical system spacing, thus resolving the contradiction between measurement accuracy and camera size
Solution Approach 2:
The patent replaces the mechanical approach of increasing physical distance between optical systems with a computational approach using image magnification ratio. Instead of relying on mechanical displacement (parallel disparity), the system uses optical magnification differences combined with image processing to achieve distance measurement, eliminating the need for large camera size
2Area of stationary object
If two optical systems are arranged so as to be close to each other, then the camera size is reduced, but the parallel disparity between the subject images decreases and thus accuracy of the distance measurement reduces
Solution Approach 1:
The patent changes the measurement parameter from parallel disparity to image magnification ratio. By utilizing the ratio of magnifications of subject images formed by two optical systems with different magnification characteristics, the system achieves accurate distance measurement even when optical systems are closely spaced, thus resolving the contradiction between camera size and measurement accuracy
3Reliability
If the search for feature points is performed over the entire area of the second image, then all possible feature points are detected, but the processing time for calculating the distance becomes long
Solution Approach 1:
The patent segments the search area from the entire second image to only the overlapping imaging area between the first and second images. This segmentation reduces the number of pixels that need to be searched for feature points, significantly decreasing processing time while maintaining detection reliability within the valid measurement region
Solution Approach 2:
The patent performs preliminary determination of the overlapping imaging area before feature point detection. By pre-defining the search boundaries based on the geometric relationship between the two optical systems, the system avoids unnecessary searches in non-overlapping regions, thus reducing processing time without compromising feature point detection accuracy
Data Source
AI summary
The distance measuring camera includes a first imaging system for obtaining a first image, a second imaging system for obtaining a second image and a size obtaining part 3 for measuring a distance between a plurality of feature points of a first subject in the first image to obtain a size of the first subject image and measuring a distance between a plurality of feature points of a second subject image in the second image to obtain a size of the second subject image. The size obtaining part 3 searches pixels on an epipolar line only in a search area of the second image in which a first imaging area corresponding to the first image can be overlapped with a second imaging area corresponding to the second image to detect the plurality of feature points of the second subject image.