An X-corner Detection Method Applied to Vision Positioning and Calibration
A corner detection and visual positioning technology, which is applied in the field of X corner detection, can solve the problems such as being unsuitable for parallel batch processing, and the algorithm calculation amount is large, so as to achieve the effect of enhancing robustness and improving detection speed.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0046] An X corner detection method applied to visual positioning and calibration, such as figure 2 shown, including:
[0047] S1: Acquire an image, using a trapezoidal window (such as figure 1 Sampling the image; set the side length of the trapezoidal window sampling as 2r pixels, and the trapezoidal window is a square, then the samples taken by the trapezoidal window contain a total of 8r-4 pixels, and r is less than Half of the side length of the smallest X corner point in the image; all pixels of the trapezoidal window are counted into a circular data queue, all pixels of the trapezoidal window are the sample data P, and the i-th pixel is recorded as P i , P i The grayscale value of f is i , i=1,2...(8r-4);
[0048] S2: Preliminarily determine whether the sample data P contains the X corner point according to the image characteristics of the X corner point, if the judgment condition is satisfied, then calculate the sub-pixel level position of the X corner point, other...
Embodiment 2
[0053] The X corner detection method applied to visual positioning and calibration according to Embodiment 1, the difference is that the step S2 includes:
[0054] S21: grayscale the sample data in turn; the threshold can be adaptively selected.
[0055] S22: Binarize the gray value of the sample data twice, the binarization threshold is mean±Δ, mean is the mean value of the gray value of the sample data, Δ is the threshold adjustment value, and the value range of Δ is 20-160 pixel. The value of Δ is related to the brightness of the whole image. Adding Δ as the threshold adjustment value can avoid the wrong judgment caused by the influence of image noise and enhance the robustness of the algorithm. Calculate the number of steps N of the sample data processed in step S21 s , if N s =4, then execute step S23, otherwise, execute step S5;
[0056] S23: Binarize the gray value of the sample data with the average value of the gray value of the sample data as the threshold; set t...
Embodiment 3
[0059] The X corner detection method applied to visual positioning and calibration according to Embodiment 1, the difference is that the step S3 includes:
[0060] S31: Judging the X corner point repeated detection flag, if the pixel value L of the X corner point obtained in step S23 is located in the inactive area, then it is determined that the X corner point has been detected, then jump out of this cycle, and execute step S5; otherwise, Execute step S32;
[0061] S32: Obtain the pixel value L of the X corner point and the gray value of the neighboring pixels, and the neighborhood refers to the range with the pixel value L of the X corner point as the center and the r pixel as the radius; The mean of , as the threshold, binarizes the neighborhood, and calculates the number of steps of the gray value ΔV C , if ΔV C >min_V, continue to perform step S4, otherwise, perform step S5; min_V=4.
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 

