Method for splitting joint cracks in road rock slope image
A technology in images and rock masses, applied in image analysis, image data processing, image enhancement, etc., it can solve the problems of inaccurate calculation, no edge, no color characteristics, etc., and achieve the effect of accurate calculation results.
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment 1
[0090] Following the technical solution of the present invention, in this embodiment α=0.325, β=0.335, γ=0.340, i.e. I=0.325R+0.335G+0.340B, δ 1 = 3.5, δ 2 = 1.5. In this embodiment, the improved difference counting box dimension method is used to calculate the fractal dimension.
[0091] figure 2 (a) is the converted image with conventional formula I=0.11R+0.59G+0.30B; figure 2 (b) convert the image according to the formula determined according to the weights of the three colors of the image, the image conversion formula is I=0.325R+0.335G+0.340B; the R, G, B coefficients of the traditional color variable grayscale formula It is obtained based on empirical values and is used for most of the images, but the present invention calculates the mean value of the histogram of the three components to obtain the coefficients of R, G, and B according to the characteristics of rock cracks, so that the obtained cracks are more clear.
Embodiment 2
[0093] The difference between this embodiment and Embodiment 1 is that the fractal dimension is calculated using the traditional method of difference counting box dimension.
[0094] image 3 (a) is the segmentation result of embodiment 2, image 3 (b) is the segmentation result of Example 1. The traditional difference counting box dimension method is to arrange grids sequentially on the (x, y) plane of the image. When the size of the image is not an integer multiple of the grid size, the grid size at the edge of the image will be smaller than s. The original solution is to put the image Add an edge, and set the gray value of the newly added edge to zero. This does not cause large errors when the image size is much larger than the maximum box size used. However, the extraction of joint cracks needs to be calculated on smaller image blocks, and the calculated fractal dimension will have a large error, which will affect the subsequent segmentation results. The improved metho...
PUM
Login to View More Abstract
Description
Claims
Application Information
Login to View More 


