I am a masters student going to work in a project to analyze the cracks in underwater concrete structures.
I need some suggestions for data acquisition and length measurement of the crack.
I have decided to do crack segmentation using Mask-RCNN. But I don't know which methodology is best to measure the length of the cracks. While searching about this, I found many ways to measure the crack size when there is another reference object of known size in the image. But in my case, there won't be any reference object and also it is not possible to know the distance between the camera and target since it is underwater.
If the images are of stereotype, Will that solve this issue?
Can anyone help?