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?

  • 1
    $\begingroup$ With "stereotype" you probably mean stereoscopic, and yes, given a known and stable camera arrangement, it should be possible to calculate distance and therefore absolute size. $\endgroup$ Nov 14 '19 at 12:44

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.