Automated 3d burr detection in cast manufacturing using sparse convolutional neural networks

HIGHLIGHTS

SUMMARY

Using the learned features the authors show a burr localization approach that is able to estimate burr height similar to high resolution CT scans with Z-statistic value (z=0.279) supporting the hypothesis that the CT measured and the estimate burr height distributions are similar. The authors analyze this approach pipeline in two scenarios: CAD to scan registration where the authors estimate an SE(3) transformation between CAD models and the Zivid scans, and burr size estimation which generates a per point estimation of burr height for all viewing angles of the workpiece . . .

 



If you want to have access to all the content you need to log in!

Thanks :)

Username or Email

Password

Remember me

Lost your password?

If you don't have an account, you can create one here.