Elimination of Reflections in Laser Scanning Systems with Convolutional Neural Networks

“Elimination of Reflections in Laser Scanning Systems with Convolutional Neural Networks”

Authors: Ola Alstad and Olav Egeland,
Affiliation: NTNU
Reference: 2022, Vol 43, No 1, pp. 9-20.

Keywords: Robotic welding, laser, reflections, filtering, CNN

Abstract: This paper presents a machine learning approach for eliminating reflections in line laser scanning of aluminium workpieces to be welded. The elimination of reflections is important to obtain accurate laser scanning of workpiece geometry for highly reflective materials like aluminium. The proposed solution is to use a convolutional neural network (CNN) which is trained to eliminate the reflections. The training of the network is done by simulating the laser line of the scanner in ray-tracing software using aluminium surfaces with appropriate reflection properties. This CNN then recovers the reflected laser line by removing the reflections. The CNN is used with two different camera configurations. In the first configuration one camera and one laser scanner are used. In the second configuration two cameras are used in a stereo arrangement in combination with the line laser. In this case, the planar homography of the laser plane is used to detect possible points on the laser line in a preprocessing step. The high performance of the solution is demonstrated for simulated data.

PDF

PDF (6394 Kb) DOI: 10.4173/mic.2022.1.2

DOI forward links to this article:

[1] Jaime Marco-Rider, Andrej Cibicik and Olav Egeland (2022), doi:10.1109/JSEN.2022.3194258

References:
[1] Blais, F. (2004). Review of 20 years of range sensor development, Journal of electronic imaging. 13(1):231--243. doi:10.1117/1.1631921
[2] Clark, J., Trucco, E., and Wolff, L.B. (1997). Using light polarization in laser scanning, Image and Vision Computing. 15(2):107--117. doi:10.1016/S0262-8856(96)01126-2
[3] Demes, L. (2021). Free public domain pbr materials, 2021. https://ambientcg.com/.
[4] Fisher, R. and Naidu, D. (1996). A comparison of algorithms for subpixel peak detection, In Image technology, pages 385--404. Springer. doi:10.1007/978-3-642-58288-2_15
[5] FrankChen, G.M. and Mumin, S. (2000). Overview of three-dimensional shape measurement using optical methods, Optical Engineering. 39:10--21. doi:10.1117/1.602438
[6] Goodfellow, I.J., Bengio, Y., and Courville, A. (2016). Deep Learning, MIT Press, Cambridge, MA, USA. http://www.deeplearningbook.org.
[7] Grans, S. and Tingelstad, L. (2021). Blazer: Laser scanning simulation using physically based rendering, arXiv preprint arXiv:2104.05430.
[8] Hartley, R. and Zisserman, A. (2003). Multiple View Geometry in Computer Vision, Cambridge University Press, New York, NY, USA, 2 edition. doi:10.1017/CBO9780511811685
[9] Koehler, J., Noell, T., Reis, G., and Stricker, D. (2012). Robust outlier removal from point clouds acquired with structured light, In Eurographics (Short Papers). pages 21--24. doi:10.2312/conf/EG2012/short/021-024
[10] Li, H., Zhang, X., Zhuang, L., and Yang, Y. (2019). Specular surface measurement with laser plane constraint to reduce erroneous points, In International Conference on Intelligent Robotics and Applications. Springer, pages 53--63. doi:10.1007/978-3-030-27541-9_5
[11] Lynch, K. and Park, F. (2017). Modern Robotics: Mechanics, Planning, and Control, Cambridge Univeristy Press.
[12] Pharr, M., Jakob, W., and Humphreys, G. (2016). Physically based rendering: From theory to implementation, Morgan Kaufmann. doi:10.1016/C2013-0-15557-2
[13] Pottmann, H. and Wallner, J. (2001). Computational Line Geometry, Springer-Verlag, Berlin. doi:10.1007/978-3-642-04018-4
[14] Ronneberger, O., Fischer, P., and Brox, T. (2015). U-net: Convolutional networks for biomedical image segmentation, In International Conference on Medical image computing and computer-assisted intervention. Springer, pages 234--241. doi:10.1007/978-3-319-24574-4_28
[15] Roosendaal, T. (2021). Blender - a 3D modelling and rendering package, Blender Foundation, Stichting Blender Foundation, Amsterdam. http://www.blender.org.
[16] Trucco, E., Fisher, R.B., and Fitzgibbon, A.W. (1994). Direct calibration and data consistency in 3-D laser scanning, Department of Artificial Intelligence, University of Edinburgh. doi:10.5244/C.8.48
[17] Trucco, E., Fisher, R.B., Fitzgibbon, A.W., and Naidu, D. (1998). Calibration, data consistency and model acquisition with laser stripers, International Journal of Computer Integrated Manufacturing, 1998. 11(4):293--310. doi:10.1080/095119298130642
[18] Zou, K.H., Warfield, S.K., Bharatha, A., Tempany, C.M., Kaus, M.R., Haker, S.J., WellsIII, W.M., Jolesz, F.A., and Kikinis, R. (2004). Statistical validation of image segmentation quality based on a spatial overlap index1: scientific reports, Academic radiology. 11(2):178--189. doi:10.1016/s1076-6332(03)00671-8

BibTeX:
@article{MIC-2022-1-2,
  title={{Elimination of Reflections in Laser Scanning Systems with Convolutional Neural Networks}},
  author={Alstad, Ola and Egeland, Olav},
  journal={Modeling, Identification and Control},
  volume={43},
  number={1},
  pages={9--20},
  year={2022},
  doi={10.4173/mic.2022.1.2},
  publisher={Norwegian Society of Automatic Control}
};

Article

“Elimination of Reflections in Laser Scanning Systems with Convolutional Neural Networks”