Hierarchical registration method for surface quality inspection of long products

  1. delaCalle, F. J. 1
  2. García, D. F. 1
  3. Usamentiaga, R. 1
  4. Nuño, P. 1
  5. Magadán, L. 1
  1. 1 Universidad de Oviedo
    info

    Universidad de Oviedo

    Oviedo, España

    ROR https://ror.org/006gksa02

Revista:
The Visual Computer

ISSN: 0178-2789,  1432-2315

Año de publicación: 2023

Tipo: Artículo

DOI: 10.1007/S00371-023-02839-5 GOOGLE SCHOLAR lock_openAcceso abierto editor

Otras publicaciones en: The Visual Computer

Resumen

Manufacturing industry often uses 3D scanning technologies to inspect their products. Some of these techniques produce a point cloud that represent a section of the manufactured product. The clouds must be aligned to the model of the product in order to check its quality. Current registration methods are usually affected by dimensional problems or volumetric anomalies. This paper proposes a new method for the registration process aligning the cloud to the model in several steps. The first step is the state-of-the-art method. The second step uses the information acquired in the first one to perform a fine registration in order to not being affected by dimensional defects or little miss alignments in the previous step providing a huge improvement in the measurement of surface defects. In this paper, several techniques are proposed in order to provide a set of tools that the final users can tune to fit their needs. The whole procedure of registration can be run in real-time conditions using the sampling and caching strategies proposed. The methods proposed are tested over more than 10,000 profiles of a rail proving they successfully align the cloud and the model providing better results in the measurement of surface defects.

€ Ver financiación

Información de financiación

This work was funded by the project MCIU-22-PID2021-124383OB-I00 of the Spanish State Plan for Scientific and Technical Research and Innovation 2021–2023.

Financiadores

Referencias bibliográficas

  • Besl, P., McKay, N.D.: A method for registration of 3-d shapes. IEEE Trans. Pattern Anal. Mach. Intell. 14, 239–256 (1992). https://doi.org/10.1109/34.121791
  • de la Calle Herrero, F., García, D.F., Usamentiaga, R.: Rail surface inspection system using differential topographic images. IEEE Trans. Ind. Appl. 57, 2994–3003 (2021). https://doi.org/10.1109/TIA.2021.3059605
  • de la Calle Herrero, F., Garcia, F.D., Usamentiaga, R.: Generation of differential topographic images for surface inspection of long products. J. Real Time Image Process. 17, 967–980 (2020). https://doi.org/10.1007/s11554-018-0844-2
  • de la Calle Herrero, F., Garcia, F.D., Usamentiaga, R.: Surface defect system for long product manufacturing using differential topographic images. Sensors 20, 2142 (2020). https://doi.org/10.3390/s20072142
  • Garrett, T., Radkowski, R., Sheaffer, J.: Gpu-accelerated descriptor extraction process for 3d registration in augmented reality. In: 2016 23rd International Conference on Pattern Recognition (ICPR), pp. 3085–3090 (2016). https://doi.org/10.1109/ICPR.2016.7900108
  • Gautier, Q., Shearer, A., Matai, J., Richmond, D., Meng, P., Kastner, R.: Real-time 3d reconstruction for fpgas: a case study for evaluating the performance, area, and programmability trade-offs of the altera opencl sdk (2014). https://doi.org/10.13140/RG.2.1.4950.4168
  • Hu, L., Xiao, J., Wang, Y.: An automatic 3D registration method for rock mass point clouds based on plane detection and polygon matching. Vis. Comput. 36, 669–681 (2020). https://doi.org/10.1007/s00371-019-01648-z
  • Ikeda, O., Duan, Y.: Color photometric stereo for albedo and shape reconstruction. In: 2008 IEEE Workshop on Applications of Computer Vision, pp. 1–6 (2008). https://doi.org/10.1109/WACV.2008.4544015
  • Kehtarnavaz, N., Gamadia, M.: Real-time image and video processing: from research to reality (2006)
  • Li, Y., Yang, X., Chen, L., Zhi, Y., Liu, H.: Robust registration of rail profile and complete detection of outliers in complex field environment. IEEE Trans. Intell. Transp. Syst. 23, 20098–20109 (2022). https://doi.org/10.1109/TITS.2022.3177860
  • Manso, P., García, D.F., Usamentiaga, R.: Rail flatness measurement method based on virtual rules. IEEE Trans. Ind. Appl. 53, 4116–4124 (2017). https://doi.org/10.1109/TIA.2017.2676092
  • Molleda, J., Usamentiaga, R., Millara, Á.F., García, D.F., Manso, P., Suarez, C.M., Garcia, I.: A profile measurement system for rail manufacturing using multiple laser range finders. IEEE Ind. Appl. Soc. Annu. Meet. 2015, 1–8 (2015)
  • Santur, Y., Karakose, M., Akin, E.: A new rail inspection method based on deep learning using laser cameras, pp. 1–6 (2017). https://doi.org/10.1109/IDAP.2017.8090245
  • Secil, S., Turgut, K., Parlaktuna, O., Ozkan, M.: 3-d visualization system for geometric parts using a laser profile sensor and an industrial robot. In: IEEE International Symposium on Robotics and Manufacturing Automation (ROMA), vol. 2014, pp. 160–165 (2014)
  • Sharif, M.M., Haas, C., Walbridge, S.: Using termination points and 3d visualization for dimensional control in prefabrication. Autom. Constr. 133, 103998 (2022). https://doi.org/10.1016/j.autcon.2021.103998
  • Sharifzadeh, S., Biro, I., Lohse, N., Kinnell, P.: Abnormality detection strategies for surface inspection using robot mounted laser scanners. Mechatronics 51, 59–74 (2018). https://doi.org/10.1016/j.mechatronics.2018.03.001
  • Standards Australia: 1085.1-2002 Railway track material. Part 1 steel rails. International Standards (2001)
  • European Standards: 13674-1:2011+a1:2017 Railway applications. Track. Rail vignole railway rails 46 kg/m and above. International Standards (2017)
  • Usamentiaga, R., García, D.F., de la Calle Herrero, F.J.: Real-time inspection of long steel products using 3-d sensors: calibration and registration. IEEE Trans. Ind. Appl. 54, 2955–2963 (2018). https://doi.org/10.1109/TIA.2018.2795562
  • Xiong, Z., Li, Q., Mao, Q., Zou, Q.: A 3d laser profiling system for rail surface defect detection. Sensors 17 (2017). https://doi.org/10.3390/s17081791
  • Ye, C., Acikgoz, S., Pendrigh, S., Riley, E., DeJong, M.: Mapping deformations and inferring movements of masonry arch bridges using point cloud data. Eng. Struct. 173, 530–545 (2018). https://doi.org/10.1016/j.engstruct.2018.06.094
  • Yang, J., Li, H., Campbell, D., Jia, Y.: Go-ICP: a globally optimal solution to 3D ICP point-set registration. IEEE Trans. Pattern Anal. Mach. Intell. 38, 1–1 (2015). https://doi.org/10.1109/TPAMI.2015.2513405
  • Yang, J., Yang, Y., Wang, C., Li, F.: Rotation robust non-rigid point set registration with Bayesian student’s t mixture model. Vis. Comput. 39, 367–379 (2023). https://doi.org/10.1007/s00371-021-02335-8
  • Zeng, A., Song, S., Nießner, M., Fisher, M., Xiao, J., Funkhouser, T.: 3DMatch: learning local geometric descriptors from RGB-D reconstructions. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 199–208 (2017). https://doi.org/10.1109/CVPR.2017.29
  • Zhang, J., Yao, Y., Deng, B.: Fast and robust iterative closest point. IEEE Trans. Pattern Anal. Mach. Intell. 44, 3450–3466 (2021). https://doi.org/10.1109/TPAMI.2021.3054619