Improve 3D laser scanner measurements accuracy using a FFBP neural network with Widrow-Hoff weight/bias learning function

• Autorzy: Rodríguez-Quiňonez J. C. , Sergiyenko O. , Hernandez-Balbuena D. , Rivas-Lopez M. , Flores-Fuentes W. , Basaca-Preciado L. C.

Identyfikatory

DOI

10.2478/s11772-014-0203-1

• Języki publikacji: EN

Abstrakty

EN

Many laser scanners depend on their mechanical construction to guarantee their measurements accuracy, however, the current computational technologies allow us to improve these measurements by mathematical methods implemented in neural networks. In this article we are going to introduce the current laser scanner technologies, give a description of our 3D laser scanner and adjust their measurement error by a previously trained feed forward back propagation (FFBP) neural network with a Widrow-Hoff weight/bias learning function. A comparative analysis with other learning functions such as the Kohonen algorithm and gradient descendent with momentum algorithm is presented. Finally, computational simulations are conducted to verify the performance and method uncertainty in the proposed system.

Słowa kluczowe

EN

laser; scanner; neural network

• Wydawca: Stowarzyszenie Elektryków Polskich ; Polska Akademia Nauk ; Wojskowa Akademia Techniczna im. Jarosława Dąbrowskiego
• Czasopismo: Opto-Electronics Review
• Rocznik: 2014
• Tom: Vol. 22, No. 4
• Strony: 224--235
• Opis fizyczny: Bibliogr. 42 poz.. il., tab., wykr.

Twórcy

autor

Rodríguez-Quiňonez J. C.

• Faculty of Engineering, Autonomous University of Baja California, Mexicali, Baja California, Mexico

autor

Sergiyenko O.

• Engineering Institute, Autonomous University of Baja California, Mexicali, Baja California, Mexico

autor

Hernandez-Balbuena D.

• Faculty of Engineering, Autonomous University of Baja California, Mexicali, Baja California, Mexico

autor

Rivas-Lopez M.

• Engineering Institute, Autonomous University of Baja California, Mexicali, Baja California, Mexico

autor

Flores-Fuentes W.

• Faculty of Engineering, Autonomous University of Baja California, Mexicali, Baja California, Mexico

autor

Basaca-Preciado L. C.

• Engineering School, CETYS, Mexicali, Baja California, Mexico

Bibliografia

• 1. D. Hoffmeister, C. Curdt, N. Tilly, and J. Bendig, “3D terres trial laser scanning for field crop modelling”, Workshop on Remote Sensing Methods for Change Detection and Process Modelling, pp. 17–22, Cologne, 2010.
• 2. L.C. Básaca-Preciado, O.Y. Sergiyenko, J.C. Rodríguez-Quinonez, X. Garca, V.V. Tyrsa, M. Rivas-Lopez, D. Hernandez-Balbuena, P. Mercorelli, M. Podrygalo, A. Gurko, I. Tabakova, and O. Starostenko, “Optical 3D laser measurement system for navigation of autonomous mobile robot”, Opt. Laser Eng. 54, 159–169 (2014).
• 3. A. Pesci, G. Teza, E. Bonali, G. Casula, and E. Boschi, “A laser scanning based method for fast estimation of seismic-induced building deformations”, J. Photogrammetry and Remote Sensing 79, 185–198 (2013).
• 4. B. Li, L. Jiang, S. Wang, H.-L. Tsai, and H. Xiao, “Femtosecond laser fabrication of long period fibre gratings and applications in refractive index sensing”, Opt. Laser Tech. 43, 1420–1423 (2011).
• 5. Z. Zang and Y. Zhang, “Analysis of optical switching in a Yb3+-doped fibre Bragg grating by using self-phase modulation and cross-phase modulation”, Appl. Opt. 51 3424–3430 (2012).
• 6. Z. Zang, “All-optical switching in Sagnac loop mirror containing an ytterbium-doped fibre and fibre Bragg grating”, Appl. Opt. 52, 5701–5706 (2013).
• 7. Z. Zhi-Gang and Y. Wen-Xuan, “Theoretical and experimental investigation of all-optical switching based on cascaded LPFGs separated by an erbium-doped fibre”, J. Appl. Phys. 109, 103–106 (2011).
• 8. Y. Arayici, “An approach for real world data modelling with the 3d terrestrial laser scanner for built environment”, Automat. Constr. 16, 816–829 (2007).
• 9. M. Rivas, O. Sergiyenko, and V. Tyrsa, “Machine vision: approaches and limitations”, in Computer Vision, Intech. pp. 395–428, 2008.
• 10. W. Flores-Fuentes, M. Rivas-Lopez, O. Sergiyenko, F.F. Gonzalez-Navarro, J. Rivera-Castillo, D. Hernandez-Balbuena, and J.C. Rodríguez-Quinonez, “Combined application of power spectrum centroid and support vector machines for measurement improvement in optical scanning systems”, Signal Process. 98, 37–51 (2014).
• 11. R. Nian, B. He, and A. Lendasse, “3D object recognition based on geometrical topology model and extreme learning machine”, Neural Comput. Appl. 23, 427–433 (2013).
• 12. R. Shankarapillai, M. Ananthakrishnan, N. Rai, A. Mathur, and L. Mathur, “Periodontitis risk assessment using two artificial neural networks-a pilot study”, Int. J. Dental Clinics 2, 36–40 (2010).
• 13. K. Guo and G. Duan, “3D image retrieval based on differential geometry and co-occurrence matrix”, Neural Computing and Applications .doi:10.1007/s00521-012-12884. URL http:// link.springer.com/article/10.1007/s00521–012–1288–4
• 14. J.-B. Li, W.-H. Sun, Y.-H. Wang, and L.-L. Tang, “3D model classification based on nonparametric discriminant analysis with kernels”, Neural Comput. Appl. 23, 771–781 (2013).
• 15. O. Sergiyenko, V. Tyrsa, D. Hernandez-Balbuena, M. Rivas Lopez, I. Rendon Lopez, and L. Devia Cruz, “Precise optical scanning for practical multi applications”, 34th IEEE Conf. Industrial Electronics, pp. 1656–1661, Orlando, 2008.
• 16. J.C. Rodríguez-Qunionez, O. Sergiyenko, V. Tyrsa, L. Basaca, and J. Hipolito, “Continuous monitoring of rehabilitation in patients with scoliosis using automatic laser”, Pan American Health Care Exchanges, pp. 410–414, Rio de Janeiro, 2011.
• 17. L. Basaca, L.C. Básaca, J. Rodríguez, O.Y. Sergiyenko, V. Tyrsa, W. Hernández, J.I Nieto Hipólito, and O. Starostenko, “3D laser scanning vision system for autonomous robot navigation”, IEEE Inter. Symp. on Industrial Electronics, pp. 1773–1779, Bari, 2010.
• 18. A. Rogalski, “History of infrared detectors”, Opto-Electron. Rev. 20, 279–308 (2012).
• 19. T.A. Hamdalla, “Theoretical and artificial neural network modelling for the output power of irradiated erbium doped fibre amplifier”, Opt. Laser Tech. 49, 264–267 (2013).
• 20. S.K. Kumari, “A novel algorithm for uplink interference suppression using smart antennas in mobile communications”, Master’s thesis, Florida State University, 2004.
• 21. S. Haykin, Introduction to Adaptive Filters, Macmillan, 1985.
• 22. G. Lathen, T. Andersson, R. Lenz, and M. Borga, Momentum Based Optimization Methods for Level Set Segmentation, Springer SSVM, pp. 124–136, Norway, 2009.
• 23. J. Nocedal and S.J. Wright, Numerical Optimization, Springer, 1999.
• 24. X.S. Zhang, Neural Networks in Optimization, Springer, 2000.
• 25. J.F. Bonnans, J.C. Gilbert, C. Lamarechal, and C.A. Sagastizabal, Numerical Optimization, Springer, 2006.
• 26. D. Marquardt, “An algorithm for least-squares estimation of nonlinear parameters”, SIAM Journal on Applied Mathematics 11, 431–441 (1963).
• 27. B.M. Wilamowski and H. Yu, “Improved computation for Levenberg Marquardt training”, IEEE T. Neural Networks 21, 930–937 (2010).
• 28. F. Huang, K. Fehrs, G. Hartmann, and R. Klette, “Wide-angle vision for road views”, Opto-Electron. Rev. 21, 1–22 (2013).
• 29. A. Abba, F. Caponio, A. Geraci, and G. Ripamontii, “Non-linear least-squares in fpga devices for digital spectroscopy”, Nuclear Science Symposium Conf. Record, pp. 563–568, Orlando, 2009.
• 30. J. Będkowski and J. Naruniec, “On-line range images registration with GPGPU”, Opto-Electron. Rev. 21, 52–62 (2013).
• 31. T. Mathworksl, Neural Networks Toolbox Users Guide, The Mathworks, 2000.
• 32. A.L. Betker, T. Szturm, and Z. Moussavii, “Application of feedforward backpropagation neural network to center of mass estimation for use in a clinical environment”, Engineering in Medicine and Biology Society, Man, pp. 2714, 2003.
• 33. M. Sugiyama, M. Krauledat, and K.R. Muller, “Covariate shift adaptation by importance weighted cross validation”, J. Machine Learning Research, 985–1005, (2007).
• 34. J.C. Rodriguez-Quinonez, O. Sergiyenko, and F.F. Gonzalez−Navarro, L. Basaca−Preciado, and V. Tyrsa, “Surface recognition improvement in 3d medical laser scanner using Levenberg-Marquardt method”, Signal Process. 93, 378–286 (2013).
• 35. J.C. Rodríguez-Quinonez, O. Sergiyenko, L. Basaca-Preciado, V. Tyrsa, A.G. Gurko, M.A. Podrygalo, M. Rivas-Lopez, and D. Hernandez-Balbuena, “Optical monitoring of scoliosis by 3D medical laser scanner”, Opt. Laser Eng. 54, 175–186 (2014).
• 36. B. Huang, C. Yu, and B.D. Anderson, “Analysing localization errors in one dimensional sensor networks”, Signal Process. 92, 427–438 (2012).
• 37. J. Chen, X. Wu, M.Y. Wang, and X. Li, “3D shape modelling using a self developed hand-held 3D laser scanner and an efficient ht-icp point cloud registration algorithm”, Opt. Laser Techn. 45, 414–423 (2013).
• 38. D. García-San-Miguel and J. Lerma, “Geometric calibration of a terrestrial laser scanner with local additional parameters: An automatic strategy”, J. Photogrammetry and Remote Sensing 79, 122–136 (2013).
• 39. W.Y. Yan, A. Shaker, A. Habib, and A.P. Kersting, “Improving classification accuracy of airborne lidar intensity data by geometric calibration and radiometric correction”, J. Photo-grammetry and Remote Sensing 67, 35–44 (2012).
• 40. M.K. Transtrum and J.P. Sethna, “Improvements to the Levenberg-Marquardt algorithm for nonlinear least-squares minimization”, J. Computational Physics, 2012.
• 41. O. Yu. Sergiyenko, “Optoelectronic system for mobile robot navigation”, Optoelectronics Instrumentation and Data Processing 46, 414–428 (2010).
• 42. L. Lidner, O. Sergiyenko, V. Tyrsa, and P. Mercorelli, “An approach for dynamic triangulation using servomotors”, IEEE 23rd Inter. Symp. on Industrial Electronics, pp. 1926–1931, Istanbul, 2014.