Accuracy Improvement by Artificial Neural Networks in Technical Vision System

This paper proposes an Artificial Neural Network (ANN) to accurately predict the real angles obtained by a Triangulation Vision System. The performance of the ANN is compared with the K-Nearest Neighbors algorithm from previous publications. For the experimentation it was necessary to create a database to train and prove both methods in different coordinates on a determinate area through the dynamic triangulation method. Afterwards, the root mean square error is calculated to obtain the accuracy of each algorithm. Finally, several laser scanning measurements were taken at different distances to analyze the measurement dispersion of both algorithms.

[1]  Adrian Bowyer,et al.  The intellectual property implications of low-cost 3D printing , 2010 .

[2]  Oleg Sergiyenko,et al.  Surface recognition improvement in 3D medical laser scanner using Levenberg-Marquardt method , 2013, Signal Process..

[3]  Paul Kinahan,et al.  Attenuation correction for a combined 3D PET/CT scanner. , 1998, Medical physics.

[4]  Barry Berman,et al.  3D printing: the new industrial revolution , 2012, IEEE Engineering Management Review.

[5]  Matthew Turk,et al.  VITS-A Vision System for Autonomous Land Vehicle Navigation , 1988, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Don Ray Murray,et al.  Using Real-Time Stereo Vision for Mobile Robot Navigation , 2000, Auton. Robots.

[7]  Julio C. Rodríguez-Quiñonez,et al.  Implementing k-Nearest Neighbor Algorithm on Scanning Aperture for Accuracy Improvement , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.

[8]  M. Norgaard,et al.  The NNSYSID toolbox-a MATLAB(R) toolbox for system identification with neural networks , 1996, Proceedings of Joint Conference on Control Applications Intelligent Control and Computer Aided Control System Design.

[9]  Violeta Valcárcel Asencios.  Data Mining y el descubrimiento del conocimiento , 2014 .

[10]  S. Shafer,et al.  Dynamic stereo vision , 1989 .

[11]  Tan Liu,et al.  A Review of Machine Vision-Based Structural Health Monitoring: Methodologies and Applications , 2016, J. Sensors.

[12]  Marc Pollefeys,et al.  PIXHAWK: A system for autonomous flight using onboard computer vision , 2011, 2011 IEEE International Conference on Robotics and Automation.

[13]  Wendy Flores-Fuentes,et al.  Accuracy improvement in 3D laser scanner based on dynamic triangulation for autonomous navigation system , 2017, 2017 IEEE 26th International Symposium on Industrial Electronics (ISIE).

[14]  Paul J. Besl,et al.  Active, optical range imaging sensors , 1988, Machine Vision and Applications.

[15]  B. Favre-Bulle,et al.  Efficient tracking of 3D-robot positions by dynamic triangulation , 1998, IMTC/98 Conference Proceedings. IEEE Instrumentation and Measurement Technology Conference. Where Instrumentation is Going (Cat. No.98CH36222).

[16]  G Sansoni,et al.  Three-dimensional vision based on a combination of gray-code and phase-shift light projection: analysis and compensation of the systematic errors. , 1999, Applied optics.

[17]  Ashkan Moosavian,et al.  Comparison of Two Classifiers; K-Nearest Neighbor and Artificial Neural Network, for Fault Diagnosis on a Main Engine Journal-Bearing , 2013 .

[18]  Simon Haykin,et al.  Neural Networks: A Comprehensive Foundation , 1998 .