Improve a 3D distance measurement accuracy in stereo vision systems using optimization methods’ approach

Abstract This paper presents a 3D distance measurement accuracy improvement for stereo vision systems using optimization methods A Stereo Vision system is developed and tested to identify common uncertainty sources. As the optimization methods are used to train a neural network, the resulting equation can be implemented in real time stereo vision systems. Computational experiments and a comparative analysis are conducted to identify a training function with a minimal error performance for such method. The offered method provides a general purpose modelling technique, attending diverse problems that affect stereo vision systems. Finally, the proposed method is applied in the developed stereo vision system and a statistical analysis is performed to validate the obtained improvements.

[1]  Chao-Ton Su,et al.  Neural networks for precise measurement in computer vision systems , 1995 .

[2]  Yandong Tang,et al.  A High-Precision Calibration Method for Stereo Vision System , 2011 .

[3]  Emile A. Hendriks,et al.  Adaptive stereo similarity fusion using confidence measures , 2015, Comput. Vis. Image Underst..

[4]  Wei-Song Lin,et al.  Accurate linear technique for camera calibration considering lens distortion by solving an eigenvalue problem , 1993 .

[5]  Xavier Armangué,et al.  A comparative review of camera calibrating methods with accuracy evaluation , 2002, Pattern Recognit..

[6]  Isabelle Bloch,et al.  Recursive head reconstruction from multi-view video sequences , 2014, Comput. Vis. Image Underst..

[7]  M. Hanke.  Conjugate gradient type methods for ill-posed problems , 1995 .

[8]  Marek R. Ogiela,et al.  Real time area-based stereo matching algorithm for multimedia video devices , 2013 .

[9]  Sohaib Khan,et al.  Camera calibration and three-dimensional world reconstruction of stereo-vision using neural networks , 2001, Int. J. Syst. Sci..

[10]  Yongtae Do.  Application of neural networks for stereo-camera calibration , 1999, IJCNN'99. International Joint Conference on Neural Networks. Proceedings (Cat. No.99CH36339).

[11]  D. Marquardt.  An Algorithm for Least-Squares Estimation of Nonlinear Parameters , 1963 .

[12]  Xianyu Su,et al.  A new approach for the bundle adjustment problem with fixed constraints in stereo vision , 2012 .

[13]  Lu Lu,et al.  High precision camera calibration in vision measurement , 2007 .

[14]  Julio C. Rodriguez-Quinonez,et al.  Optical monitoring of scoliosis by 3D medical laser scanner , 2014 .

[15]  Oleg Starostenko,et al.  Optical 3D laser measurement system for navigation of autonomous mobile robot , 2014 .

[16]  M. Jalali-Heravi,et al.  QSAR study of heparanase inhibitors activity using artificial neural networks and Levenberg-Marquardt algorithm. , 2008, European journal of medicinal chemistry.

[17]  Juan Andrade-Cetto,et al.  Uncertainty analysis of the DLT-Lines calibration algorithm for cameras with radial distortion , 2015, Comput. Vis. Image Underst..

[18]  Yang Xu,et al.  Calibration for stereo vision system based on phase matching and bundle adjustment algorithm , 2015 .

[19]  Indrajit Mukherjee,et al.  Comparing the performance of neural networks developed by using Levenberg-Marquardt and Quasi-Newton with the gradient descent algorithm for modelling a multiple response grinding process , 2012, Expert Syst. Appl..

[20]  Hao Yu,et al.  Improved Computation for Levenberg–Marquardt Training , 2010, IEEE Transactions on Neural Networks.

[21]  Reinhard Klette,et al.  Wide-angle vision for road views , 2013 .

[22]  Stephen J. Wright,et al.  Numerical Optimization , 2018, Fundamental Statistical Inference.

[23]  Tugrul U. Daim,et al.  Using artificial neural network models in stock market index prediction , 2011, Expert Syst. Appl..

[24]  Wendy Flores-Fuentes,et al.  Energy Center Detection in Light Scanning Sensors for Structural Health Monitoring Accuracy Enhancement , 2014, IEEE Sensors Journal.

[25]  Antonios Gasteratos,et al.  A stereo matching approach based on particle filters and scattered control landmarks , 2015, Image Vis. Comput..

[26]  Tao Lin,et al.  Recognition of the initial position of weld based on the image pattern match technology for welding robot , 2005 .

[27]  Jatinder N. D. Gupta,et al.  Comparative evaluation of genetic algorithm and backpropagation for training neural networks , 2000, Inf. Sci..

[28]  O. Sergiyenko,et al.  Improve 3D laser scanner measurements accuracy using a FFBP neural network with Widrow-Hoff weight/bias learning function , 2014 .

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

[30]  Reinhard Klette,et al.  Computer vision - three-dimensional data from images , 1998 .

[31]  Melvyn L. Smith,et al.  Automatic machine vision calibration using statistical and neural network methods , 2005, Image Vis. Comput..

[32]  Cihan H. Dagli,et al.  The use of feedforward neural networks for machine vision calibration , 1999 .

[33]  Dorian Garcia,et al.  Accurate Calibration of a Stereovision Sensor: Comparison of Different Approaches , 2000, VMV.