An improved neural networks for stereo-camera calibration

• Autorzy: Xing Y. J. , Xing J. , Sun J. , Hu L.
• Konferencja: 12th International Scientific Conference CAM3S'2006, 27-30th November 2006, Gliwice-Zakopane
• Języki publikacji: EN

Abstrakty

EN

Purpose: Improve the generalization capability and speed of back-propagation neural network (BPNN). Design/methodology/approach: In this paper, CCD cameras are calibrated implicitly using BP neural network by means of its ability to fit the complicated nonlinear mapping relation. Conventional BP algorithms easily fall into part-infinitesimal, slowing speed of convergence and exorbitance training that will influence the training result, delay convergence time and debase generalization capability. During our experiments, dense sample data are acquired by using high precisely numerical control platform, and the variances error (PVE) is adopted during training the neural network. Findings: Experiments indicate that the neural network used PVE has great generalization. The error percentages obtained from our set-up are limitedly better than those obtained through Mean Square Error (MSE). The system is generalization enough for most machine-vision applications and the calibrated system can reach acceptable precision of 3D measurement standard. Research limitations/implications: The value needs to be decided by experiments, and the reconstruction images will be distorted if the value is more than 6. Originality/value: The variances error is be adopted in BPNN first.

Słowa kluczowe

EN

image analysis; stereo vision; neural networks; BP neural network; visual systems

PL

analiza obrazu; widzenie stereoskopowe; sieci neuronowe; sieć neuronowa BP; system wizyjny

• Wydawca: International OCSCO World Press
• Czasopismo: Journal of Achievements in Materials and Manufacturing Engineering
• Rocznik: 2007
• Tom: Vol. 20, nr 1-2
• Strony: 315--318
• Opis fizyczny: Bibliogr. 15 poz., fot., rys., tab.

Twórcy

autor

Xing Y. J.

autor

Xing J.

autor

Sun J.

autor

Hu L.

• Dalian University of Technology, Key Laboratory for Precision and Non-traditional Machining Technology of Ministry of Education, 116023, P.R. China,

Bibliografia

• [1] L. Guan, H. Kong, A real-time machine vision system for visual information processing, Proceedings of International Conference on Systems, Man, and Cybernetics, 1994, 2:1375-1380.
• [2] K. Niranjan Prasad, B. Ramamoorthy, Tool wear evaluation by stereo vision and prediction by artificial neural network Journal of Materials Processing Technology, 112 (2001) 43-52.
• [3] D. Yongtae. Application of neural networks for stereo-camera calibration. Proceedings of conference on Neural Networks, 1999, 2719 - 2722.
• [4] K. Zhang, B. Xu, L.X.Tang, H.M.Shi, Camera Calibration of Binocular Vision System Based on BP Neural Network, Journal of Machinery & Electronics 12 (2005) 12-14.
• [5] B. Endelt, K.B. Nielsen, J. Danckert, New framework for on-line feedback control of a deep-drawing operation, Journal of Materials Processing Technology, 177 (2006) 426-429.
• [6] F. Cupertino, V. Giordano, E. Mininno, A neural visual servoing in uncalibrated environments for robotic manipulators. Proceedings of Conference on Systems, Man and Cybernetics, 6, 2004, 5362 - 5367.
• [7] L.N. Smith, M.L. Smith, Automatic machine vision calibration using statistical and neural network methods Journal of Image and Vision Computing, 23 (2005) 887-899.
• [8] F. Dieterle, S. Busche, G. Gauglitz, Growing neural networks for a multivariate calibration and variable selection of time-resolved measurements, Journal of Analytica Chimica Acta, 490 (2003) 71-83.
• [9] U. Zuperl, F. Cus, B. Mursec ,T. Ploj ,A generalized neural network model of ball-end milling force system, Journal of Materials Processing Technology, 175 (2006) 98-108.
• [10] M. Lhuillier and L. Quan, Quasi-Dense Reconstruction from Image Sequence, Proc. Seventh European Conf. Computer Vision 2 (2002) 125-139.
• [11] Q. Memony, S. Khan, Camera calibration and three-dimensional world reconstruction of stereo-vision using neural networks, Journal of Systems Science 32 (2001) 1155 – 1159.
• [12] N. Uchida, T. Shibahara, T. Aoki, H. Nakajima, K. Kobayashi,3D Face Recognition Using Passive Stereo Vision, Proceedings of ICIP 2 (2005) 950-953.
• [13] S.S. Panda, A.K. Singh, D. Chakraborty, S.K. Pal, Drill wear monitoring using back propagation neural network, Journal of Materials Processing Technology, 172 (2006):283-290.
• [14] J.P. Wang, Y.C. Chueh, Neural network approach to recognize the grid patterns in experimental mechanics, Journal of Materials Processing Technology, 140 (2003) 90-94.
• [15] A.W. Zhang, Z. Sui, S.X. Hu, J.J. Chen, M.Z. Li. Method for vision system calibration based on neural network. Journal of optical technique, 27 (2001) 302-304.