Study on Calibrating Method of FOB Position Tracker Based on Neural Network

Abstract:

Due to the instability and low precision of electromagnetic position trackers and the inefficiency of existing calibrating methods, a method with high accuracy and effectiveness for FOB (Flock of Birds) calibration was studied. The components, operational principle, merits and drawbacks of FOB were briefly introduced. The positions of 343 sampling points set in the effective working area were measured and the data was processed for trainings and tests of the calibration model established using genetic algorithm and BP algorithm. Experiments were conducted to verify the effectiveness of the method and the results showed the calibrated tracker’s average errors in the X, Y, and Z direction were 0.86cm, 0.70cm and 0.83cm respectively, meeting the requirements of human-computer interaction.

• Periodical: Applied Mechanics and Materials (Volumes 556-562)
• Pages: 5945-5950
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.556-562.5945
• Online since: May 2014
• Authors: Shan Shan Li, Zhong Xiang Zhu*, Bo Liu, Zheng He Song, En Rong Mao, Shang Guan Lantian
• Keywords: BP Algorithm, Calibration, FOB, Genetic Algorithm (GA), Neural Network (NN)

References

[1] Czemuszenko M, Sandin D, Defanti T, Line of sight method for tracker calibration in projection-based VR systems. In: Proceedings 2nd International Immersive Projection Technology Workshop. Ames IO (May 1998).

[2] M.A. Nixon, B.C. McCallum, W.R. Fright, and N.B. Price, The Effect of Metals and Interfering Fields on Electromagnetic Trackers. Presence: Technology and Virtual Environments, vol. 7 (1998), p.204–218.

DOI: 10.1162/105474698565587

[3] M.A. Livingston and A. State, Magnetic Tracking Calibration for Improved Augmented Reality System, Presence: Teleoperators and Virtual Environment, vol. 6 (1997), p.533–546.

DOI: 10.1162/pres.1997.6.5.532

[4] Chen Junjie, Huang Weiyi, Fitting of sensor output character based on genetic neural network. Journal of Transcluction Technology, 2001, 14(4), p.323–327. (In Chinese).

[5] Qian Guangyao, Zhao Xingguang, Fitting of output character of consistency sensor based on genetic algorithm and linear neural network. Transactions of China Electrotechnical Society, 2007, 22(11), p.17–20, 40. (In Chinese).

[6] Qian Guangyao, Xia Eryong, Wang Huyang, Zhang Wenhao, Fitting of sensor output character based on genetic algorithm and wavelet neural network. Measurement Technique, 2011, (9), p.3–6. (In Chinese).

[7] Xu Jing, Research on human-machine interaction for typical agricultural equipment. Beijing: China Agricultural University. 2010. (In Chinese).

[8] Wang Zhaoqi, Gao Wen, Xu Yan, A sensor-based method to capture motion of two arms. Chinese Journal of Computers, 2001, 24(6), p.616–619. (In Chinese).

[9] Ascension Technology Corporation, The Flock of Birds: Installation and operation guide. (January 18, 1999), p.1–131.

[10] Cui Yanping, Lin Yuchi, Zhang Xiaoling, Study on camera calibration for binocular vision based on neural network. Journal of Optoeletronics • Laser, 2005, 16(9), p.1097–1100. (In Chinese).

[11] Ikits, M., Brederson, J.D., Hansen, C.D., Hollerbach, J.M., An improved calibration framework for electromagnetic tracking devices. Proceedings - Virtual Reality Annual International Symposium, Institute of Electrical and Electronics Engineers Computer Society: Yokohama, Japan, IEEE Computer Society, p.63–70, (2001).

DOI: 10.1109/vr.2001.913771