SCIENCE CHINA Information Sciences, Volume 59, Issue 4: 042412(2016) https://doi.org/10.1007/s11432-015-5516-2

A low-complexity sensor fusion algorithm based on a fiber-optic gyroscope aided camera pose estimation system

More info
  • ReceivedSep 16, 2015
  • AcceptedOct 20, 2015
  • PublishedFeb 1, 2016


Visual tracking, as a popular computer vision technique, has a wide range of applications, such as camera pose estimation. Conventional methods for it are mostly based on vision only, which are complex for image processing due to the use of only one sensor. This paper proposes a novel sensor fusion algorithm fusing the data from the camera and the fiber-optic gyroscope. In this system, the camera acquires images and detects the object directly at the beginning of each tracking stage; while the relative motion between the camera and the object measured by the fiber-optic gyroscope can track the object coordinate so that it can improve the effectiveness of visual tracking. Therefore, the sensor fusion algorithm presented based on the tracking system can overcome the drawbacks of the two sensors and take advantage of the sensor fusion to track the object accurately. In addition, the computational complexity of our proposed algorithm is obviously lower compared with the existing approaches (86% reducing for a 0.5 min visual tracking). Experiment results show that this visual tracking system reduces the tracking error by 6.15% comparing with the conventional vision-only tracking scheme (edge detection), and our proposed sensor fusion algorithm can achieve a long-term tracking with the help of bias drift suppression calibration.

Funded by

International S&T Cooperation Program of China(2015DFG12520)

National Natural Science Foundation of China(61571379)

National Natural Science Foundation of China(61275005)


[1] Klein G S W, Drummond T W. Image Vision Comput, 2004, 22: 769-776 CrossRef Google Scholar

[2] Hol J D. Pose Estimation and Calibration Algorithms for Vision and Inertial Sensors. Sweden Linköping: Linköping Univ Press, 2008. 7--23. Google Scholar

[3] Song S, Qiao W, Li B, et al. IEEE Trans Magn, 2014, 50: 4003707-776 Google Scholar

[4] Wang Q, Chen W P, Zheng R, et al. Inf Process Sens Netw, 2003, 2634: 642-657 CrossRef Google Scholar

[5] Zhang X, Hu W, Xie N, et al. Int J Comput Vis, 2015, 115: 279-304 CrossRef Google Scholar

[6] Zhang X, Hu W, Maybank S, et al. Sequential particle swarm optimization for visual tracking. In: Proceedings of IEEE International Conference on Computer Vision and Pattern Recognition, Anchorage, 2008. 1--8. Google Scholar

[7] Li Y, Ai H, Yamashita T, et al. IEEE Trans Anal, 2008, 30: 1728-1740 Google Scholar

[8] Park I K, Singhal N, Lee M H, et al. IEEE Trans Parall Distr, 2011, 22: 91-104 CrossRef Google Scholar

[9] Erdem A T, Ercan A O. IEEE Trans Image Process, 2015, 24: 538-548 CrossRef Google Scholar

[10] Foxlin E. Inertial head-tracker sensor fusion by a complementary separate-bias Kalman filter. In: Proceedings of IEEE Virtual Reality Annual International Symposium, Santa Clara, 1996. 185--194. Google Scholar

[11] Hol J D, Dijkstra F, Luinge H, et al. Tightly coupled UWB/IMU pose estimation. In: Proceedings of IEEE International Conference on Ultra-Wideband, Vancouver, 2009. 688--692. Google Scholar

[12] He P, Cardou P, Desbiens A, et al. Multibody Syst Dyn, 2014, 35: 1-27 Google Scholar

[13] Corke P, Lobo J, Dias J. Int J Robot Res, 2007, 26: 519-535 CrossRef Google Scholar

[14] Starner T. IEEE Pervas Comput, 2013, 12: 14-16 Google Scholar

[15] Chai L, Nguyen K, Hoff B, et al. An adaptive estimator for registration in augmented reality. In: Proceedings of 2nd IEEE and ACM International Workshop on Augmented Reality, San Francisco, 1999. 23--32. Google Scholar

[16] You S, Neumann U. Fusion of vision and gyro tracking for robust augmented reality registration. In: Proceedings of IEEE Conference on Virtual Reality, Yokohama, 2001. 71--78. Google Scholar

[17] Zhang G. The Principles and Technologies of Fiber-Optic Gyroscope. Beijing: National Defense Industry Press, 2008. 1--25. Google Scholar

[18] Barbour N, Schmidt G. IEEE Sens J, 2001, 1: 332-339 CrossRef Google Scholar

[19] Hwangbo M, Kim J S, Kanade T. Int J Robot Res, 2011, 30: 1755-1774 CrossRef Google Scholar

[20] Yu J, Wang Z F. Sci China Inf Sci, 2014, 57: 029101-1774 Google Scholar

[21] Gonzalez R C, Woods R E, Eddins S L. Digital Image Processing Using Matlab. Beijing: Publishing House of Electronics Industry, 2014. 205--229. Google Scholar

[22] Wang X, He C, Wang Z. Opt Lett, 2011, 36: 1191-1193 CrossRef Google Scholar

[23] He C, Yang C, Wang Z. Opt Eng, 2012, 51: 124401-1193 CrossRef Google Scholar

Copyright 2020 Science China Press Co., Ltd. 《中国科学》杂志社有限责任公司 版权所有

京ICP备18024590号-1       京公网安备11010102003388号