Abstract
In recent years, visual tracking algorithms based on state estimators have been developed in order to improve the performance during tracking tasks. However, this performance changes according to target type, object kinematics and scenario complexity. When working with high-speed maneuvering targets, tracking errors increase considerably due to low response of estimators as well as the kinematic mismatch betwen the real motion profile and the one assumed by the estimator. Some examples of objects that present this high-speed behavior are rockets, aircrafts and missiles. To overcome this visual tracking problem, this work proposes an interacting multiple model algorithm based on four kinematic models: constant velocity, constant acceleration, constant turn and thrust acceleration. We present three different scenarios with complex maneuvers for comparison study, and experimental results show that visual tracking is improved when using the proposed strategy.
Similar content being viewed by others
References
Hem, L., Daiqin, Y., Zhenzhong, C.: Adaptive background for real-time visual tracking. In: International Conference on Multimedia and Expo, Seattle, USA (2016)
Fanxiang, Z., Xuan, L., Zhitong, H., Yuefeng, J.: Kernel based multiple cue adaptive appearance model for robust real-time visual tracking. IEEE Signal Processing Letters 20(11), 1094–1097 (2013)
Pang, Y., Shi, X., Jia, B., Blasch, E., Sheaff, C., Pham, K., Chen, G., Ling, H.: Multiway Histogram Intersection for Multi-target Tracking. In: 18th International Conference on Information Fusion, Washington DC, pp. 1938–1945 (2015)
Can, W., Hong, L., Yuan, G.: Scene-Adaptive Hierarchical data association for multiple objects tracking. IEEE Signal Processing Letters 21(6), 697–701 (2014)
Leizea, I., Mendizabal, A., Alvarez, H., Aguinaga, I., Borro, D., Sanchez, E.: Real-time visual tracking of deformable objects in robot asisted surgery. IEEE Comput. Graph. Appl. 37(1), 56–68 (2017)
Bertinetto, L., Valmadre, J., Golodetz, S., Miksik, O., Torr, P.: Staple: Complementary learners for Real-Time tracking. In: IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, Nevada, USA, pp. 1401–1409 (2016)
McDonagh, S., Klaudiny, M., Bradley, D., Beeler, T., Matthews, I., Mitchell, K.: Synthetic prior design for real-time face tracking. In: 4th International Conference on 3D Vision, California, USA, pp. 639–648 (2016)
Henk, A.: An Efficient Filter for Abruptly Changing Systems. In: IEEE 23rd Conference on Decision and Control, Las Vegas, Nevada (1984)
Henk, A, Yaakov, B.: The interacting multiple model algorithm for systems with markovian switching coefficients. IEEE Trans. Automatic Control 33(8), 780–783 (1988)
Mazor, E., Aberbuch, A., Bar-Shalom, Y., Dayan, J.: Interacting multiple model methods in target tracking: A survey. IEEE Trans. Aerospace Electronic Syst 34(1), 103–123 (1998)
Farmer, M., Hsu, R., Jain, A.: Interacting multiple model (IMM) Kalman filters for robust high speed human motion tracking. In: I16th International Conference on Pattern Recognition, Quebec, Canada (2002)
Dhassi, Y., Aarab, A., Alfidi, M.: IMM-PF visual tracking based on multi-feature fusion. In: 11th International Conference on Intelligent Systems: Theories and Applications (SITA), Mohammedia, Morocco (2016)
Genovese, A.: The Interacting multiple model algorithm for accurate state estimation of maneuvering targets. Johns Hopkins Apl Techical Digest 22(4), 614–623 (2001)
Grabner, H., Grabner, M., Bischof, H.: Real-time tracking via on-line boosting. In Proc BMVC 1, 47–56 (2006)
Blair, W., Watson, G., Alouani, A.: Use of kinematic constraint for tracking constant speed maneuvering targets, INAVSWCTR 91-561, Naval Surface Warfare Center, Dahlgren, VA (1991)
Acknowledgments
The authors would like to thank the Instituto Politécnico Nacional de México, CONACyT and Instituto de Investigación y Desarrollo Tecnológico de la Armada de México for funding this project.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher’s Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Sánchez-Ramírez, E.E., Rosales-Silva, A.J., Vianney-Kinani, J.M. et al. A Four-Model Based IMM Algorithm for Real-Time Visual Tracking of High-Speed Maneuvering Targets. J Intell Robot Syst 95, 761–775 (2019). https://doi.org/10.1007/s10846-018-0926-1
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10846-018-0926-1