Video Object Tracking Using Kalman and Unbiased FIR Filters (I)

Resumen: Tracking of moving objects is a well-known problem of estimating the trajectory of a target in a video sequence. The video object tracking generally is accompanied by variations in the size and position of image frames; that is, consecutive video frames do not follow the object with precision in the tracking process. These variations can be considered colored measurement noise (CMN) caused by the object and camera frame dynamics. In this paper, we treat such variations as a Gauss-Markov color measurement noise. A recursive strategy in object tracking is used for the unbiased finite impulse response (UFIR) and Kalman filter (KF); each recursion has two recognized phases: predict and update. Filters are showed to be able to produce a high precision in object tracking under CMN. The standard Kalman and UFIR algorithms are tested in video sequences with different factors to affectation to demonstrate the best performance.

¿Cómo citar?

Eli G. Pale-Ramon, Yuriy S. Shmaliy, Jorge A. Ortega-Contreras, Miguel A. Vázquez Olguín & Luis J. Morales-Mendoza, Mario González-LeeVideo Object Tracking Using Kalman and Unbiased FIR Filters (I). Memorias del Congreso Nacional de Control Automático, pp. 358-363, 2021.

Palabras clave

Video object tracking, colored measurement noise, Kalman filter, unbiased FIR filter

• Bar-Shalom, Y., Rong Li, X., and Kirubarajan, T. (2001). Estimation with applications to tracking and navigation. John Wiley and Sons, Inc., Hoboken, N.J.
• Bishop, A. N., Savkin, A. V., and Pathirana, P. N. (2010). Vision-based target tracking and surveillance with robust set-valued state estimation, IEEE Signal Process. Let., 17(3), pp. 289–292.
• Brown, R. G., and Hwang, P. Y. (2012). Introduction to random signals and applied Kalman filtering: with MATLAB exercises, 4th ed. J Wiley and Sons, N.J.
• Burger, W. and Burger, M. (2009). Principles of digital image processing. Springer, London.
• Choeychuent, K., Kumhomtand, P. and Chamnongthait, K. (2006). An Efficient Implementation of the Nearest Neighbor Based Visual Objects Tracking. In 2006 Int. Symp. on Intelligent Signal Process. and Commun. Syst., Tottori, Japan, pp. 574 – 576.
• Computer Vision Lab (2015). Datasets-visual tracker benchmark. Available at: http://cvlab.hanyang.ac.kr/tracker_benchmark/datasets.ht ml. (Accessed: 25 February 2021).
• Deepak, P. and Suresh, S. (2015). Design and Utilization of Bounding Box in Human Detection and Activity Identification. Springer, Cham. Farhadi, A. and Redmon, J. (2018). Yolov3: An incremental improvement, Cornell University. Available at: https://arxiv.org/abs/1804.02767. (Accessed: 16 March 2021).
• Grewal, M. S., and Andrews, A. (2014). Kalman filtering: Theory and Practice with MATLAB. John Wiley and Sons, Hoboken, NJ.
• Jahne, B. (2004). Practical handbook on image processing for scientific and technical applications. CRC press, FL.
• Kang, T. K., Mo, Y. H., Pae, D. S., Ahn, C. K., and Lim, M. T. (2017). Robust visual tracking framework in the presence of blurring by arbitrating appearance- and feature-based detection. Measurement, 95, pp. 50-69.
• Liang, P., Blasch, E., and Ling, H. (2015). Encoding color information for visual tracking: Algorithms and benchmark, IEEE Trans. Image Process, 24(12), pp. 5630–5644.
• Murray, S. (2017). Real-time multiple object tracking-a study on the importance of speed. Cornell University. Available at: https://arxiv.org/abs/1709.03572. (Accessed: 16 March 2021).
• Padilla, R., Passos, W., Dias, T. L. B., Netto, S. L., and da Silva, E. A. B. (2021). A Comparative Analysis of Object Detection Metrics with a Companion OpenSource Toolkit. Electronics, 10(279).
• Pale-Ramon, E. G. (2021). Database. Available at: https://drive.google.com/drive/folders/1emoP9O7R0vY NGd343TSvkkUd2eitBS1h?usp=sharing. (Accessed: 08 July 2021).
• Pale-Ramon, E. G., Contreras, J., Lucio, J., Shmaliy, Y.S., Zhao, S. (2020). Recursive Algorithms for Visual Target Tracking Under Colored Measurement Noise. In 2020 24th Int. Conf. on Circuits, Syst., Commun. and Computers (CSCC), Crete Island, Greece, pp. 5-10.
• Parekh, H., Thakore, D., and Jaliya, U. (2014). A Survey on Object Detection and Tracking Methods. Int. J. of Innovative Research in Comp. and Commun. Eng., 2(2), pp. 2970-2978.
• Parmar, M. (2016). A survey of video object tracking methods. GIT-J. of Eng. and Technol., 9, pp. 519-524.
• Ramirez-Echeverria, F., Sarr, A. and Shmaliy, Y. S. (2014). Optimal memory for discrete-time fir filters in statespace. IEEE Trans. on Signal Process., 62(3), p. 557– 561.
• Shmaliy, Y. S. (2010). An iterative Kalman-like algorithm ignoring noise and initial conditions. IEEE Trans. on Signal Process., 59(6), pp. 2465–2473.
• Shmaliy, Y. S., Zhao, S., and Ahn, C. K. (2020). Kalman and UFIR state estimation with colored measurement noise using backward Euler method. IET Signal Process., 14(2), pp. 64-71.
• Shmaliy, Y. S., Zhao, S., and C. K. Ahn (2017). Unbiased finite impulse response filtering: An iterative alternative to Kalman filtering ignoring noise and initial conditions. IEEE Control Syst. Mag., 37(5), pp. 70-89.
• Simon, D. (2006). Optimal state estimation: Kalman, H∞, and nonlinear approaches. John Wiley and Sons, Hoboken, N.J.
• Solomon, C. and Breckon, T. (2011). Fundamentals of Digital Image Processing: A practical approach with examples in Matlab. John Wiley and Sons.
• Yilmaz, A., Javed, O. and Shah, M. (2006). Object tracking: A Survey. ACM Computing Surveys, 38(4), pp. 1- 45.
• Yoon, Y., Kosaka, A., and Kak, A. (2008). A new Kalmanfilter-based framework for fast and accurate visual tracking of rigid objects. IEEE Transactions on Robotics, 24(5), pp. 1238-1251.
• Zhao, S., Shmaliy, Y.S., and Ahn, C. (2018). Biasconstrained optimal fusion filtering for decentralized WSN with correlated noise sources. IEEE Trans. on Signal and Inform. Process. over Networks, 4(4), pp. 727-735.