Total views : 314

Six Object Tracking Algorithms: A Comparative Study

Affiliations

  • Department of Instrumentation and Control Engineering, National Institute of Technology, Tiruchirappalli - 620015, Tamil Nadu, India
  • Flight Mechanics and Control Division, MSDF Lab, CSIR-NAL, Bangalore - 560017, Karnataka, India

Abstract


Objectives: To compare five different objects tracking algorithms performance wise with the proposed algorithm and to find out the best one among them for tracking of an object in occlusion and Background clutter condition i.e. when background contains target features. Methods/Analysis: In the proposed algorithm, the object’s position is obtained by Mean Shift tracking and then the prediction of object’s position is done through Kalman Filter. The Proposed method has Kalman Filter which consists of an adaptive system matrix and adaptive process error covariance and measurement error covariance matrices respectively. Adaptive system matrix of Kalman Filter is getting updated online depending on the quality of observation by Mean Shift algorithm and adaptive process and measurement noise covariance matrices are getting updated according to the variation in Bhattacharya Coefficient respectively. Findings: Proposed algorithm has a maximum value (0.2177 and 0.4821) of tracking efficiency metric i.e. Bhattacharya Coefficient in both video dataset among all the algorithms and it is taking less execution time (0.002761 sec and 0.005431 sec) than other Kalman filter based tracking algorithms. Applications/Improvements: Proposed algorithm is able to track the target in occlusion and background variation condition with more efficiency and less execution time than rest of the algorithms.

Keywords

Adaptive, Covariance, Kalman Filter, Mean Shift, Occlusion, Tracking.

Full Text:

 |  (PDF views: 505)

References


  • Indhu B, Naidu VPS. Gimbaled camera control for on-point target tracking. American Research Journal of Electronics and Communication Engg, C; 2015 Feb; 1(1):1–9.
  • Naidu VPS. Fusion of radar and IRST sensor measurements for 3D target tracking using extended kalman filter. Defense Science Journal. 2009 Mar; 59(2):175-82.
  • Salhi A, Jammouss AY. Object tracking system using camshift, mean shift, and Kalman filter. World Acad Sci Eng Technol. 2012 Apr; 6(4):674–9.
  • Jatoth RK, Shubhra S, Ali Ejaz. Performance comparison of Kalman Filter and mean shift algorithm for object tracking. I J Information Engineering and Electronic Business. 2013 Mar; 5(5):17–24.
  • Comaniciu D, Ramesh V, Meer P. Kernel-based objects tracking. IEEE: Trans Pattern Anal Mach Intel. 2003 Apr; 25(5):564–77.
  • Comaniciu D, Meer P. Real-time tracking of non-rigid objects using Mean Shift. IEEE Trans Pattern Anal Machine Intel. 2000; 24(5):603-19.
  • Comaniciu D, Ramesh V, Meer P. Real-time tracking of non-rigid objects using mean shift. IEEE Proceedings of Computer Vision and Pattern Recognition. 2000 Jun. p. 142–9.
  • Jeyakar J, Babu R, Ramakrishnan KR. Robust object tracking with the background-weighted local kernels. Computer Vision Image Underst. 2008 Dec; 112(3):296–309.
  • Ning J, Zhang L, Zhang D, Wu C. Robust mean-shift tracking with corrected background-weighted histogram. IET Computer Vision. 2012 Jan; 6(1):62–9.
  • Mazinan AH, Amir-Latifi A. Applying mean shift, motion information and Kalman Filtering approaches to object tracking. ISA Transactions. 2012 May; 51(3):485–97.
  • Zhao J, Qiao W, Men G. An approach based on mean shift and Kalman Filter for target tracking under occlusion. Proceedings of the Eighth International Conference on Machine Learning and Cybernetics, Baoding; 2009 Jul 4. p. 12–5.
  • Object tracking using a Kalman filter. 2015. Available from: http://blog.cordiner.net/2011/05/03/object-tracking-using-a-kalman-filter-matlab/
  • Ahmed E, Ahmed A, Hadhoud M. A robust framework for object tracking based on corrected background weighted histogram mean shift and unscented Kalman Filter. IEEE IPAS’14: International Image Processing Applications and Systems Conference; 2014 Nov. p. 1–6.
  • Yang Y, Jia Y, Rong C. Object tracking based on corrected background-weighted histogram mean shift and Kalman Filter. Proceedings of the 2nd International Conference On Systems Engineering and Modeling; 2013 Apr. p. 687–2.
  • Karavasilis V, Nikou C, Likas A. Visual tracking by adaptive Kalman filtering and mean shift. International Journal of Computer and Electrical Engineering. 2010 May. p. 153–62.
  • Li X, Zhang T, Shen X. Object tracking using an adaptive Kalman Filter combined with mean. Shift Eng. 2010 Feb; 49(2):1-5.
  • Rene S, Georgakis C. How NOT to make the extended Kalman Filter fail. Ind Eng Chem Res. 2013 Jan; 52(9):3354–62.
  • Tian-Jian L, Zu-Tao Z. Adaptive double Kalman Filter and mean shift for robust fast object tracking. IJACT. 2013 Mar; 5(6):349–56.
  • Object tracking using a Kalman filter. 2015. Available from: http://cvlab.epfl.ch/teaching/topics/

Refbacks

  • There are currently no refbacks.


Creative Commons License
This work is licensed under a Creative Commons Attribution 3.0 License.