IJSEA Archive (Volume 6, Issue 10)
International Journal of Science and Engineering Applications (IJSEA) (Volume 6, Issue 10 October 2017)
A Neuro-Fuzzy Based Approach to Object Tracking and Motion Prediction
Keywords: ANFIS, Charge couple device (CCD)-Positioning System, DC servomotor, Segmentation
In this Paper, object tracking system model was developed using Neuro-Fuzzy hybrid based approach to predict the trajectory of an object moving around a scene. Servo motors were used to perform high-precision positioning in azimuth and elevation directions, fuzzy logic is applied to control the position servo motors via feedback. A Neuro-Fuzzy hybrid approach is used to design the fuzzy rule base of the intelligent system for control. In particular, ANFIS methodology was used to build a Sugeno fuzzy model for controlling the servo motor position carrying charge couple device camera (CCD) on a chaotic trajectory. An advanced test bed is used in order to evaluate the tracking properties and the robustness of the ANFIS controller operations. However, the variations of the Mechanical configuration of the drive, which is common to these two applications, can lead to error in object positioning before segmentation. The result for the azimuth and elevation time responses show that the rise time tr reduces to 0.1 and 0.3, respectively. The settling time decreases to 0.5 for the motors with ANFIS controller, the delay time reduces to 0.1 for both motors. Steady state was reached. Conclusively, ANFIS controller output was the best in terms of faster rise time, settling time, reduced delay time and object position stabilization.
 Sunitha.M, S. (2013). Real time object Tracking. International Journal of Emerging Technology and Advance Engineering., 3(3), 2250–2459.
 Ramya G, (2014). Real time visual surveilance. Global Journal of Researchesin Engineering, 14(6).
 Jain A. (1999). Object tracking using Fuzzy Logic for khepera 11 Robot. Journal of Electrical and Electronics Engineering, 46(5), 315.
 Lopes. (2011). Fuzzy Logic based approach for object features.
 Landge. (2014). Tracking using Background Subtraction. An international Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, 3(7), 45-65
 Ghate & Gawi. (2014). Object detection using Neural Network. 1(2 ).
 Zhong QU, Quingquing Zhang, T. G. (2012). Moving Object Tracking based on Codebook and Particle Filter. Internatinal Workshop on Information
 Yilmaz Alper, J. O. and S. M. (2006). Object Tracking: A survey”. ACM Compt. Surv., 1–45.
 Evlampios Apostolidis. (2013). Fast object Re-detection and Localization in video For Spatio- Temporal fragmen. In International Conference on fast Molina, José M,
 Jesús García, (2003). Neuro-Fuzzy Technique for image analyis. IEE Journal of Advance Science Technology, 5(8), 209–231.
 Jang, S. (2015). Fuzzy Control of data systems for moving vehicle using Robust Cotrollers. Journal of science Mathematics and Physics , 36-46.
 Sidney R. Bowes, Fellow, Derrick Holliday. (2004). New Natural Observer Applied to Speed-Sensor less DC Servo and Induction Motors. IEEE Conference Control.
 Javiya, K. a. (2016). Comparisons of Different Controller for Position Tracking of DC Servo Motor. International Journal of Advanced Research in Electrical Engineering, Vol. 5 ( Issue 2), 966-967.
 Bolton, W. (Experiment Note,1999). pp. 1-10.
 Jane,(Handbook of Servo Control,2014)
 Lofti A. Zadeh and Berkeley, C. (1995). Fuzzy Logic Toolbox User's Guide. Matlab Image Processing Toolbox User Guide. (2004).
title = " A Neuro-Fuzzy Based Approach to Object Tracking and Motion Prediction ",
journal = "International Journal of Science and Engineering Applications (IJSEA)",
volume = "6",
number = "10",
pages = "307 - 321 ",
year = "2017",
author = " Engr. Simon Samuel, Engr. Ibrahim A. Usman, Engr. Baams Baamani Alfred ",