Untitled Document
You are from : ( )  
Untitled Document
Untitled Document

International Journal of Information Technology & Computer Science ( IJITCS )

Abstract :

This paper propose a two dimensional behavior analysis for mouse in a cage. Animal behavior analysis is important to task for various area. Furthermore, we are interested in mouse tracking that automation behavior analysis which is becoming crucial task in many fields such as Biology and Medical Engineering. Mouse tracking is challenged by some difficulties that due to non-rigid objects, drastic movement, cluttered environments. We propose a method by dividing into two parts against robust to these problems: Detection and Tracking. First, we propose to detect foreground objects in order to represent whole appearance of the mouse. Second, we propose to use the ellipse model for tracking. The ellipse model not only can represent the whole appearance of the mouse, but provide various information of relevant behavior patterns such as stretch out and stand up motions. The tracking is implemented based on extended Kalman filter (EKF). The effectiveness of the proposed approach is demonstrated for a variety of mouse behavior in using video sequences. Our experiments demonstrate how the proposed method can operate reliably under severe appearance change of targets and cluttered environments .

Keywords :

: Mouse Tracking, Behavior Analysis, Kalman Filter (KF), Extended Kalman Filter (EKF).

References :

  1. Burghardt, T. and N. Campbell. Individual animal identification using visual biometrics on deformable coat patterns. in Proceedings of the 5th International Conference on Computer Vision Systems, Berlin, Germany.. Accessed. 2007.
  2. Gonçalves, W.N., et al., Hidden markov models applied to snakes behavior identification, in Advances in Image and Video Technology. 2007, Springer. p. 777-787.
  3. Burghardt, T. and J. Ćalić. Real-time face detection and tracking of animals. in Neural Network Applications in Electrical Engineering, 2006. NEUREL 2006. 8th Seminar on. 2006. IEEE.
  4. Zhou, J. and C.M. Clark. Autonomous fish tracking by rov using monocular camera. in Computer and Robot Vision, 2006. The 3rd Canadian Conference on. 2006. IEEE.
  5. Wawerla, J., et al., Bearcam: Automated wildlife monitoring at the arctic circle. Machine Vision and Applications, 2009. 20(5): p. 303-317.
  6. Figueiredo, G., et al. Development of machine vision based poultry behavior analysis system. in Proc. ASAE Annual Internat. Meeting. 2003. Citeseer.
  7. Tweed, D. and A. Calway. Tracking Many Objects Using Subordinated Condensation. in BMVC. 2002.
  8. Doucet, A., S. Godsill, and C. Andrieu, On sequential Monte Carlo sampling methods for Bayesian filtering. Statistics and computing, 2000. 10(3): p. 197-208.
  9. Arulampalam, M.S., et al., A tutorial on particle filters for online nonlinear/non-Gaussian Bayesian tracking. Signal Processing, IEEE Transactions on, 2002. 50(2): p. 174-188.
  10. Kay, S.M., Fundamentals of Statistical Signal Processing: Practical Algorithm Development. Vol. 3. 2013: Pearson Education.
  11. Welch, G. and G. Bishop, An introduction to the kalman filter. 2006. University of North Carolina: Chapel Hill, North Carolina, US, 2006.
  12. Jaward, M., et al. Multiple object tracking using particle filters. in Aerospace Conference, 2006 IEEE. 2006. IEEE.

Untitled Document
Untitled Document
  Copyright © 2014  IJITCS.  All rights reserved. IISRC® is a registered trademark of IJITCS Properties.