Journal of Mechanical Science and Technology

The Korean Society of Mechanical Engineers (대한기계학회)
권호 표지

Image Processed Tracking System of Multiple Moving Objects Based on Kalman Filter

  • Kim, Sang-Bong (Department of Mechanical Engineering, Pukyong National University) ;
  • Kim, Dong-Kyu (Department of Mechanical Engineering, Pukyong National University) ;
  • Kim, Hak-Kyeong (Department of Mechatronics Engineering, Pukyong National University)
  • Published : 2002.04.01
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a development result for image processed tracking system of multiple moving objects based on Kalman filter and a simple window tracking method. The proposed algorithm of foreground detection and background adaptation (FDBA) is composed of three modules: a block checking module(BCM), an object movement prediction module(OMPM), and an adaptive background estimation module (ABEM). The BCM is processed for checking the existence of objects. To speed up the image processing time and to precisely track multiple objects under the object's mergence, a concept of a simple window tracking method is adopted in the OMPM. The ABEM separates the foreground from the background in the reset simple tracking window in the OMPM. It is shown through experimental results that the proposed FDBA algorithm is robustly adaptable to the background variation in a short processing time. Furthermore, it is shown that the proposed method can solve the problems of mergence, cross and split that are brought up in the case of tracking multiple moving objects.

Keywords

References

  1. Brofferio S. et al, 1990, 'A Background Updating Algorithm for Moving Object Scenes, 'Time-varying Image Processing and Moving Object Recognition, Vol. 2, Elsevier Publishers B. V., Amsterdam, The Netherlands, pp. 289-296
  2. Chapman and Hall, Image Precessing, Analysis and Machine Vision, 2-6 Boundary Row, London SEI 8HN
  3. Gonzalez R. C., 1992, Digital Image Processing, Addison Wesley
  4. Gregory A. B., 1994, Digital Image Processing, Wiley and Sons
  5. Jee M. S., Kim S. B., 1994, 'Development of Two Dimensional Position Measuring for Floating Stucture Using an Image Processing Method,' Journal of Ocean engineering and technology, Vol. 8(2), pp. 22-27
  6. Karmann K. P., Brandt A. V., 1990, 'Moving Object Recognition Using an Adaptive Background Memory,' duddl Time-varying Image Processing and Moving Object Recognition, Vol. 2, Elsevier Publishers B. V., Amsterdam, The Netherlands, pp. 297-307
  7. Kim, D. K., Kang, B. Ch. and Kim, S. B., 1998, 'Development of Counting and Trajectory Extraction Algorithms of Sperm Using Image Processing,' 13th KACC, pp. 881-884
  8. Leung, M. K. and Yang, Y. H., 'Human Body Motion Segmentation In A Complex Dcene,' Pattern Recognition, Vol. 20, pp. 55-64 https://doi.org/10.1016/0031-3203(87)90017-3
  9. Lewis, F. L., Applied Optimal Control & Estimation, Prentice-Hall Interna-tional, 1994
  10. Nagel, H. H., 'On the Estimation of Optical Flow;Relations Between Different Approaches and Some New Results,' Artificial Intelligence, Vol. 33, pp. 299-324 https://doi.org/10.1016/0004-3702(87)90041-5
  11. Park, H. S., Kim, H. S. and Kim S. B., 1998, 'The Tracking of 2-D Moving Object Using the Digital Image Processing,' Proceedings of the KSPSE Autumn Annual Meetings '98, pp. 175-180
  12. Samuel, B. and Robert, P., 1999, Design and Analysis of Modern Tracking Systems, Artech House
  13. Tompson, W. B., Barnard, S. T., 1981, 'Low-Level Estimation and Interpolation Visual motion,' IEEE computer, Vol. 14(8), pp. 20-28 https://doi.org/10.1109/C-M.1981.220559
  14. Wu, W. et al., 1996, 'Analysis of Sperm Motion by Trajectory Extraction from Image Sequence,' Journal of the Society of Instrument and Control Engineers, Vol. 32, pp. 597-603
  15. Wang, H. and Daley, S., 1996, 'Actuator Fault Diagnosis;An Adaptive Observer Based Technique,' IEEE Trans. on Automatic Control, Vol. 41, No. 7, pp. 1073-1078 https://doi.org/10.1109/9.508919