Advertisement

Signal, Image and Video Processing

, Volume 7, Issue 1, pp 27–43 | Cite as

Evolutionary algorithm for data association and IMM-based target tracking in IR image sequences

  • Mukesh A. ZaveriEmail author
  • S. N. Merchant
  • Uday B. Desai
Original Paper

Abstract

Simultaneous tracking of multiple maneuvering and non-maneuvering targets in the presence of dense clutter and in the absence of any a priori information about target dynamics is a challenging problem. A successful solution to this problem is to assign an observation to track for state update known as data association. In this paper, we have investigated tracking algorithms based on interacting multiple model to track an arbitrary trajectory in the presence of dense clutter. The novelty of the proposed tracking algorithms is the use of genetic algorithm for data association, i.e., observation to track fusion. For data association, we examined two novel approaches: (i) first approach was based on nearest neighbor approach and (ii) second approach used all observations to update target state by calculating the assignment weights for each validated observation and for a given target. Munkres’ optimal data association, most widely used algorithm, is based on nearest neighbor approach. First approach provides an alternative to Munkres’ optimal data association method with much reduced computational complexity while second one overcomes the uncertainty about an observation’s source. Extensive simulation results demonstrate the effectiveness of the proposed approaches for real-time tracking in infrared image sequences.

Keywords

Evolutionary/Genetic algorithm Interacting multiple model Data association 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Chong, C.-Y., Garren, D., Grayson, T.P.: Ground target tracking—a historical perspective. In: Proc. IEEE Aerospace Conference, vol. 3, pp. 433–448, Mar 2000Google Scholar
  2. 2.
    Bar-shalom Y., Fortmann T.E.: Tracking and Data Association. Academic Press, Boston (1989)Google Scholar
  3. 3.
    Blackman S.S., Popoli R.: Design and Analysis of Modern Tracking Systems. Artech House, Norwood, MA (1999)zbMATHGoogle Scholar
  4. 4.
    Popp R.L., Pattipati K.R., Bar-Shalom Y.: m-Best s-d assignment algorithm with application to multitarget tracking. IEEE Trans. Aerosp. Electron. Syst. 37, 22–39 (2001)CrossRefGoogle Scholar
  5. 5.
    Roecker J.A.: A class of near optimal JPDA algorithms. IEEE Trans. Aerosp. Electron. Syst. 30, 504–510 (1994)CrossRefGoogle Scholar
  6. 6.
    Pan, Q., Zhang, H., Xiang, Y.: Combinatorial quick JPDA algorithm. In: Proc. the American Control Conference, pp. 2660–2661, Baltimore, June 1994Google Scholar
  7. 7.
    Gad, A., Majdi, F., Farooq, M.: A comparison of data association techniques for target tracking in clutter. In: Proc. 5th International Conference on Information Fusion, pp. 1126–1133, July 2002Google Scholar
  8. 8.
    Dezert J., Bar-Shalom Y.: Joint probabilistic data association for autonomous navigation. IEEE Trans. Aerosp. Electron. Syst. 29, 1275–1286 (1993)CrossRefGoogle Scholar
  9. 9.
    Willett, P., Ruan, Y., Streit, R.: The PMHT for maneuvering targets. In: Proc. SPIE Conference on Signal and Data Processing of Small Targets, vol. 3373, pp. 416–427, July 1998Google Scholar
  10. 10.
    Willett P., Ruan Y., Streit R.: PMHT: problems and some solutions. IEEE Trans. Aerosp. Electron. Syst. 38, 738–754 (2002)CrossRefGoogle Scholar
  11. 11.
    Watson, G.A., Blair, W.: IMM algorithm for tracking targets that maneuver through coordinated turns. In: Proc. SPIE Conference on Signal and Data Processing of Small Targets, vol. 1698, pp. 236–247, Aug 1992Google Scholar
  12. 12.
    Li X.R., Zhang Y.: Numerically robust implementation of multiple-model algorithms. IEEE Trans. Aerosp. Electron. Syst. 36, 266–277 (2000)CrossRefGoogle Scholar
  13. 13.
    Kirubarajan, T., Yeddanapudi, M., Bar-Shalom, Y., Pattipai, K.: Comparison of IMMPDA and IMM-assignment algorithms on real traffic surveillance data. In: Proc. SPIE Conference on Signal and Data Processing of Small Targets, vol. 2759, pp. 453–464, May 1996Google Scholar
  14. 14.
    Helmick, R.E., Watson, G.A.: IMM-IPDAF for track formation on maneuvering targets in cluttered environments. In: Proc. SPIE Conference on Signal and Data Processing of Small Targets, vol. 2235, pp. 460–471, July 1994Google Scholar
  15. 15.
    Jouan, A., Jarry, B., Michalska, H.: Tracking closely maneuvering targets in clutter with an IMM-JVC algorithm. In: Proceedings of Third International Conference on Information Fusion (FUSION 2000), vol. 1, pp. MOD2/10–MOD2/16, July 2000Google Scholar
  16. 16.
    Gavriloaia, G., Sperila, A., Stoica, A.: An ad-hoc method for avoiding tracks coalescence in pdaf for tracks fusion. In: Proceedings of 7th International Conference on Telecommunications in Modern Satellite, Cable and Broadcasting Services, vol. 2, pp. 579–582, Sept 2005Google Scholar
  17. 17.
    Hadzagic, M., Michalska, H., Jouan, A.: IMM-JVC and IMM-JPDA for closely maneuvering targets. In: Proceedings of Thirty-Fifth Asilomar Conference on Signals, Systems and Computers, vol. 2, pp. 1278–1282, Nov 2001Google Scholar
  18. 18.
    Blom, H.A., Bloem, E.A.: Combining IMM and JPDA for tracking multiple maneuvering targets in clutter. In: Proc. International Conference on Information Fusion, pp. 705–712, July 2002Google Scholar
  19. 19.
    Zaveri, M.A., Desai, U.B., Merchant, S.: PMHT based multiple point targets tracking using multiple models in infrared image sequence. In: Proc. IEEE Conference on Advanced Video and Signal Based Surveillance (AVSS) 2003, pp. 73–78, Miami, Florida, July 2003Google Scholar
  20. 20.
    Zaveri, M.A., Desai, U.B., Merchant, S.: Interacting multiple model based tracking of multiple point targets using expectation maximization algorithm in infrared image sequence. In: Proc. SPIE: Visual Communications and Image Processing (VCIP) 2003, vol. 5150, pp. 303–314, Lugano, Switzerland, July 2003Google Scholar
  21. 21.
    Li X.R., Jilkov V.P.: Survey of maneuvering target tracking. Part V: multiple-model methods. IEEE Trans. Aerosp. Electron. Syst. 41, 1255–1321 (2005)CrossRefGoogle Scholar
  22. 22.
    Goldberg D.E.: Genetic Algorithms in Search, Optimization, and Machine Learning. Addison-Wesley Publication, Reading (1989)zbMATHGoogle Scholar
  23. 23.
    Hillis, D.B.: Using a genetic algorithm for multi-hypothesis tracking. In: Proc. of Ninth IEEE International Conference on Tools with Artificial Intelligence, pp. 112–117, Nov 1997Google Scholar
  24. 24.
    Chen G., Hong L.: A genetic algorithm based multi-dimensional data association algorithm for multi-sensor-multi-target tracking. Mathl. Comput. Model. 26(4), 57–69 (1997)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Chan K.C.C., Lee V., Leung H.: Generating fuzzy rules for target tracking using a steady-state genetic algorithm. IEEE Trans. Evol. Comput. 1, 189–200 (1997)CrossRefGoogle Scholar
  26. 26.
    Lee B.J., Park J.B., Lee H.J., Joo Y.H.: Fuzzy-logic-based imm algorithm for tracking manoeuvring target. IEE Proc. Radar Sonar Navig. 152, 16–22 (2005)CrossRefGoogle Scholar
  27. 27.
    Goto, R., Sato, Y.: The motion analysis of a moving object in sea by analyzing doppler effects of sound with genetic algorithms. In: Proceedings of IEEE International Conference on Systems, Man, and Cybernetics, pp. 984–991, Taipei, Taiwan, Oct 2006Google Scholar
  28. 28.
    Jin, L., Yao, C., Huang, X.: An improved method on meteorological prediction modeling using genetic algorithm and artificial neural network. In: Procceedings of IEEE 6th World Congress on Intelligent Control and Automation, pp. 31–35, Dalian, China, June 2006Google Scholar
  29. 29.
    Fu, X.-W., Fang, K.-L., Li, X.: Self-adjusted tracker based on genetic neural-networks for tracking multi-target. In: Proceedings of IEEE Fourth International Conference on Machine Learning and Cybernetics, pp. 662–664, Guangzhou, Aug 2005Google Scholar
  30. 30.
    Turkmen I., Guney K., Karaboga D.: Genetic tracker with neural network for single and multiple target tracking. Elsevier J. Neurocomput. 69, 2309–2319 (2006)CrossRefGoogle Scholar
  31. 31.
    Carrier, J.-Y., Litva, J., Leung, H., Lo, T.: Genetic algorithm for multiple-target-tracking data association. In: Proc. SPIE, Acquisition, Tracking and Pointing X, vol. 2739, pp. 180–190, Apr 1996Google Scholar
  32. 32.
    Zaveri M.A., Merchant S.N., Desai U.B.: Robust neural-network based data association and multiple model-based tracking of multiple point targets. IEEE Trans. Syst. Man Cybern. C Appl. Rev. 37, 337–351 (2007)CrossRefGoogle Scholar
  33. 33.
    Zaveri, M.A., Merchant, S.N., Desai, U.B.: Genetic IMM_NN based tracking of multiple point targets in infrared image sequence. In: Proc. Second International Conference on Information Technology (ITPC), Asian Applied Computing Conference, AACC—2004, Kathmandu, Nepal, Oct 2004Google Scholar
  34. 34.
    Zaveri, M.A., Merchant, S.N., Desai, U.B.: Tracking multiple point targets using genetic interacting multiple model based algorithm. In: Proc. IEEE International Symposium on Circuits and Systems (ISCAS—2004), vol. 3, pp. III–917–20, Vancouver, Canada, May 2004Google Scholar
  35. 35.
    Zaveri, M.A., Merchant, S.N., Desai, U.B., Nanda, P.K.: Evolutionary IMM-JPDA based tacking of multiple point targets in infrared image sequence. In: Proc. National Conference on Recent trends in Power, Signal Processing and Control (APSC—2004), Rourkela, India, Nov 2004Google Scholar
  36. 36.
    Tang, K., Man, K., Kwong, S., He, Q.: Genetic algorithms and their applications. IEEE Signal Process Mag., pp. 22–37, Nov 1996Google Scholar
  37. 37.
    More, S.T., Pandit, A.A., Merchant, S., Desai, U.: Synthetic IR scene simulation of air-borne targets. In: Proc. 3rd Conference ICVGIP 2002, pp. 108–113, Ahmedabad, India, Dec 2002Google Scholar
  38. 38.
    Pandit, A., More, S., Merchant, S., Desai, U.B.: IR scene simulation, search and tracking system. tech. rep., SPANN Lab, Department of Electrical Engineering, Indian Institute of Technology, Bombay—400076, India, Jan 2002Google Scholar
  39. 39.
    More, S.: Synthetic IR scene simulation of air borne targets. M. tech. thesis, Indian Institute of Technology, Bombay, India, Jan 2003Google Scholar
  40. 40.
    Pandit, A.: Image rendering in IR scence simulation. m. tech. thesis, Indian Institute of Technology, Bombay, India, Jan 2003Google Scholar
  41. 41.
    Zaveri, M.A., Merchant, S., Desai, U.B.: Multiple single pixel dim target detection in infrared image sequence. In: Proc. IEEE International Symposium on Circuits and Systems, (ISCAS) 2003, pp. 380–383, Bangkok, May 2003Google Scholar
  42. 42.
    Zaveri M.A., Merchant S.N., Desai U.B.: Wavelet based detection and its application to tracking in ir sequence. IEEE Trans. Syst. Man Cybern. C Appl. Rev. 37, 1269–1286 (2007)CrossRefGoogle Scholar
  43. 43.
    Singer R.A.: Estimating optimal tracking filter performance for manned maneuvering targets. IEEE Trans. Aerosp. Electron. Syst. 6, 473–483 (1970)CrossRefGoogle Scholar
  44. 44.
    Bar-shamlom Y., Li X.-R., Kirubarajan T.: Estimation with Applications To Tracking and Navigation. Wiley, New York (2001)CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Limited 2011

Authors and Affiliations

  • Mukesh A. Zaveri
    • 1
    Email author
  • S. N. Merchant
    • 2
  • Uday B. Desai
    • 3
  1. 1.Computer Engineering DepartmentSVNITSuratIndia
  2. 2.SPANN Lab, Electrical Engineering DepartmentIIT-BombayMumbaiIndia
  3. 3.Indian Institute of TechnologyHyderabadIndia

Personalised recommendations