ارزیابی جامع الگوریتم‌های بهینه‌سازی ژنتیک استاندارد، ژنتیک بهبودیافته و ازدحام ذرات بهبود یافته در کشف ترکیب بهینه ترم‌های توابع کسری وابسته به زمین

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشگاه صنعتی خواجه نصیرالدین طوسی

2 استاد گروه فتوگرامتری و سنجش از دور، دانشکده مهندسی نقشه‌برداری، دانشگاه صنعتی خواجه نصیرالدین طوسی

3 پژوهشگر پسادکتری سنجش از دور، دانشکده مهندسی نقشه‌برداری، دانشگاه صنعتی خواجه نصیرالدین طوسی

4 پژوهشگر پسادکتری، دانشکده مهندسی و علوم کاربردی، دانشگاه مموریال نیوفوندلند، کانادا

چکیده

استفاده از توابع کسری، در غیاب اطلاعات افمریز مدار ماهواره و هندسه داخلی سنجنده، یکی از بهترین روش‌ها برای زمین‌مرجع‌سازی تصاویر ماهواره‌ای و استخراج اطلاعات مکانی از تصاویر ماهواره‌ای است. تعداد زیاد ترم‌ها و عدم تفسیرپذیری آنها، باعث‌شده تا تعدد نقاط کنترل مورد‌نیاز و ایجاد خطای پارامتر‌های اضافه، به‌عنوان مهم‌ترین ضعف‌های توابع کسری وابسته به زمین شناخته شوند. استفاده از الگوریتم‌های بهینه‌سازی، یکی از راهکار‌های مناسب رفع این ضعف‌ها است. به‌همین‌دلیل از الگوریتم‌های بهینه‌سازی مختلف، برای کشف ترکیب بهینه ترم‌های توابع کسری وابسته به زمین استفاده شده است. از آنجا که سازوکار هریک از این الگوریتم‌ها با یکدیگر متفاوت است، میزان کارایی و خصوصیات مختلف این الگوریتم‌ها در کشف ترکیب بهینه ترم‌های توابع کسری وابسته به زمین متفاوت است اما تفاوت‌های موجود به‌صورت جامع، مورد مقایسه و تحلیل قرار نگرفته است. در این مقاله، به‌منظور بررسی کامل و جامع توانایی‌های سه الگوریتم بهینه‌سازی ژنتیک، ژنتیک بهبودیافته و ازدحام ذرات بهبودیافته در کشف ترکیب بهینه ترم‌های توابع کسری از دیدگاه‌های مختلف از جمله دقت، سرعت، تعداد نقاط کنترل مورد نیاز و قابلیت اطمینان به نتایج بدست آمده، از 4 تصویر ماهواره‌ای متعلق به سنجنده‌های GeoEye-1، IKONOS-2، SPOT-3-1ª و SPOT-3-1B استفاده شده است. اختلاف دقت کمتر از 4/0 پیکسل در نتایج هر یک از الگوریتم‌های بهینه‌سازی، 10 تا 12 برابر‌بودن سرعت الگوریتم ژنتیک بهبودیافته نسبت به دو الگوریتم دیگر، به ترتیب برتری 25/45 و 27 درصدی درجه آزادی الگوریتم بهینه‌سازی ازدحام ذرات بهبودیافته نسبت به الگوریتم ژنتیک بهبودیافته و ژنتیک و پراکندگی نسبتا یکسان نتایج هر یک از الگوریتم‌ها در 10 بار اجرای برنامه، حاکی از آن است که دقت هر سه الگوریتم بهینه‌سازی نسبتا یکسان، سرعت الگوریتم ژنتیک بهبودیافته بیشتر، تعداد نقاط کنترل مورد نیاز الگوریتم ازدحام ذرات بهبودیافته کمتر از دو الگوریتم دیگر و قابلیت اطمینان به نتایج هر یک از الگوریتم‌های بهینه‌سازی به منظور کشف ترکیب بهینه ترم‌های توابع کسری وابسته به زمین، یکسان است.

کلیدواژه‌ها


عنوان مقاله [English]

Comprehensive assessment of standard genetic optimization algorithm, modified genetic optimization algorithm and modified particle swarm optimization algorithm for optimization of terrain-dependent rational function models

نویسندگان [English]

  • Behrooz Moradi 1
  • mohammad javad valadan zoej 2
  • mojtaba jannati 3
  • somayeh yavari 4
1 K.N.Toosi university
2 Faculty of Geomatics Engineering, K.N Tossi University of Technology
3 Faculty of Geomatics Engineering, K.N Tossi University of Technology
4 Faculty of Engineering and Applied Science, Memorial University of Newfoundland, Canada
چکیده [English]

In the absence of satellite ephemeris data and inner geometry of satellite’s sensor, utilization of Rational Function Models (RFMs) is one of the best approaches to georeferencing satellite images and extracting spatial information from them. However, since RFMs have high number of coefficients, then usually high number of control points is needed for their estimation. In the other hand, RFM terms are uninterpretable and all of them causes over-parametrization error which count as the most important weakness of the terrain-dependent RFMs. Utilization of optimization algorithms is one of the best approaches to eliminate these weaknesses. Therefore, various optimization algorithms have been used to discover the optimal composition of RFM’s terms. Since the mechanism of these algorithms is different, the performance and feature characteristics of these algorithms differ in the discovery of the optimal composition train-dependent RFM’s terms. But the existing differences not comprehensively analyzed. In this paper, in order to comprehensive assessment the abilities of Genetic Optimization Algorithm (GA), Genetic modified Algorithm (GM), and a modified Particle Swarm Optimization (PSO) in terms of accuracy, quickness, number of control points required, and reliability of results, are evaluated. These methods are evaluated using for different datasets including a GeoEye-1, an IKONOS-2, a SPOT-3-1A, and a SPOT-3-1B satellite images. In terms of accuracy achieved, difference between these methods was less than 0.4 pixel. In terms of speed of evaluation of parameters, GM was 10 to 12 time more quickly in comparison with two other algorithms. In terms of control points required, degree of freedom of modified PSO was 45.25 percent and 27 percent more than GM and GA respectively, and finally in terms of reliability, the dispersion of RMSE obtained in 10 runs of three algorithms are relatively same. These results indicated that accuracy and reliability of all three methods are almost the same, speed of GM is higher and modified PSO needs less control points to optimize terrain-dependent RFM

  1. Aguilar, M.A., Saldana, M.M. and Aguilar, F.J., 2013, Assessing Geometric Accuracy of the Orthorectification Process from Geoeye-1 and worldview-2 Panchromatic Images, International Journal of Applied Earth Observation and Geoinformation 21: 427–435.
  2. Elbeltagi, E., Hegazy, T. and Grierson, D., 2005, Comparison among five evolu-tionary-based optimization algo-rithms”, Advanced Engineering Info-rmation, 19 (2005): 43-53.
  3.  
  4. Fraser, C.S. and Hanley, H.B., 2003, Bias Compensation in Rational Functions for IKONOS Satellite Imagery, Photogrammetric Engineering & Remote Sensing 69 (1): 53–57.
  5. Holland, J.H., 1975, Adaptation in Natural and Artificial Systems, Ann Arbor: University of Michigan Press.
  6. Jannati, M. and Valadan Zoej, M.J., 2015, Introducing genetic modification concept to optimize rational function models (RFMs) for georeferencing of satellite imagery, GIScience & Remote Sensing, 52 (4): 510-525.
  7. Kennedy, J. and Eberhart, R.C., A discrete binary version of the particle swarm algorithm, Proceedings of IEEE International Conference on Syst., Man, Cybern., Comput. Cybern. Simul., Orlando, FL, 1997, vol. 5, pp. 4104–4108.
  8. Valadan Zoej, M.J. and Petrie, G., 1998, Mathematical modeling and accuracy testing of SPOT level 1B stereo pairs, Photogrammetric Record, (16) 91: 67-82.
  9. Valadan Zoej, M.J. and Sadeghian, S., 2003, Orbital parameter modeling accuracy testing of Ikonos Geo image,” Photogrammetric Journal of Finland, 18(2): 70-80.
  10. McGlone, C., 1996, Sensor Modeling in Image Registration, Digital Photo-grammetry: An Addendum (C. W. Greve, editor), American Society for Photogrammetry and Remote Sensing, Bethesda, Maryland, pp. 115–123.
  11. Russell C. Ebrahart, Yuhui shi., 1988, Com-parision between genetic algorithms and particle swarm optimization, 1988 Annual Conference on Evolutionary Orogramming, san Diego.
  12. Tao, C. V. and Y. Hu, 2001, A Compre-hensive Study of the Rational Function Model Photogrammetric Processing.” Photogramm Engineering Remote Sens 67 (12): 1347–1357.
  13. Toutin, Th., spring, 2003, Review Paper: Geometric Processing of Remote Sensing Images: Models, Algorithms, and Methods, International Journal of Remote Sensing, 25: 1893-1924.
  14. Unger, D.R., Kulhavy, D.L. and Hung, I.K., 2013, Validating the Geometric Accuracy of High Spatial Resolution Multispectral Satellite Data” GIScience and Remote Sensing 50 (3): 271–280.
  15. Valadan Zoej, M.J., Mokhtarzadeh, M., Mansourian, A., Ebadi, H. and Sadeghian., S., 2007, Rational Function Optimization Using Genetic Algo-rithms, International Journal of Applied Earth Observation and Geoinformation 9 (4): 403–413.
  16. Yavari, S., Valadan Zoej, M.J., Mohammad-zadeh, A. and Mokhtarzade, M., 2013, Particle Swarm Optimization of RFM for Georeferencing of Satellite Images, IEEE Geoscience and Remote Sensing Letters, 10 (1): 135-139.
  17. Yavari, S., Valadan Zoej, M.J., Sahebi, M.R. and Mokhtarzade, M., 2016, An automatic novel structural linear feature-based matching based on new concepts of mathematically generated lines and points, Photogrammetric Engineering and Remote Sensing, 82 (5): 17-28.
  18. Yavari, S., Valadan Zoej, M.J. and Sadeghian, S., 2008, Mathematical Modeling of Georectified Dynamic Space Images, International Journal of Geoinformatics, 4 (4)Aguilar, M.A., Saldana, M.M. and Aguilar, F.J., 2013, Assessing Geometric Accuracy of the Orthorectification Process from Geoeye-1 and worldview-2 Panchromatic Images, International Journal of Applied Earth Observation and Geoinformation 21: 427–435.
  19. Elbeltagi, E., Hegazy, T. and Grierson, D., 2005, Comparison among five evolu-tionary-based optimization algo-rithms”, Advanced Engineering Info-rmation, 19 (2005): 43-53.
  20.  
  21. Fraser, C.S. and Hanley, H.B., 2003, Bias Compensation in Rational Functions for IKONOS Satellite Imagery, Photogrammetric Engineering & Remote Sensing 69 (1): 53–57.
  22. Holland, J.H., 1975, Adaptation in Natural and Artificial Systems, Ann Arbor: University of Michigan Press.
  23. Jannati, M. and Valadan Zoej, M.J., 2015, Introducing genetic modification concept to optimize rational function models (RFMs) for georeferencing of satellite imagery, GIScience & Remote Sensing, 52 (4): 510-525.
  24. Kennedy, J. and Eberhart, R.C., A discrete binary version of the particle swarm algorithm, Proceedings of IEEE International Conference on Syst., Man, Cybern., Comput. Cybern. Simul., Orlando, FL, 1997, vol. 5, pp. 4104–4108.
  25. Valadan Zoej, M.J. and Petrie, G., 1998, Mathematical modeling and accuracy testing of SPOT level 1B stereo pairs, Photogrammetric Record, (16) 91: 67-82.
  26. Valadan Zoej, M.J. and Sadeghian, S., 2003, Orbital parameter modeling accuracy testing of Ikonos Geo image,” Photogrammetric Journal of Finland, 18(2): 70-80.
  27. McGlone, C., 1996, Sensor Modeling in Image Registration, Digital Photo-grammetry: An Addendum (C. W. Greve, editor), American Society for Photogrammetry and Remote Sensing, Bethesda, Maryland, pp. 115–123.
  28. Russell C. Ebrahart, Yuhui shi., 1988, Com-parision between genetic algorithms and particle swarm optimization, 1988 Annual Conference on Evolutionary Orogramming, san Diego.
  29. Tao, C. V. and Y. Hu, 2001, A Compre-hensive Study of the Rational Function Model Photogrammetric Processing.” Photogramm Engineering Remote Sens 67 (12): 1347–1357.
  30. Toutin, Th., spring, 2003, Review Paper: Geometric Processing of Remote Sensing Images: Models, Algorithms, and Methods, International Journal of Remote Sensing, 25: 1893-1924.
  31. Unger, D.R., Kulhavy, D.L. and Hung, I.K., 2013, Validating the Geometric Accuracy of High Spatial Resolution Multispectral Satellite Data” GIScience and Remote Sensing 50 (3): 271–280.
  32. Valadan Zoej, M.J., Mokhtarzadeh, M., Mansourian, A., Ebadi, H. and Sadeghian., S., 2007, Rational Function Optimization Using Genetic Algo-rithms, International Journal of Applied Earth Observation and Geoinformation 9 (4): 403–413.
  33. Yavari, S., Valadan Zoej, M.J., Mohammad-zadeh, A. and Mokhtarzade, M., 2013, Particle Swarm Optimization of RFM for Georeferencing of Satellite Images, IEEE Geoscience and Remote Sensing Letters, 10 (1): 135-139.
  34. Yavari, S., Valadan Zoej, M.J., Sahebi, M.R. and Mokhtarzade, M., 2016, An automatic novel structural linear feature-based matching based on new concepts of mathematically generated lines and points, Photogrammetric Engineering and Remote Sensing, 82 (5): 17-28.
  35. Yavari, S., Valadan Zoej, M.J. and Sadeghian, S., 2008, Mathematical Modeling of Georectified Dynamic Space Images, International Journal of Geoinformatics, 4 (4): 47-55.
  36. Yavari, S., Valadan Zoej, M.J., Mohammad-zadeh, A. and Mokhtarzade, M., 2012, Comparison of Particle Swarm Optimization and Genetic Algorithm in Rational Function Model Otimi-zation, International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXII ISPRS Congress, Melbourne, Australia.
  37. Fraser, C. S., and H. B. Hanley. 2003. “Bias Compensation in Rational Functions for IKONOS
  38. Satellite Imagery.” Photogrammetric Engineering & Remote Sensing 69 (1): 53–57.
  39. Holland, J. H. 1975. Adaptation in Natural and Artificial Systems. Ann Arbor: University of
  40. Michigan Press.
  41. Jannati, M., and Valadan Zoej, M.J., 2015. Introducing genetic modification concept to optimize rational function models (RFMs) for georeferencing of satellite imagery, GIScience & Remote Sensing, 52 (4): 510-525.
  42. J. Kennedy and R. C. Eberhart, “A discrete binary version of the particle swarm algorithm,” Proceedings of IEEE International Conference on Syst., Man, Cybern., Comput. Cybern. Simul., Orlando, FL, 1997, vol. 5, pp. 4104–4108.
  43. M. J. Valadan Zoej and G. Petrie, 1998. “Mathematical modeling and accuracy testing of SPOT level 1B stereo pairs,” Photogrammetric Record, (16) 91: 67-82.
  44. M. J. Valadan Zoej and S. Sadeghian, 2003. “Orbital parameter modeling accuracy testing of Ikonos Geo image,” Photogrammetric Journal of Finland, 18(2): 70-80.
  45. McGlone, C. 1996. “Sensor Modeling in Image Registration.” Digital Photogrammetry: An Addendum (C. W. Greve, editor), American Society for Photogrammetry and Remote Sensing, Bethesda, Maryland, pp. 115–123.
  46. Russell C. Ebrahart, Yuhui shi., 1988. “Comparision between genetic algorithms and particle swarm optimization ”, 1988 Annual Conference on Evolutionary Orogramming, san Diego.
  47. Tao, C. V., and Y. Hu. 2001. “A Comprehensive Study of the Rational Function Model
  48. Photogrammetric Processing.” Photogramm Engineering Remote Sens 67 (12): 1347–1357.
  49. Toutin, Th., spring 2003, “Review Paper: Geometric Processing of Remote Sensing Images: Models, Algorithms, and Methods.” International Journal of Remote Sensing, 25: 1893-1924.
  50. Unger, D. R., D. L. Kulhavy, and I. K. Hung. 2013. “Validating the Geometric Accuracy of High
  51. Spatial Resolution Multispectral Satellite Data.” GIScience and Remote Sensing 50 (3):
  52. –280.
  53. Valadan Zoej, M. J., M. Mokhtarzadeh, A. Mansourian, H. Ebadi, and S. Sadeghian. 2007.
  54. “Rational Function Optimization Using Genetic Algorithms.” International Journal of Applied
  55. Earth Observation and Geoinformation 9 (4): 403–413.
  56. Yavari, S., Valadan Zoej, M.J., Mohammadzadeh, A., and Mokhtarzade, M., 2013. “Particle Swarm Optimization of RFM for Georeferencing of Satellite Images”, IEEE Geoscience and Remote Sensing Letters, 10 (1): 135-139.
  57. Yavari, S., Valadan Zoej, M.J., Sahebi, M.R., and Mokhtarzade, M., 2016. “An automatic novel structural linear feature-based matching based on new concepts of mathematically generated lines and points”, Photogrammetric Engineering and Remote Sensing, 82 (5): 17-28.
  58. Yavari, S., Valadan Zoej, M.J., and Sadeghian, S., 2008. “Mathematical Modeling of Georectified Dynamic Space Images”, International Journal of Geoinformatics, 4 (4): 47-55.
  59. Yavari, S., Valadan Zoej, M. J., Mohammadzadeh, A., and Mokhtarzade, M., 2012. “Comparison of Particle Swarm Optimization and Genetic Algorithm in Rational Function Model Otimization,” International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XXII ISPRS Congress, Melbourne, Australia.