ساخت و ارزیابی سامانه تشخیص تراکم توده زنبور درون کندو با استفاده از بینایی ماشین

نوع مقاله : مقاله پژوهشی

نویسندگان

دانشگاه رامین خوزستان

چکیده

هدف از این پژوهش ساخت یک کندو مجهز به سامانه اخذ و تحلیل تصاویر به صورت بی­سیم و بی­درنگ به منظور بررسی تراکم توده زنبور درون کندو و در صورت نیاز نابودسازی آفت­های احتمالی با تله­گذاری می‏باشد. در این مطالعه از دو روش جریان نوری و ماتریس تفاوت- تن خاکستری همسایگی به منظور بررسی وضعیت کندو و تعیین فعالیت زنبورها استفاده گردید. نتایج حاصل از بررسی‏ها نشان داد که مطابق تحلیل جریان نوری، میانگین در سطح احتمال 5 درصد توانایی تشخیص تراکم توده را دارد. مطابق با تحلیل بافت، ویژگی‏های شلوغی و پیچیدگی با وضعیت تراکم توده زنبورها درون کندو دارای ارتباط معنی­داری می­باشند (05/0p<). همچنین به منظور تشخیص فعالیت زنبورها، از طبقه­بند­کننده غیرخطی بیز استفاده گردید که ترکیب میانگین و پیچیدگی و میانگین و شلوغی به ترتیب با دقت کلی 67/98 و 95/92 درصد داده­ها را دسته­بندی نمودند. 

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Manufacturing and testing of a system to detect bee colony density inside the hive using machine vision

نویسندگان [English]

  • Saman Abdanan Mahdizadeh
  • Maryam Soltani Kazemi
دانشگاه رامین خوزستان
چکیده [English]

The aim of this research was to construct an equipped hive with the acquisition, communication and analysis systems to send images on-line, wirelessly. This system could be used to evaluate density of bee colonies and also work as bait box to eliminate bee pest, if necessary. In this study, two methods, optical flow and neighborhood gray-tone difference matrix, were used to determine hive condition and bee activities. According to the results of optical flow analysis, mean was able to detect bulk of existing bee inside the hive at the confidence level of 5%. According to analysis of the texture, the parameters of busyness and complexity have a significant relationship with the bee’s density inside the hive (p<0.05). Moreover, in order to organizing the data in groups the classification algorithms based on Bayesian theorem was developed and executed. Concord to classification results, combination of mean with complexity and mean with busyness could classify the data with the total accuracy 98.67 and 92.95, respectively

کلیدواژه‌ها [English]

  • honey bee
  • Wireless
  • Machin Vision
  • Optical flow
  • Neighborhood Gray-Tone Matrix (NGTDM)
Ahmadi, A. A. (1984). Diseases and parasites in southern Iran. Incidence of honey bee (A. millifera). Bee world, 65, 134-136.
Amadasun, M., & King, R. (1989). Textural features corresponding to textural properties. Systems, Man and Cybernetics, IEEE Transactions on, 19(5), 1264-1274.
Bellomo, N., Bianca, C. & Delitala, M. (2009). Complexity analysis and mathematical tools towards modelling of living systems. Physics of Life Reviews, 6, 144-175.
Bencsik, M., Bencsik, J., Baxter, M., Lucian, A., Romiue, J., & Millet, M. (2011). Identification of the honey bee swarming process by analysing the time course of hive vibrations. Computers and Electronics in Agriculture, 76(1), 44-50.
Bradbear, N. (1987). World distribution of major honey bee disease and pests. Bee world, 68: 15-35.
Bremond, F., Thonnat, M. & Zuniga, M. (2006). Video-understanding framework for automatic behavior recognition. Behavior Research Methods, 38, 416-426.
Buryett, M., Akratankul, P. & R.A., Morse. (1983). Tropilaelaps clareae a parasite of honey bees in south-east Asia. Bee world, 64, 25-28.
Cheng, J. R., Koh, E. G. I., Ahmed, S. & Rajapakse, J. C. (2009). Tracking of cell morphology and motion. Joint tracking of cell morphology and motion. Pattern Recognition in Bioinformatics Proceedings, 5780, 36e45.
Christodoulou, C. I., Pattichis, C. S., Pantziaris, M. & Nicolaides, A. (2003). Texture-based classification of atherosclerotic carotid plaques. Medical Imaging, IEEE Transactions on, 22(7), 902-912.       
Courty, N. & Corpetti, T. (2007). Crowd motion capture. Computer Animation and Virtual Worlds, 18, 361-370.
Dawkins, M. S., Cain, R., & Roberts, S. J. (2012). Optical flow, flock behaviour and chicken welfare. Animal Behaviour84(1), 219-223.
Ferrari, S., Silva, M., Guarino, M. & Berckmans, D. (2008). Monitoring of swarming sounds in bee hives for early detection of the swarming period. Computers and electronics in agriculture, 64 (1), 72-77.
Giles, A. B., Massom, R. A. & Warner, R. C. (2009). A method for sub-pixel scale feature-tracking using Radarset images applied to the Mertz Glacier, East Antarctica. Remote Sensing of Environment, 113, 1691-1699.
Gonzalez, R. C., Woods, R. E., & Eddins, S. L. (2004). Digital image processing using MATLAB. Pearson Education India.
Krell, R. (1996). Value-added products from beekeeping. F.A.O Bulletin No 124, Rome, Italy.
Lee, H.-J., Roberts, S. J., Drake, K. A. & Dawkins, M. S. (2011). Prediction of feather damage in laying hens using optical flow and Markov models. Journal of the Royal Society Journal Interface, 8, 489-499.
Ma, Y. Q. & Cisar, P. (2008). Activity representation in crowds. Structural, Syntactic, and Statistical Pattern Recognition, 5342, 107-116.
Mossadegh. M.S. & R. Bahreini. (1994). Acarapis mites of honey bee , Apis mellifera, in Iran . Exp. Appl. Acarolo. , 18 (8): 503 – 506.
Neves, D. P., Abdanan Mehdizadeh, S., Tscharke, M., Nääs, I. A. & Banhazi, T. M. (2015). Detection of flock movement and behaviour of broiler chickens at different feeders using image analysis. Information Processing in Agriculture, (accepted for publication).
Shi, L. Z., Nascimento, J. M., Chandsawangbhuwana, C., Botvinick, E. L. & Berns, M. W. 2008. An automatic system to study sperm motility and energetics. Biomedical Microdevices, 10, 573-583.
Sonka, M., Hlavac, V. & Boyle, R. (1999). Image Processing Analysis and Machine Vision. 2nd edn. London: PWS Publishing.
Trees, H. L. V. (2001). Detection, Estimation, and Modulation Theory, New York: Wiley.
Von Frisch, K. (1967). The Dance Language and Orientation of Bees. The Belknap Press of Harvard University Press, Cambridge, Mass.
Weissleder, R. & Pitter, M. J. (2008). Imaging in the era of molecular oncology. Nature, 452, 580- 589