DOI QR코드

DOI QR Code

Detection Method for Bean Cotyledon Locations under Vinyl Mulch Using Multiple Infrared Sensors

  • Lee, Kyou-Seung (Dept. of Bio-Mechatronic Engineering, Sungkyunkwan University) ;
  • Cho, Yong-jin (Dept. of Bio-Mechatronic Engineering, Sungkyunkwan University) ;
  • Lee, Dong-Hoon (Dept. of Bio-systems Engineering, Chungbuk National University)
  • Received : 2016.08.22
  • Accepted : 2016.08.27
  • Published : 2016.09.01

Abstract

Purpose: Pulse crop damage due to wild birds is a serious problem, to the extent that the rate of damage during the period of time between seeding and the stage of cotyledon reaches 45.4% on average. This study investigated a method of fundamentally blocking birds from eating crops by conducting vinyl mulching after seeding and identifying the growing locations for beans to perform punching. Methods: Infrared (IR) sensors that could measure the temperature without contact were used to recognize the locations of soybean cotyledons below vinyl mulch. To expand the measurable range, 10 IR sensors were arranged in a linear array. A sliding mechanical device was used to reconstruct the two-dimensional spatial variance information of targets. Spatial interpolation was applied to the two-dimensional temperature distribution information measured in real time to improve the resolution of the bean coleoptile locations. The temperature distributions above the vinyl mulch for five species of soybeans over a period of six days from the appearance of the cotyledon stage were analyzed. Results: During the experimental period, cases where bean cotyledons did and did not come into contact with the bottom of the vinyl mulch were both observed, and depended on the degree of growth of the bean cotyledons. Although the locations of bean cotyledons could be estimated through temperature distribution analyses in cases where they came into contact with the bottom of the vinyl mulch, this estimation showed somewhat large errors according to the time that had passed after the cotyledon stage. The detection results were similar for similar types of crops. Thus, this method could be applied to crops with similar growth patterns. According to the results of 360 experiments that were conducted (five species of bean ${\times}$ six days ${\times}$ four speed levels ${\times}$ three repetitions), the location detection performance had an accuracy of 36.9%, and the range of location errors was 0-4.9 cm (RMSE = 3.1 cm). During a period of 3-5 days after the cotyledon stage, the location detection performance had an accuracy of 59% (RMSE = 3.9 cm). Conclusions: In the present study, to fundamentally solve the problem of damage to beans from birds in the early stage after seeding, a working method was proposed in which punching is carried out after seeding, thereby breaking away from the existing method in which seeding is carried out after punching. Methods for the accurate detection of soybean growing locations were studied to allow punching to promote the continuous growth of soybeans that had reached the cotyledon stage. Through experiments using multiple IR sensors and a sliding mechanical device, it was found that the locations of the crop could be partially identified 3-5 days after reaching the cotyledon stage regardless of the kind of pulse crop. It can be concluded that additional studies of robust detection methods considering environmental factors and factors for crop growth are necessary.

Keywords

References

  1. Blazquez, C. H. 1989. Densitometry, image analysis, and interpretation of aerial color infrared photographs of citrus. Hortscience 24(4):691-693.
  2. Camargo, A. and J. S. Smith. 2009. An image-processing based algorithm to automatically identify plant disease visual symptoms. Biosystems engineering 102:9-21. https://doi.org/10.1016/j.biosystemseng.2008.09.030
  3. Ceccardi, T. L, R. L. Heath and I. P. Ting. 1995. Low-temperature exotherm measurement using infrared thermography. Hortscience 30(1):140-142.
  4. Feyaerts, F. and L. V. Gool. 2001. Multi-spectral vision system for weed detection. Pattern Recognition Letter 22:667-674. https://doi.org/10.1016/S0167-8655(01)00006-X
  5. Hashimoto, Y., T. Ino, P. J. Kramer, A. W. Naylor and B. R. Strain. 1984. Dynamic analysis of water stress of sunflower leaves by means of a thermal image processing system. Plant Physiololgy 74:266-269.
  6. Inoue, Y. 1986. Remote-monitoring of function and state of crop community. Japenese Journal of Crop Science 55(2): 261-268. https://doi.org/10.1626/jcs.55.261
  7. Kim, G. Y., K. H. Ryu and H. Y. Chae. 1999. Measurement of stress related crop temperature variations. Journal of Bio-Environment Control 8(2):233-236 (In Korean, with English abstract).
  8. Lim, S. K. 2009. Seedling emergence rates and the degrees of damage after soybean seeding by time of eating damage by pigeons and pheasants. National Institute of Crop Science (In Korean).
  9. Philipp, I. and T. Rath. 2002. Improving plant discrimination in image processing by use of different colour space transformations. Computers and Electronics in Agriculture 35:1-15. https://doi.org/10.1016/S0168-1699(02)00050-9
  10. Sogaard, H. T. 2005. Weed classification by active shape models. Biosystems Engineering 91(3):271-281. https://doi.org/10.1016/j.biosystemseng.2005.04.011
  11. Tumbo, S. D., M. Salyani, J. D. Whitney, T. A. Wheaton and W. M. Miller. 2002. Investigation of laster and ultrasonic ranging sensors for measurements of citrus canopy volume. Applied Engineering in Agriculture. 18(3):367-372.