Journal of Biosystems Engineering

Korean Society for Agricultural Machinery (한국농업기계학회)
권호 표지
DOI QR코드

DOI QR Code

Detection of Precise Crop Locations under Vinyl Mulch using Non-integral Moving Average Applied to Thermal Distribution

  • Cho, Yongjin (Department of Bio-Mechatronic Engineering, Sungkyunkwan University) ;
  • Yun, Yeji (Department of Bio-Mechatronic Engineering, Sungkyunkwan University) ;
  • Lee, Kyou-Seung (Department of Bio-Mechatronic Engineering, Sungkyunkwan University) ;
  • Lee, Dong-Hoon (Department of Bio-systems Engineering, Chungbuk National University)
  • Received : 2017.04.28
  • Accepted : 2017.05.22
  • Published : 2017.06.01
Download PDF
⟨ Previous Next ⟩

Abstract

Purpose: Damage to pulse crops by wild birds is a serious problem. The damage is to such an extent that the rate of damage during the period between seeding and cotyledon stages reaches 54.6% on an average. In this study, a crop-position detection method was developed wherein infrared (IR) sensors were used to determine the cotyledon position under a vinyl mulch. Methods: IR sensors that helped measure the temperature were used to locate the cotyledons below the vinyl mulch. A single IR sensor module was installed at three locations of the crops (peanut, red lettuce, and crown daisy) in the cotyledon stage. The representative thermal response of a $16{\times}4$ pixel area was detected using this sensor in the case where the distance from the target was 25 cm. A spatial image was applied to the two-dimensional temperature distribution using a non-integral moving-average method. The collected data were first processed by taking the moving average via interpolation to determine the frame where the variance was the lowest for a resolution unit of 1.02 cm. Results: The temperature distribution was plotted corresponding to a distance of 10 cm between the crops. A clear leaf pattern of the crop was visually confirmed. However, the temperature distribution after the normalization was unclear. The image conversion and frequency-conversion graphs were obtained based on the moving average by averaging the points corresponding to a frequency of 40 Hz for 8 pixels. The most optimized resolutions at locations 1, 2, and 3 were found on 3.4, 4.1, and 5.6 Pixels, respectively. Conclusions: In this study, to solve the problem of damage caused by birds to crops in the cotyledon stage after seeding, the vinyl mulch is punched after seeding. The crops in the cotyledon stage could be accurately located using the proposed method. By conducting the experiments using the single IR sensor and a sliding mechanical device with the help of a non-integral interpolation method, the crops in the cotyledon stage could be precisely located.

Keywords

References

  1. Ceccardi T. L., R. L. Heath and I. P. Ting. 1995. Lowtemperature exotherm measurement using infrared thermography. Hortscience 30(1): 140-142. https://doi.org/10.21273/HORTSCI.30.1.140
  2. Guzman E., V. Baeten, J. A. F. Pierna and J. A. Garcia-Mesa. 2013. Infrared machine vision system for the automatic detection of olive fruit quality. Talanta. 116: 984-898.
  3. Jeon H. Y., H. Zhu, R. Derksen, E. Ozkan and C. Krause. 2011. Evaluation of ultrasonic sensor for variable-rate spray applications. Computers and Electronics in Agriculture 75: 213-221. https://doi.org/10.1016/j.compag.2010.11.007
  4. Jeong B. J. and S. W. Jang. 2009. Image processing using thermal infrared image. Journal of the Korea Academia-Industrial cooperation Society 10(7): 1503-1508. https://doi.org/10.5762/KAIS.2009.10.7.1503
  5. Lee K. S, Y. J. Cho and D. H. Lee. 2016. Detection method for bean cotyledon locations under vinyl mulch using multiple infrared sensors. Journal of biosystem engineering, 41(3): 263-272. https://doi.org/10.5307/JBE.2016.41.3.263
  6. 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).
  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. Viola, P. and M. Jones. 2001. Rapid object detection using a boosted cascade of simple features. In Computer Vision and Pattern Recognition, 2001. CVPR 2001. Proceedings of the 2001 IEEE Computer Society Conference on (Vol. 1, pp. I-I). IEEE.
  9. Yuan, F. 2008. A fast accumulative motion orientation model based on integral image for video smoke detection. Pattern Recognition Letters 29(7): 925-932. https://doi.org/10.1016/j.patrec.2008.01.013