DOI QR코드

DOI QR Code

A Study on Orthogonal Image Detection Precision Improvement Using Data of Dead Pine Trees Extracted by Period Based on U-Net model

U-Net 모델에 기반한 기간별 추출 소나무 고사목 데이터를 이용한 정사영상 탐지 정밀도 향상 연구

  • Received : 2022.07.20
  • Accepted : 2022.08.30
  • Published : 2022.08.31

Abstract

Although the number of trees affected by pine wilt disease is decreasing, the affected area is expanding across the country. Recently, with the development of deep learning technology, it is being rapidly applied to the detection study of pine wilt nematodes and dead trees. The purpose of this study is to efficiently acquire deep learning training data and acquire accurate true values to further improve the detection ability of U-Net models through learning. To achieve this purpose, by using a filtering method applying a step-by-step deep learning algorithm the ambiguous analysis basis of the deep learning model is minimized, enabling efficient analysis and judgment. As a result of the analysis the U-Net model using the true values analyzed by period in the detection and performance improvement of dead pine trees of wilt nematode using the U-Net algorithm had a recall rate of -0.5%p than the U-Net model using the previously provided true values, precision was 7.6%p and F-1 score was 4.1%p. In the future, it is judged that there is a possibility to increase the precision of wilt detection by applying various filtering techniques, and it is judged that the drone surveillance method using drone orthographic images and artificial intelligence can be used in the pine wilt nematode disaster prevention project.

소나무 재선충 피해나무는 줄어들고 있으나, 피해 지역은 전국으로 확대되고 있다. 최근에 딥러닝 기술이 발전하면서 소나무재선충 고사목 탐지 연구에 적용이 빠르게 시도되고 있다. 본 연구의 목적은 딥러닝 학습데이터의 효과적인 취득과 정확한 참값을 확보하고, 학습을 통해 U-Net 모델의 탐지능력을 보다 향상시키기 위함이다. 이러한 목적달성을 위해 단계별 딥러닝 알고리즘을 적용한 필터링 방법을 이용하여 딥러닝 모델의 불명확한 분석 근거를 최소화하고, 효율적인 분석 및 판단을 할 수 있도록 하였다. 분석결과 U-Net알고리즘을 이용한 소나무재선충 고사목 탐지 및 성능향상에 있어 기간별로 분석한 참값을 이용한 U-Net 모델이 기존에 제공하였던 참값을 이용한 U-Net 모델보다 재현율(Recall)은 -0.5%p, 정밀도(Precision)은 7.6%p, F-1 score는 4.1%p로 분석되었다. 향후 다양한 필터링 기법을 적용하여 재선충 탐지 정밀도를 높일 수 있는 가능성이 있을 것으로 판단되며, 드론 정사영상과 인공지능을 이용한 드론 예찰방법이 소나무재선충 방제 사업에 활용 가능할 것으로 판단된다.

Keywords

References

  1. Choi, Y.R., Lee, J.S., and Yun, H.C. (2015), Extraction of forest resources using high density LiDAR data, Journal of the Korean Society of Survey Geodesy Photogrammetry, Vol. 33, No. 2, pp. 73-81. (in Korean with English abstract). https://doi.org/10.7848/ksgpc.2015.33.2.73
  2. Derczynski, L. (2016), Complementarity, F-score, and NLP evaluation, Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC'16), European Language Resources Association (ELRA), pp. 261-266.
  3. Jung, Y.J. (2015), Pine wood nematode, The Magazine of The Korean Society of Hazard Mitigation, Vol. 15, pp. 124-128.
  4. Kim, M.I., Lee, W.K., and Kwon, T.H. (2011), Early detecting damaged trees by pine wilt disease using DI(Detection Index) from portable near infrared camera, Journal of Korean Society of Forest Science, Vol. 100, No.3 , pp. 374~381. (in Korean with English abstract). https://doi.org/10.14578/jkfs.2011.100.3.8
  5. Kim, M.J., Bang, H.S., and Lee, J.W. (2017), Accredited use of unmanned aerial vehicle for forecasting pine wood nematode in boundary area: A case study of Sejong metropolitan autonomous city, Korean Society of Forest Science, Vol. 106, No. 1, pp. 100~109. (in Korean with English abstract) https://doi.org/10.14578/jkfs.2017.106.1.100
  6. Kim, S.H, (2022), A Study on the Improvement of Orthoimage Detection by the U-Net model : Focusing on the Case of Pine Wilt Disease, Ph.D. dissertation, Youngnam University, Gyeongsan, Korea, 91p.
  7. Korea Forest Service. (2016), National Forest Inventory Report, Korea Forest Service, Daejeon, Korea, pp. 1-192 (in Korean).
  8. Kotsiantis, S., Kanellopoulos, D. and Pintelas, P. (2006). "Handling imbalanced datasets: A review." GESTS International Transactions on Computer Science and Engineering, Vol. 30, No. 1, pp. 25-36.
  9. Lee, K.W. and Park, J.K. (2019), Economic evaluation of unmanned aerial vehicle for forest pest monitoring, Journal of the Korea Academia Industrial cooperation Society, Vol. 20, No. 1, pp. 440-446 (in Korean with English abstract). https://doi.org/10.5762/KAIS.2019.20.1.440
  10. Lee, N.K., Kim, J.Y., and Shim, J.H. (2021), Empirical study on analyzing training data for CNN-based product classification deep learning model, The Journal of Society for e-Business Studies, Vol. 26, No. 1, pp. 107-126. (in Korean with English abstract) https://doi.org/10.7838/jsebs.2021.26.1.107
  11. Lee, S.K. and Seo, S.T. (2016), First report of Armillaria root disease caused by Armillaria tabescens on carpinus tschonoskii in south Korea. Plant Disease. Vol. 100, No. 1, pp. 213.
  12. Lim, E.T. and Do, M.S. (2021), Pine wilt disease detection based on deep learning using an unmanned aerial vehicle. Journal of Civil and Environmental Engineering Research, Vol. 41, No. 3, pp. 317-325. (in Korean with English abstract). https://doi.org/10.12652/Ksce.2021.41.3.0317
  13. Olaf, R., Philipp, F., and Thomas B. (2015), U-Net : Convolutional networks for biomedical image segmentation, International Conference on Medical image computing and computer-assisted intervention, 9351, pp. 234~241.
  14. Zhang, R.R., You, J., Kim, B.J., Sun, J.N., and Lee, J.H. (2020), Searching the damaged pine trees from wilt disease based on deep learning, Korean Institute of Smart Media, Vol. 9, No. 3, pp. 46-51. (in Korean with English abstract). https://dx.doi.org/10.30693/SMJ.2020.9.3.46