KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

The Application Methods of FarmMap Reading in Agricultural Land Using Deep Learning

딥러닝을 이용한 농경지 팜맵 판독 적용 방안

  • Received : 2022.05.11
  • Accepted : 2022.09.18
  • Published : 2023.02.28
Download PDF
⟨ Previous Next ⟩

Abstract

The Ministry of Agriculture, Food and Rural Affairs established the FarmMap, an digital map of agricultural land. In this study, using deep learning, we suggest the application of farm map reading to farmland such as paddy fields, fields, ginseng, fruit trees, facilities, and uncultivated land. The farm map is used as spatial information for planting status and drone operation by digitizing agricultural land in the real world using aerial and satellite images. A reading manual has been prepared and updated every year by demarcating the boundaries of agricultural land and reading the attributes. Human reading of agricultural land differs depending on reading ability and experience, and reading errors are difficult to verify in reality because of budget limitations. The farmmap has location information and class information of the corresponding object in the image of 5 types of farmland properties, so the suitable AI technique was tested with ResNet50, an instance segmentation model. The results of attribute reading of agricultural land using deep learning and attribute reading by humans were compared. If technology is developed by focusing on attribute reading that shows different results in the future, it is expected that it will play a big role in reducing attribute errors and improving the accuracy of digital map of agricultural land.

본 논문은 농림축산식품부에서 구축한 농경지 전자지도인 팜맵을 딥러닝을 이용하여 농경지 속성정보인 논, 밭, 인삼, 과수, 시설, 비경지의 속성 정보를 판독하는 방안을 제안한다. 팜맵은 항공 및 위성 영상을 이용하여 현실 세계의 농경지를 디지털화하여 작물 생산 현황 파악과 드론 운영에 공간정보로 활용되고 있으며, 판독 매뉴얼을 작성하여 매년 사람을 통해 농경지의 경계를 구획하고 속성을 판독하여 갱신한다. 사람을 통한 농경지 속성판독은 사람의 판독 역량과 경험에 따라 차이를 보이며, 판독 오류는 예산과 공간적 시간적 한계로 직접 현장에 갈 수 없어 현실적으로 검증이 쉽지 않다. 팜맵은 5가지의 농경지 속성의 이미지에 해당 객체의 위치 정보와 클래스 정보를 가지고 있어 적합한 AI의 기법은 인스턴스 분할 모델인 ResNet50으로 실험을 진행하였으며, 딥러닝을 이용한 농경지 속성판독과 사람에 의한 속성판독 결과를 비교하여, 향후 다른 결과를 나타내는 속성판독에 집중하여 기술을 개발한다면 속성 오류를 줄이고 농경지 전자지도의 정확성 향상에 큰 역할을 할 것으로 기대된다.

Keywords

References

  1. Statistics Korea 2010, Agricultural area Survey, 2020.
  2. Ministry of Agriculture, Food and Rural Affairs, Press Release, "Anyone can use the electronic map farm map of agricultural land," 2021.
  3. K. J. Son, "Study on applying spatial information to agriculture based on the farm map," Journal of the Korea Society of Informaion Technology Policy & Managment, '21-13, Vol.13, No.1, pp.2229-2235, 2021.
  4. Statistics Korea, "2020 Total Cultivated Land Survey using Farm Map data," 2020.
  5. Ministry of Agriculture, Food and Rural Affairs, "Establishment of Smart Farm Map Construction Plan," 2017.
  6. H. K. Choi, B. K. Lee, S. R. Son, and H. H. Ahn, "CCMS (Crop Classification Management System) detecting growth environment changes to improve crop production rate," The Journal of Korea Institute of Information, Electronics, and Communication Technology, Vol,13, No.2, pp.145-152, 2020. https://doi.org/10.17661/JKIIECT.2020.13.2.145
  7. J. M. Koo, "Introduction of detector analysis and large data sets for object detection in satellite images," Korean Society for Remote Sensing Fall Conference, 2020.
  8. K. Kim, S. Hong, B. Choi, and E. Kim, "Probabilistic ship detection and classification using deep learning." Applied Sciences, Vol.8, No.6, pp.936. 2018.
  9. Institute for Land, Infrastructure and Transport Science and Technology Promotion, "Final report on the development of deep learning-based CCTV image retention system for initial response to accidents in tunnels," 2019.
  10. A. Bewley, Z. Ge, L. Ott, F. Ramos, and B. Upcroft, "Simple online and realtime tracking," In: Proceedings of the Image Processing (ICIP) IEEE International Conference, pp.3464-3468, 2016.
  11. S. H. Lee, "Land cover classification using sematic image segmentation with deep learning," Korean Journal of Remote Sensing, Vol.35, No.2, pp.279-288, 2019.
  12. H. Su, S. Wei, S. Liu, J. Liang, C. Wang, J. Shi, and X. Zhang, "HQ-ISNet: High-quality instance segmentation for remote sensing imagery," Remote Sens, Vol.12, No.6, pp.989, 2020.
  13. A. R. Song and Y. I. Kim, "Deep learning-based hyperspectral image classification with application to environmental geographic information systems," Korean Journal of Remote Sensing, Vol.33, No.6, pp.1061-1073, 2017.
  14. R. Qin, X. Huang, and A, Gruen, "Object-Based 3D building change detection on multitemporal stereo images," IEEE, Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol.8, No.5, pp.2125-2137, 2017.
  15. C. Qi, H. Su, K. Mo, and L. J. Guibas, "Pointnet: Deep learning on point sets for 3d classification and segmentation," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.652-660, 2017.
  16. H. D. Seo and Y. M. Kim, "Object classification and change detection in point clouds using deep learning," Journal of Cadastre & Land InformatiX, Vol.50, No.2, pp.37-51, 2020.
  17. K. H. Seo, C. H. Oh, D. W. Kim, M. Y. Lee, Y. J. Yang, and Y. K. Lee, "Monitoring method of land use and land cover change using deep learning algorithm," Sejong: KRIHS, 2018,
  18. K. He, X. Zhang, S. Ren, and J. Sun, "Deep residual learning for image recognition," In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp.770-778. 2016.
  19. C. N. Lim, Y. S. Park, and J. W. Lee, "Deep learning model validation method based on image data feature coverage," KIPS Transactions on Software and Data Engineering, Vol.10, No.9, pp.375-384, 2021. https://doi.org/10.3745/KTSDE.2021.10.9.375