Ecology and Resilient Infrastructure

Korean Society of Ecology and Infrastructure Engineering (응용생태공학회)
권호 표지
DOI QR코드

DOI QR Code

Application and Evaluation of the Attention U-Net Using UAV Imagery for Corn Cultivation Field Extraction

무인기 영상 기반 옥수수 재배필지 추출을 위한 Attention U-NET 적용 및 평가

  • Shin, Hyoung Sub (Corp. Environment Remotesensing Institute (ERI)) ;
  • Song, Seok Ho (Corp. Environment Remotesensing Institute (ERI)) ;
  • Lee, Dong Ho (Department of Agricultural and Rural Engineering, Chungbuk National University) ;
  • Park, Jong Hwa (Department of Agricultural and Rural Engineering, Chungbuk National University)
  • Received : 2021.12.01
  • Accepted : 2021.12.16
  • Published : 2021.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, crop cultivation filed was extracted by using Unmanned Aerial Vehicle (UAV) imagery and deep learning models to overcome the limitations of satellite imagery and to contribute to the technological development of understanding the status of crop cultivation field. The study area was set around Chungbuk Goesan-gun Gammul-myeon Yidam-li and orthogonal images of the area were acquired by using UAV images. In addition, study data for deep learning models was collected by using Farm Map that modified by fieldwork. The Attention U-Net was used as a deep learning model to extract feature of UAV in this study. After the model learning process, the performance evaluation of the model for corn cultivation extraction was performed using non-learning data. We present the model's performance using precision, recall, and F1-score; the metrics show 0.94, 0.96, and 0.92, respectively. This study proved that the method is an effective methodology of extracting corn cultivation field, also presented the potential applicability for other crops.

본 연구에서는 위성영상 촬영 한계를 극복하고 재배 필지 현황 파악 기술 발전에 기여하고자 무인기 영상 및 딥러닝 모형을 이용하여 옥수수 재배 필지 추출 방법을 제안하였다. 연구대상지역은 충북 괴산군 감물면 이담리 일대로 설정하고, 무인기 촬영을 통해 해당지역의 정사영상을 취득하였다. 모형에 필요한 학습자료는 현장조사 자료와 팜맵을 이용하여 구축하였다. 본 연구에 적용한 딥러닝 모형은 의미론적 분할 모형인 Attention U-Net을 이용하였다. 모형의 성능 평가는 학습과정을 거친 후 비학습 자료를 이용하여 옥수수 재배 필지 추출에 대해서 실시 하였다. 모형 성능평가 결과 정밀도는 0.94, 재현율은 0.96 및 F1-Score는 0.92로 나타났다. 본 연구에 적용한 Attention U-Net방법은 옥수수 재배 필지를 효과적으로 추출할 수 있는 방법임을 확인하였다. 따라서 본 연구 방법은 옥수수는 물론 다른 작물에 대한 재배 필지 구분에도 유용하게 활용될 수 있을 것으로 기대된다.

Keywords

Acknowledgement

본 연구는 농촌진흥청 공동연구사업 (과제번호: PJ014049022021)의 지원을 받았으며, 이에 감사드립니다.

References

  1. Chen, Z. and Ho, P.H. 2019. Global-connected network with generalized ReLU activation. Pattern Recognition 96, 106961. doi:10.1016/j.patcog.2019.07.006.
  2. Jeong, C.H. and Park, J.H. 2021. Analysis of Growth Characteristics Using Plant Height and NDVI of Four Waxy Corn Varieties Based on UAV Imagery. Korean Journal of Remote Sensing 37(4): 733-745. doi:10.7780/KJRS.2021.37.4.5
  3. Keras. The Python Deep Learning API. https://keras.io/. Accessed 12 August 2021.
  4. Kim, Y.S., Park, N.W., Hong, S.Y., Lee, K.D. and Yoo, H.Y. 2014. Early production of large-area crop classification map using time-series vegetation index an past crop cultivation patterns-A case study in Iowa State, USA. Korean Journal of Remote Sensing 30(4): 493-503. (in Korean) doi:10.7780/kjrs.2014.30.4.7
  5. Kussul, N., Lavreniuk, M., Skakun, S. and Shelestov, A. 2017. Deep learning classification of land cover and crop types using remote sensing data. IEEE Geoscience and Remote Sensing Letters 14(5): 778-782. doi:10.1109/LGRS.2017.2681128
  6. Lee, D.H., Shin, H.S. and Park, J.H. 2020. Developing a p-NDVI Map for Highland Kimchi Cabbage Using Spectral Information from UAVs and a Field Spectral Radiometer. Agronomy 10(11): 1798. doi:10.3390/agronomy10111798
  7. Lee, D.H, Kim H.J. and Park J.H. 2021. UAV, a Farm Map, and Machine Learning Technology Convergence Classification Method of a Corn Cultivation Area. Agronomy. 2021; 11(8): 1554. doi:10.3390/agronomy11081554
  8. Lee, S.H. and Lee, M.J. 2020. A Study on Deep Learning Optimization by Land Cover Classification Item Using Satellite Imagery. Korean Journal of Remote Sensing 36(6-2): 1591-1604. (in Korean) doi:10.7780/kjrs.2020.36.6.2.9
  9. Lottes, P., Khanna, R., Pfeifer, J., Siegwart, R. and Stachniss, C. 2017. UAV-based crop and weed classification for smart farming. IEEE International Conference on Robotics and Automation (ICRA). 3024-3031. doi:10.1109/ICRA.2017.7989347
  10. MAFRA. 2017. Ministry of Agriculture Food and Rural Affairs, https://agis.epis.or.kr/ASD/main/intro.do#. Accessed 26 June 2021.
  11. MAFRA. 2021. Ministry of Agriculture, Food and Rural Affairs. https://lib.mafra.go.kr/skyblueimage/5622.pdf. Accessed 12 November 2021.
  12. McNairn, H., Kross, A., Lapen, D., Caves, R. and Shang, J. 2014. Early season monitoring of corn and soybeans with Terra SAR-X and RADARSAT-2. Internati nal Journal of Applied Earth Observation and Geoinformation 28: 252-259. doi:10.1016/j.jag.2013.12.015
  13. Na, S.I., Park, C.W., So, K.H., Park, J.M. and Lee, K.D. 2017. Satellite Imagery based Winter Crop Classification Mapping using Hierarchica Classification. Korean Journal of Remote Sensing 33(5-2): 677-687. (in Korean) doi: 10.7780/kjrs.2017.33.5.2.7
  14. NICS. 2021. National Institute of Crop Science. https://nongupin.co.kr/news/articleView.html?idxno=92916. Accessed 8 June 2021.
  15. Otsu, N. 1979. A threshold selection method from gray-level histograms. IEEE Transactions on Systems 9(1): 62-66. doi: 10.1109/TSMC.1979.4310076
  16. Park, J.K. and Park, J.H. 2015. Crop classification using imagery of unmanned aerial vehicle. Journal of the Korean Society of Agricultural Engineers 57(6): 91-97. (in Korean) doi:10.5389/KSAE.2015.57.6.091
  17. Park, J.K. and Park, J.H. 2016. Applicability Evaluation of Agricultural Subsidies Inspection Using Unmanned Aerial Vehicle. Journal of the Korean Society of Agricultural Engineers 58(5): 29-37. (in Korean) doi:10.5389/KSAE.2016.58.5.029
  18. Python 3.7, 2018, https://python.org/. Accessed 2 July 2021.
  19. Ronneberger, O., Fischer, P. and Brox, T. 2015. U-Net : Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention(MICCAI) 9351: 234-241. arxiv: 1505.04597.pdf
  20. Sameen, M.I., Pradhan, B. and Ziz, O.S. 2018. Classification of very high resolution aerial photos using spectral-spatial convolutional neural networks. Journal of Sensors 2018: 1-12. doi:10.1155/2018/7195432
  21. Schlemper J., Oktay, O., Schaap, M., Heinrich, M., Kainz, B., Glocker, B. and Rueckert, D. 2019. Attention Gated Networks : Learning to Leverage Salient Regions in Medical Images. Medical Image Analysis 53: 197-207. doi:10.1016/j.media.2019.01.012
  22. Seong, S.K., Na, S.I. and Choi, J.W. 2020. Assessment of the FC-DenseNet for Crop Cultivation Area Extraction by Using RapidEye Satellite Imagery. Korean Journal of Remote Sensing 36(5-1): 823-833. (in Korean) doi:10.7780/kjrs.2020.36.5.1.14
  23. Tensorflow. An End-to-End Open Source Machine Learning Platform. https://tensorflow.org/. Accessed 12 August 2021.
  24. Tong, X., Sun, B., Wei, J., Zuo, Z. and Su, S. 2021. EAAU-Net: Enhanced Asymmetric Attention U-Net for Infrared Small Target Detection. Remote Sensing, 13(16): 3200. doi:10.3390/rs13163200
  25. Ulmas, P. and Liiv, I. 2016. Segmentation of satellite imagery using u-net models for land cover classification. IEEE Access 4: 1-11. arxiv:2003.02899.pdf
  26. Yang, M.D., Huang, K.S., Kuo, Y.H., Tsai, H.P. and Lin, L.M. 2017. Spatial and Spectral Hybrid Image Classification for Rice Lodging Assessment through UAV Imagery. Remote Sensing 9(6): 1-19. doi:10.3390/rs9060583
  27. Zhang, Z., Liu, Q. and Wang, Y. 2018. Road Extraction by Deep Residual U-Net. IEEE Geoscience and Remote Sensing Letters 15(5): 749-753. doi: 10.1109/LGRS.2018.2802944