Korean Journal of Remote Sensing (대한원격탐사학회지)

Korean Society of Remote Sensing (대한원격탐사학회)
권호 표지
DOI QR코드

DOI QR Code

Field Crop Classification Using Multi-Temporal High-Resolution Satellite Imagery: A Case Study on Garlic/Onion Field

고해상도 다중시기 위성영상을 이용한 밭작물 분류: 마늘/양파 재배지 사례연구

  • Yoo, Hee Young (Geoinformatic Engineering Research Institute, Inha University) ;
  • Lee, Kyung-Do (National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Na, Sang-Il (National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Park, Chan-Won (National Institute of Agricultural Sciences, Rural Development Administration) ;
  • Park, No-Wook (Department of Geoinformatic Engineering, Inha University)
  • 유희영 (인하대학교 공간정보공학연구소) ;
  • 이경도 (농촌진흥청 국립농업과학원) ;
  • 나상일 (농촌진흥청 국립농업과학원) ;
  • 박찬원 (농촌진흥청 국립농업과학원) ;
  • 박노욱 (인하대학교 공간정보공학과)
  • Received : 2017.07.14
  • Accepted : 2017.08.22
  • Published : 2017.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, a study on classification targeting a main production area of garlic and onion was carried out in order to figure out the applicability of multi-temporal high-resolution satellite imagery for field crop classification. After collecting satellite imagery in accordance with the growth cycle of garlic and onion, classifications using each sing date imagery and various combinations of multi-temporal dataset were conducted. In the case of single date imagery, high classification accuracy was obtained in December when the planting was completed and March when garlic and onion started to grow vigorously. Meanwhile, higher classification accuracy was obtained when using multi-temporal dataset rather than single date imagery. However, more images did not guarantee higher classification accuracy. Rather, the imagery at the planting season or right after planting reduced classification accuracy. The highest classification accuracy was obtained when using the combination of March, April and May data corresponding the growth season of garlic and onion. Therefore, it is recommended to secure imagery at main growth season in order to classify garlic and onion field using multi-temporal satellite imagery.

이 논문에서는 고해상도 다중시기 위성영상을 이용한 밭작물 재배지 분류 가능성을 확인하기 위해 마늘과 양파 주산지를 대상으로 분류를 수행하였다. 마늘과 양파의 생육주기에 맞춰 영상을 수집하고 단일시기와 다양한 다중시기 자료의 조합으로 분류를 시도하였다. 단일시기 자료의 경우 파종이 모두 끝난 시기인 12월과 작물이 활발히 자라기 시작하는 3월 영상을 이용하였을 때 높은 분류 정확도를 보였다. 한편, 단일시기 자료 보다는 다중시기 자료를 이용하였을 때 더 높은 분류 정확도를 보였는데 자료의 수가 많은 것이 무조건 높은 분류 정확도를 반영하지는 않았다. 오히려 파종 시기 또는 파종 직후의 영상은 분류 정확도를 떨어뜨리는 역할을 하였고 마늘과 양파의 성장기인 3, 4, 5월 영상을 동시에 이용하여 분류하였을 때 가장 높은 분류 정확도를 얻었다. 따라서, 다중시기 위성영상을 이용하여 마늘과 양파를 분류하기 위해서는 작물 주요 성장기의 영상 확보가 매우 중요하다는 것을 확인할 수 있었다.

Keywords

References

  1. Beyer, F., J.T. Jarmer, B. Siegmann, and P. Fischer, 2015. Improved crop classification using multitemporal RapidEye data, Proc. of Analysis of Multitemporal Remote Sensing Images 2015 8th International Workshop, Annecy, France, Jul. 22-24, pp. 1-4.
  2. Breiman, L., 2001. Random forests, Machine Learning, 45(1): 5-32. https://doi.org/10.1023/A:1010933404324
  3. Burges, C.J.C., 1998. A tutorial on support vector machines for pattern recognition, Data Mining and Knowledge Discovery, 2: 121-167. https://doi.org/10.1023/A:1009715923555
  4. Conrad, C., R.R. Colditz, S. Dech, D. Klein, and P.L. Vlek, 2011. Temporal segmentation of MODIS time series for improving crop classification in Central Asian irrigation systems, International Journal of Remote Sensing, 32(23): 8763-8778. https://doi.org/10.1080/01431161.2010.550647
  5. Dawbin, K.W. and J.C. Evans, 1988. Large area crop classification in New South Wales, Australia, using Landsat data, International Journal of Remote Sensing, 9(2): 295-301. https://doi.org/10.1080/01431168808954853
  6. Hong, S.-Y., J. Hur, J.-B. Ahn, J.-M. Lee, B.-K. Min, C.-K. Lee, Y. Kim, K.D. Lee, S.-H. Kim, G.Y Kim, and K.M. Shim, 2012. Estimating rice yield using MODIS NDVI and meteorological data in Korea, Korean Journal of Remote Sensing, 28(5): 209-520 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2012.28.5.4
  7. Howard, D.M. and B.K. Wylie, 2014. Annual crop type classification of the US Great Plains for 2000 to 2011, Photogrammetric Engineering and Remote Sensing, 80(6): 537-549. https://doi.org/10.14358/PERS.80.6.537-549
  8. Huang, C., L.S. Davis, and J.R.G. Townshend, 2002. An assessment of support vector machines for land cover classification, International Journal of Remote Sensing, 23(4): 725-749. https://doi.org/10.1080/01431160110040323
  9. Immitzer, M., C. Atzberger, and T. Koukal, 2012. Tree species classification with random forest using very high spatial resolution 8-band WorldView-2 satellite data, Remote Sensing, 4(9): 2661-2693. https://doi.org/10.3390/rs4092661
  10. Jeong, S.J., H.S. Yun, D.U. Kim, H.J. Kim, C.S. Ryu, and Y. Kwon, 2016. Development of crop image segmentation technique for monitoring the growth status of garlic (Allium sativum) in UAV remote sensing, Proc. of 2016 Korean Society for Agricultural Machinery, Cheonan, Nov. 2-3, vol. 21, p. 58 (in Korean).
  11. Kim, Y.S., K.D. Lee, S.I. Na, S.Y. Hong, N.W. Park, and H.Y. Yoo, 2016. MODIS data-based crop classification using selective hierarchical classification, Korean Journal of Remote Sensing, 32(3): 235-244 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2016.32.3.3
  12. Lee, K.D., Y.E. Lee, C.W. Park, and S.I. Na, 2016. A comparative study of image classification method to classify onion and garlic using unmanned aerial vehicle(UAV) imagery, Korean Journal of Soil Science and Fertilizer, 49(6): 743-750 (in Korean with English abstract). https://doi.org/10.7745/KJSSF.2016.49.6.743
  13. Mathur, A. and G.M. Foody, 2008. Crop classification by support vector machine with intelligently selected training data for an operational application, International Journal of Remote Sensing, 29(8): 2227-2240. https://doi.org/10.1080/01431160701395203
  14. Ministry of Agriculture, Food and Rural Affairs, 2016. Agriculture, Food and Rural Affairs Statistics Yearbook 2016, Director-General for Policy Planning Bureau, Sejong, Korea (in Korean).
  15. Na, S.I., C.W. Park, Y.K. Cheong, C.S. Kang, I.B. Choi, and K.D. Lee, 2016. Selection of optimal vegetation indices for estimation of barley & wheat growth based on remote sensing - An application of unmanned aerial vehicle and field investigation data -, Korean Journal of Remote Sensing, 32(5): 483-497 (in Korean with English abstract). https://doi.org/10.7780/kjrs.2016.32.5.7
  16. National Agricultural Products Quality Management Service, 2005. An Illustrated Crop Guide, Dongyang P&C, Anyang, Korea (in Korean).
  17. Pal, M., 2005. Random forest classifier for remote sensing classification, International Journal of Remote Sensing, 26(1): 217-222. https://doi.org/10.1080/01431160412331269698
  18. Park, J. and S. Jang, 2014. The research of building smart farm map for vitalizing agricultural remote sensing, Proc. of Korean Society of Remote Sensing Fall conference 2014, Jeju, Oct. 16-17, vol. 17, pp. 23-26 (in Korean).
  19. Park, J., J. Yun, and J. Park, 2015. Classification of garlic and onion using UAV imagery, Proc. of Korean Society of Remote Sensing Fall conference 2015, Gwangju, Oct. 15-16, vol. 18, pp. 152-155 (in Korean).
  20. Park, W.M., 2007. Encyclopedia for vegetable garden, Dylnyouk, Gyeonggi, Korea (in Korean).
  21. Shao, Y., R.S. Lunetta, J. Ediriwickrema, and J. Iiames, 2010. Mapping cropland and major crop types across the Great Lakes Basin using MODISNDVI data, Photogrammetric Engineering and Remote Sensing, 76(1): 73-84. https://doi.org/10.14358/PERS.76.1.73
  22. Yeom, J.H. and Y.I. Kim, 2014. Automatic extraction of the land readjustment paddy for high-level land cover classification, Journal of Korean Society of Surveying, Geodesy, Photogrammetry and Cartography, 32(5): 443-450 (in Korean with English abstract). https://doi.org/10.7848/ksgpc.2014.32.5.443
  23. Yoon, S.-H., J.-Y. Choi, S.-H. Yoo, and M.-W. Jang, 2007. An uncertainty analysis of topographical factors in paddy field classification using a timeseries MODIS, Journal of Korean Society of Agricultural Engineers, 49(5): 67-77 (in Korean with English abstract). https://doi.org/10.5389/KSAE.2007.49.5.067

Cited by

  1. Potential of Hybrid CNN-RF Model for Early Crop Mapping with Limited Input Data vol.13, pp.9, 2017, https://doi.org/10.3390/rs13091629
  2. U-Net 기반 딥러닝 모델을 이용한 다중시기 계절학적 토지피복 분류 정확도 분석 - 서울지역을 중심으로 - vol.37, pp.3, 2017, https://doi.org/10.7780/kjrs.2021.37.3.4