Journal of the Korean Association of Geographic Information Studies (한국지리정보학회지)

The Korean Association of Geographic Information Studies (한국지리정보학회)
권호 표지
DOI QR코드

DOI QR Code

Classification of Crop Cultivation Areas Using Active Learning and Temporal Contextual Information

능동 학습과 시간 문맥 정보를 이용한 작물 재배지역 분류

  • KIM, Ye-Seul (Department of Geoinformatic Engineering, Inha University) ;
  • YOO, Hee-Young (Geoinformatic Engineering Research Institute, Inha University) ;
  • PARK, No-Wook (Department of Geoinformatic Engineering, Inha University) ;
  • LEE, Kyung-Do (Climate Change & Agroecology Division, National Academy of Agricultural Science, Rural Development Administration)
  • 김예슬 (인하대학교 공간정보공학과) ;
  • 유희영 (인하대학교 공간정보공학연구소) ;
  • 박노욱 (인하대학교 공간정보공학과) ;
  • 이경도 (농촌진흥청 국립농업과학원 기후변화생태과)
  • Received : 2015.06.13
  • Accepted : 2015.08.29
  • Published : 2015.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a classification method based on the combination of active learning with temporal contextual information extracted from past land-cover maps for the classification of crop cultivation areas. Iterative classification based on active learning is designed to extract reliable training data and cultivation rules from past land-cover maps are quantified as temporal contextual information to be used for not only assignment of training data but also relaxation of spectral ambiguity. To evaluate the applicability of the classification method proposed in this paper, a case study with MODIS time-series vegetation index data sets and past cropland data layers(CDLs) is carried out for the classification of corn and soybean in Illinois state, USA. Iterative classification based on active learning could reduce misclassification both between corn and soybean and between other crops and non crops. The combination of temporal contextual information also reduced the over-estimation results in major crops and led to the best classification accuracy. Thus, these case study results confirm that the proposed classification method can be effectively applied for crop cultivation areas where it is not easy to collect the sufficient number of reliable training data.

이 논문에서는 작물 재배지의 분류를 목적으로 능동 학습과 과거 토지 피복도 기반의 시간 문맥 정보를 결합하는 분류 방법론을 제안하였다. 신뢰성 높은 훈련 자료의 추출을 위하여 능동 학습 기반 반복 분류를 적용하였으며, 과거 토지 피복도의 작물 재배 규칙을 시간 문맥 정보로 정량화 하여 능동 학습 기법의 적용시 훈련 자료의 할당과 작물 간 분광학적 혼재 효과 완화에 이용하였다. 제안 분류 방법론의 적용 가능성을 평가하기 위해 미국 Illinois 주의 옥수수와 콩 재배지역의 구분을 목적으로 MODIS 시계열 식생지수 자료와 과거 cropland data layer(CDL) 자료를 이용한 사례연구를 수행하였다. 사례연구 결과, 초기 감독 분류 결과에서 나타났던 옥수수와 콩의 오분류와 기타 작물과 비작물의 오분류 양상이 능동 학습 기반 반복 분류를 통해 완화되었다. 그리고 CDL 자료로부터 추출한 시간 문맥 정보를 추가적으로 결합함으로써 주요 작물에서 나타나는 과추정 양상이 완화되어 가장 우수한 분류 정확도를 나타내었다. 따라서 제안 기법이 양질의 훈련 자료의 확보가 쉽지 않은 작물 재배지의 분류에 유용하게 적용될 수 있음을 확인하였다.

Keywords

References

  1. Boryan, C., Z. Yang, R. Mueller and M. Craig. 2011. Monitoring US agriculture: the US Department of Agriculture, National Agricultural Statistics Service, cropland data layer program. Geocarto International 26(5):341-358. https://doi.org/10.1080/10106049.2011.562309
  2. Chang, J., M.C. Hansen, K. Pittman, M. Carroll and C. DiMiceli. 2007. Corn and soybean mapping in the United States using MODIS time-series data sets. Agronomy Journal 99(6):1654-1664. https://doi.org/10.2134/agronj2007.0170
  3. Crawford, M.M., D. Tuia and H.L. Yang. 2013. Active learning: any value for classification of remotely sensed data? Proceedings of the IEEE 101(3):593-608. https://doi.org/10.1109/JPROC.2012.2231951
  4. Cristianini, N. and J.S. Taylor. 2000. An Introduction to Support Vector Machines and Other Kernel-based Learning Methods. Cambridge University Press, Cambridge, UK, 204pp.
  5. Demir, B.C., Persello and L. Bruzzone. 2011. Batch mode active learning methods for the interactive classification of remote sensing images. IEEE Transactions on Geoscience and Remote Sensing 49(3):1014-1032. https://doi.org/10.1109/TGRS.2010.2072929
  6. Dopido, I., J. Li, P.R. Marpu, A. Plaza, J.M.B. Dias and J.A. Benediktsson. 2013. Semisupervised self-learning for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing 51(7):4032-4044. https://doi.org/10.1109/TGRS.2012.2228275
  7. Foody, G.M., A. Mathur, C. Sanchez-Hernandez and D.S. Boyd. 2006. Training set size requirements for the classification of a specific class. Remote Sensing of Environment 104(1):1-14. https://doi.org/10.1016/j.rse.2006.03.004
  8. Kim, H.O. and J.M. Yeom. 2012. A study on object-based image analysis methods for land cover classification in agricultural areas. Journal of the Korean Association of Geographic Information Studies 15(4):26-41 (김현옥, 염종민.2012. 농촌지역 토지피복분류를 위한 객체기반 영상분석기법 연구. 한국지리정보학회지 15(4):26-41). https://doi.org/10.11108/kagis.2012.15.4.026
  9. Kim, M.H., C.K. Lee, H.K. Park, J.E. Lee, B.C. Koo and J.C. Shin. 2008. A study on rice growth and yield monitoring using medium resolution Landsat imagery. Korean Journal of Crop Science 53(4):388-393 (김민호, 이충근,박호기, 이재은, 구본철, 신진철. 2008.Landsat 위성영상을 이용한 벼 생육 및 수량 모니터링. 한국작물학회지 53(4):388-393).
  10. Kim, Y., N.W. Park, S.Y. Hong, K.D. Lee and H.Y. Yoo. 2014. Early production of large-area crop classification map using time-series vegetation index and past crop cultivation patterns - a case study in Iowa State, USA-. Korean Journal of Remote Sensing 30(4):493-503 (김예슬,박노욱, 홍석영, 이경도, 유희영. 2014. 시계열 식생지수와 과거 작물 재배 패턴을 이용한 대규모 작물 분류도의 조기 제작 -미국아이오와 주 사례연구-. 대한원격탐사학회지 30(4):493-503). https://doi.org/10.7780/kjrs.2014.30.4.7
  11. Lee, H.R., J.H. Baek and J.H. Baek. 2008. Prototype of crops information system based on ontology and WebGIS. Journal of the Korean Association of Geographic Information Studies 11(3): 43-51 (이홍로, 백정현, 백정호. 2008.Ontology와 WebGIS 기반 프로토타입 농작물 작황 정보시스템 구축. 한국지리정보학회지 11(3):43-51).
  12. Lee, S.W. and N.W. Park. 2011. Application of bayesian probability rule to the combination of spectral and temporal contextual information in landcover classification. Korean Journal of Remote Sensing 27(4):445-455 (이상원,박노욱. 2011. 토지 피복 분류에서 분광 영상정보와 시간 문맥 정보의 결합을 위한 베이지안 확률 규칙의 적용. 대한원격탐사학회지 27(4):445-455). https://doi.org/10.7780/kjrs.2011.27.4.445
  13. Lillesand, T., R.W. Kiefer and J. Chipman. 2007. Remote Sensing and Image Interpretation. Wiley, Hoboken, NJ, USA, 804pp.
  14. Lunetta, R.S., Y. Shao, J. Ediriwickrema and J.G. Lyon. 2010. Monitoring agricultural cropping patterns across the Laurentian Great Lakes basin using MODIS-NDVI data. International Journal of Applied Earth Observation and Geoinformation 12(2):81-88. https://doi.org/10.1016/j.jag.2009.11.005
  15. Luo, T., K. Kramer, D.B. Goldgof, L.O. Hall, S. Samson, A. Remsen, T. Hopkins and D. Cohn. 2005. Active learning to recognize multiple types of plankton. Journal of Machine Learning Research 6:589-613.
  16. McNairn, H., A. Kross, D. Lapen, R. Caves and J. Shang. 2014. Early season monitoring of corn and soybeans with TerraSAR-X and RADARSAT-2. International Journal of Applied Earth Observation and Geoinformation 28:252-259. https://doi.org/10.1016/j.jag.2013.12.015
  17. Mitra, P., B. Uma Shankar and S.K. Pal. 2004. Segmentation of multispectral remote sensing images using active support vector machines. Pattern Recognition Letters 25(9):1067-1074. https://doi.org/10.1016/j.patrec.2004.03.004
  18. Mun, Y.C. and H.R. Lee. 2008. Development of mobile system for crop situation investigation using GPS based on GIS. Journal of the Korean Association of Geographic Information Studies 11(4):22-31 (문영채, 이홍로.2008. GIS기반 GPS를 이용한 농작물 작황조사 모바일 시스템 구축. 한국지리정보학회지 11(4):22-31).
  19. Persello, C. and L. Bruzzone. 2014. Active and semisupervised learning for the classification of remote sensing images. IEEE Transactions on Geoscience and Remote Sensing 52(11):6937-6956. https://doi.org/10.1109/TGRS.2014.2305805
  20. Rajan, S., J. Ghosh and M.M. Crawford. 2008. An active learning approach to hyperspectral data classification. IEEE Transactions on Geoscience and Remote Sensing 46(4):1231-1242. https://doi.org/10.1109/TGRS.2007.910220
  21. Sakamoto, T., A.A. Gitelson and T.J. Arkebauer. 2014. Near real-time prediction of U.S. corn yields based on time-series MODIS data. Remote Sensing of Environment 147:219-231. https://doi.org/10.1016/j.rse.2014.03.008
  22. Shao, Y., J.B. Campbell, G.N. Taff and B. Zheng. 2015. An analysis of cropland mask choice and ancillary data for annual corn yield forecasting using MODIS data. International Journal of Applied Earth Observation and Geoinformation 38:78-87. https://doi.org/10.1016/j.jag.2014.12.017
  23. Solano, R., K. Didan, A. Jacobson and A. Huete. 2010. MODIS Vegetation Index User's Guide. Vegetation Index and Phenology Lab, The University of Arizona, AZ, USA, 38pp.
  24. Tubiello, F.N. and G. Fischer. 2007. Reducing climate change impacts on agriculture: global and regional effects of mitigation, 2000-2080. Technological Forecasting and Social Change 74(7): 1030-1056. https://doi.org/10.1016/j.techfore.2006.05.027
  25. Tuia, D., F. Ratle, F. Pacifici, M.F. Kanevski and W.J. Emery. 2009. Active learning methods for remote sensing image classification. IEEE Transactions on Geoscience and Remote Sensing 47(7):2218-2232. https://doi.org/10.1109/TGRS.2008.2010404
  26. Wardlow, B.D. and S.L. Egbert. 2008. Large-area crop mapping using time-series MODIS 250m NDVI data: an assessment for the U.S. Central Great Plains. Remote Sensing of Environment 112(3):1096-1116. https://doi.org/10.1016/j.rse.2007.07.019
  27. Zhang, J., L. Feng and F. Yao. 2014. Improved maize cultivated area estimation over a large scale combining MODIS-EVI time series data and crop phenological information. ISPRS Journal of Photogrammetry and Remote Sensing 94:102-113. https://doi.org/10.1016/j.isprsjprs.2014.04.023
  28. Zhao, M., F.A. Heinsch, R.R. Nemani and S.W. Running. 2005. Improvements of the MODIS terrestrial gross and net primary production global data set. Remote Sensing of Environment 95(2): 164-176. https://doi.org/10.1016/j.rse.2004.12.011
  29. Zhong, L., P. Gong and G.S. Biging. 2014. Efficient corn and soybean mapping with temporal extendability: a multiyear experiment using Landsat imagery. Remote Sensing of Environment 140:1-13. https://doi.org/10.1016/j.rse.2013.08.023

Cited by

  1. Self-Learning Based Land-Cover Classification Using Sequential Class Patterns from Past Land-Cover Maps vol.9, pp.9, 2017, https://doi.org/10.3390/rs9090921