Journal
JOURNAL OF APPLIED REMOTE SENSING
Volume 8, Issue -, Pages -Publisher
SPIE-SOC PHOTO-OPTICAL INSTRUMENTATION ENGINEERS
DOI: 10.1117/1.JRS.8.083654
Keywords
crop classification; moderate-resolution imaging spectroradiometer Normalized Difference Vegetation Index; Adaboost; support vector machine; Heihe River Basin
Funding
- Knowledge Innovation Program of the Chinese Academy of Sciences [KZCX2-EW-312]
- National Natural Science Foundation of China [91125004, 40901095]
Ask authors/readers for more resources
Accurate information regarding the structure of crops is critical for the improvement and optimization of land surface models. Multitemporal remote sensing imagery is more effective to determine the crop structure than the single-temporal images because they contain phenological information. Crop structure was extracted based on time series of moderate-resolution imaging spectroradiometer (MODIS) data in the middle Heihe River Basin. A time series of Normalized Difference Vegetation Index (NDVI) data with a 3-day temporal resolution was composed based on daily MODIS reflectance products (MOD 09) from January to December 2011. A total of 120 scenes of composited imagery were integrated into an image data cube of NDVI time series, which was used to extract crop structure for the study area. The spectral curves of corn, wheat, rape, vegetables, and other crops are based on both in situ measurements and visual interpretation. The major crop types were classified by using the adaptive boosting (Adaboost) and support vector machine (SVM) algorithms. The results show that the classification accuracy of Adaboost and SVM was 86.01% and 70.28%, respectively, with Kappa coefficients of 0.8351 and 0.6438, respectively. Summarizing the classification methods used in this study effectively characterize the spatial distribution of the main crops. (c) 2014 Society of Photo-Optical Instrumentation Engineers (SPIE)
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available