AUTOMATIC CROP CLASSIFICATION METHOD AND SYSTEM BASED ON MULTI-CLASSIFIER FUSION, AND STORAGE MEDIUM

UITTREKSEL Disclosed are an automatic crop classification method and system based on multi-classifier fusion, and a storage medium. The method includes: collecting and preprocessing data to obtain preprocessed high-resolution data and Hmlti-spectral time series reflectance; computing a normalized difference vegetation index (NDVI) time series on the basis of the multi-spectral time series reflectance; selecting, on the basis of the computed NDVI time series and in combination with crop type training samples, multi-spectral image data participating in classification; inputting the high- resolution data, the NDVI time series and the multi-spectral image data participating in classification into a classifier set to obtain an initial classification result set; and executing an overall classification. accuracy-majority vote (GCA-MV) algorithm on the initial classification result set to complete decision fusion classification.