Abstract: Stability of food security is the most fundamental livelihood issue of the country, as key factor affecting remote sensing planting monitoring, natural factors such as clouds and fog are key factors．Therefore, accurate and efficient rapid acquisition of cultivated land planting monitoring information is of great significance for ensuring food and agriculture security, grain yield estimation, and area estimation in the study area．At present, there are few studies on construction of Multi-period Vegetation Index（MVI）synthetic model and separability of crop characteristics and cultivated land information in remote sensing cultivated land monitoring．Based on Sentinel-2 data, a multi temporal vegetation index synthesis model was constructed to estimate extraction results of the Normalized Difference Vegetation Index（NDVI）, Enhanced Vegetation Index（EVI）, and Red Edge Chlorophyll II Vegetation Index（RECI）from 2020 to 2021, correlation between prediction models and crops in high-altitude mountainous areas were studied, and accuracy of crop recognition using different vegetation index models was explored．Result showed that, compared with EVI and RECI, multi-temporal NDVI model could better identify winter wheat with higher area extraction accuracy and has the strongest correlation with winter wheat in Yunnan Plateau．The user accuracy was about 93.28%．Both three stage NDVI combination and two stage vegetation NDVI combination could accurately extract winter wheat, but extraction accuracy of three stage vegetation NDVI model was higher．Therefore, accurate prediction of winter wheat planting area using a multi temporal vegetation NDVI model proved that the model could be effectively applied to winter wheat in mountainous areas of Yunnan Plateau, and provided data support for prediction of local winter wheat area．