Winter wheat planting area extraction method and device based on deep learning

The invention discloses a winter wheat planting area extraction method and device based on deep learning. Comprising the steps of data acquisition and preprocessing; constructing a winter wheat sample data set; constructing and training a winter wheat planting area extraction model; extracting a winter wheat planting area in the monitoring area; and post-processing the preliminary extraction result of the winter wheat planting area to obtain an optimized winter wheat planting area extraction result. According to the method, on the basis of the single-temporal high-resolution optical image of the key phenological period of winter wheat growth, a lightweight deep learning model is utilized, and the winter wheat planting area is efficiently and accurately extracted on a large scale. 一种基于深度学习的冬小麦种植区域提取方法和装置。包括：数据获取及预处理；冬小麦样本数据集构建；进行冬小麦种植区域提取模型构建及训练；在监测区域进行冬小麦种植区域提取；进行冬小麦种植区域初步提取结果的后处理，得到优化的冬小麦种植区域提取结果。本发明基于冬小麦生长关键物候期的单时相高分辨率光学影像，利用轻量级的深度学习模型，实现规模化、高效、准确地提取冬小麦种植区域。