Research on Cotton Information Extraction Based on Sentinel-2 Time Series Analysis

Abstract

Cotton is an important economic crop and plays an important role in the national economy. Therefore, timely and accurate access to crop planting area and spatial distribution information is very important for government departments to make economic decisions and adjust cotton planting structure. At the same time, crop census and cotton growth monitoring There are also important applications in terms of production estimates and disaster assessment. This study is based on Google Earth Engine remote sensing big data cloud computing platform and Sentinel-2 data, taking Zaoqiang County of Hengshui City, Hebei Province as an example, using nearly 50 scenes of Sentinel-2 data, combined with interest area index calculation, S-G filtering method, etc. The time series phenotypic analysis method was constructed to analyze the phenological characteristics of the main crop cotton and the interfering crop corn in Zaoqiang County. Based on the phenological analysis results, the key time phase data of cotton extraction was screened, and the objectoriented information extraction method was combined with spectral features and texture features. The cotton distribution information of Zaoqiang County was extracted, and the accuracy of the results was analyzed with the field sample data. The overall accuracy was 92%, which satisfied the cotton monitoring application demand of Zaoqiang County.