Method for crop classification based on multi-source remote sensing data

International Conference on Manufacturing Technology, Materials and Chemical Engineering

材料科学;化学工业

Shi, Yun^1 ; Li, Jie^1 ; Ma, Donghui^1 ; Zhang, Tongkang^1 ; Li, Qianwen^1

College of Geomatics, Xi'An University of Science and Technology, Xi'an, Shaanxi Province

710054, China^1

关键词: Agricultural policies;    Backscattering coefficients;    Classification accuracy;    Classification methods;    Mahalanobis distances;    Multi-level classifications;    Remote sensing images;    SVM(support vector machine);   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/592/1/012192/pdf
DOI  :  10.1088/1757-899X/592/1/012192

学科分类：材料科学（综合）

来源: IOP

【 摘 要 】

Using remote sensing images to classify crops to obtain spatial distribution of different crops is of great significance for crop yield estimation and agricultural policy formulation. Due to the phenomenon of the same spectrum from different materials or the phenomenon of the same materials with different spectrum, it is difficult to obtain accurate crop classification results from single-phase images. We take a farm in Lintong District of Xi'an as the research area. The crops in this study area are mostly cross-planted, and the planting area is small, so it is difficult for the traditional classification method. In order to increase classification accuracy, a multi-level classification method is proposed in this paper. The Sentinel-1 backscattering coefficient (Sigma) of image is used to pre-classify the ground in the study area, and the Sentinel-2 images which cover the crop growth cycle in the study area are used to construct a normalized vegetation index (NDVI) time series to distinguish the growth differences of different crops. Combined with field survey data and phenological characteristics of crops, on the basis of pre-classification, SVM (Support Vector Machine) method is used to classify Sentinel-2 images. The classification accuracy reaches 98.07%, which is much higher than the minimum distance, Mahalanobis distance, neural network, expert decision tree, object-oriented and other classification methods.