Abstract
Crop classification is one of the focused topics in remote sensing study nowadays. Optical imageries, although providing much information, are often contaminated with cloud or other weather effects while SAR imageries are more resilient to those. Temporal series data are often used to improve classification accuracy, especially in crop classification. This article investigates the usage of temporal series SAR imagery on crop classification in vast rural areas of China. The selected area of interest has a complicated, heavily mixed agriculture as well as lots of nonagricultural landcovers. Total ten classes are considered, six of them being crop types. A pixel-based classifier using subspace k th nearest neighbor (KNN) algorithm is applied to open source Sentinel-1 polarized SAR data. Discussion includes analyzing temporal features of the SAR observation, time domain smoothing, feature engineering, different classification algorithms, and selection of temporal series. The study results in an overall accuracy of 98.2% for the ten classes in fivefold cross validation, indicating a propitious application for agricultural monitoring using SAR data.
Highlights
C ROP classification based on remote sensing data is regarded as meaningful and useful for both commercial purpose and policy making
We explore the challenges by building the classification algorithms based on very little ground truth with 5 crop types and 5 noncrop types, among them 1 other crop type and 1 other land use type
The crop and land cover classification application based on temporal SAR for rural China is studied
Summary
C ROP classification based on remote sensing data is regarded as meaningful and useful for both commercial purpose and policy making. Many works have been carried out using remote sensing data in the form of optical imagery [1]–[8]. One way to solve the issue could be using SAR imageries instead of optical imageries. For a purpose such as crop classification, it could be very difficult to build a reasonable classifier using a single SAR image. The temporal series SAR data-based crop classification methods have been proven in many datasets such as Europe, Africa, and Southeast Asia such as Vietnam, [9]–[19]. We conducted a study for temporal SAR imagery crop classification in rural China. Six crop types are considered with four noncrop landcover types identified
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
