Estimation of fractional coverage of alpine black soils by soybean vegetation using UAV-based multi-spectral images and vegetation indices.

To extract accurately and quickly the fractional vegetation coverage (FVC) for the case of soybean crops in alpine black-soil regions during flowering-podding and seed-filling growth stages, we use unmanned aerial vehicles (UAVs) to collect multi-spectral images of the soybean crops. Different vegetation indices for the multi-spectral bands are analyzed and compared. These are a vegetative index (VEG), a colour index of vegetation extraction (CIVE), an excessive green-feature index (EXG), an excessive green-and-red difference index (EXGR), a combined vegetation index (CVI), a normalized green-blue difference index (NGBDI), a normalized vegetation index (NDVI), a soil-adjusted vegetation index (SAVI), and a modified soil-adjusted vegetation index (MSAVI). A supervised classification method is combined with a threshold method based on statistical histograms of the vegetation indices. This offers an efficient technique for extracting the soybean coverage in the alpine black soils. We divide our experimental field into soil pixels and soybean pixels, while the UAVbased remote-sensing data is divided into the categories of soil and soybean vegetation, using a supervised classification method. Then intersects of the histograms of the vegetation-indices distributions derived with the UAV data are taken as thresholds for the soil and soybeanvegetation pixels. The soybean FVC extracted from synchronously collected high-resolution visible-light images with the ground resolution 0.036 m is used as a reference value for the comparative analysis of the accuracies. Our study reveals the following: (1) the FVCextraction accuracy becomes higher than 90% if the thresholds of the vegetation indices are determined by the statistical histograms and the images obtained with the UAVs are classified in order to extract the FVC, (2) one obtains too high a coverage with the NGBDI index; the corresponding errors are equal to 6.14% and 2.18% respectively for the flowering-podding and seed-filling stages, (3) the COM, VEG, EXG, SAVI and MSAVI indices demonstrate a sufficient accuracy and reliability, and (4) the EXG index provides the highest precision at the podding stage, while the COM index is the best for the period of soybean-kernel filling. Our results represent an important reference for future high-precision extraction of the soybean-vegetation coverage at different growth stages. [ABSTRACT FROM AUTHOR]