Comparison of UAV RGB Imagery and Hyperspectral Remote-Sensing Data for Monitoring Winter Wheat Growth

Although crop-growth monitoring is important for agricultural managers, it has always been a difficult research topic. However, unmanned aerial vehicles (UAVs) equipped with RGB and hyperspectral cameras can now acquire high-resolution remote-sensing images, which facilitates accelerates such monitoring. To explore the effect of single indicator multiple indicators, this study combines six growth indicators (plant nitrogen content, above-ground biomass, plant water chlorophyll, leaf area index, height) into new comprehensive index (CGI). We investigate performance imagery data crop based on multi-time estimation CGI. The CGI estimated from vegetation indices UAV treated by linear, nonlinear, linear regression (MLR), partial least squares (PLSR), random forest (RF). results are as follows: (1) RGB-imagery red reflectance (r), excess-red (EXR), atmospherically resistant (VARI), modified green-red (MGRVI), well spectral consisting combination (LCI), simple ratio (MSR), (SR), normalized difference (NDVI), more strongly correlated than growth-monitoring indicator. (2) model constructed comparing optimal corresponding to each four stages in order r, EXR; LCI all stages. (3) MLR, PLSR, RF methods used estimate MLR method produces best estimates. (4) Finally, accurately using RGB-image indices.