Skip to main content

Advertisement

Fig. 4 | Plant Methods

Fig. 4

From: Estimation of vegetation indices for high-throughput phenotyping of wheat using aerial imaging

Fig. 4

Comparison of the observed and estimated NDVI. a DNN-RGB, b DNN-T, c DNN-GRAY, d LR-RGB estimation model.The equation, coefficient of determination (\(\text {R}^2\)) and Root Mean Squared Error (\(\text {e}_{\text {rms}}\)) of regression analysis is provided in legend. c Error statistics of estimation models at different DaS. In each box, the central mark is median, and the lower and upper edges denote the 25th and 75th percentile of errors (\(q_1\) and \(q_3\)), respectively. If the central notches of two boxes do not overlap, their true medians are different at the 0.05 significance level (indicated by *). The whiskers extend to the most extreme data points not considered outliers \([q_1-w\times (q_3 - q_1),q_3+w\times (q_3-q_1)], w=1.5\). Outliers not shown on the chart for clarity

Back to article page