Comparison of Multi-Methods for Identifying Maize Phenology Using PhenoCams

Accurately identifying the phenology of summer maize is crucial for both cultivar breeding and fertilizer controlling in precision agriculture. In this study, daily RGB images covering entire growth were collected using phenocams at sites Shangqiu (2018, 2019 2020) Nanpi (2020) China. Four phenological dates, including six leaves, booting, heading maturity maize, pre-defined extracted from phenocam-based images. The spectral indices, textural indices integrated calculated improved adaptive feature-weighting method. double logistic function, harmonic analysis time series, Savitzky–Golay spline interpolation applied to filter these was identified compared with ground observations. results show that DLF achieved highest accuracy, coefficient determination (R2) root-mean-square error (RMSE) being 0.86 9.32 days, respectively. new index performed better than single usage which R2 RMSE 0.92 9.38 extraction function based on PhenoCam data effective convenient, obtaining high accuracy. Therefore, it recommended adoption by integrating extracting data.