U.S. Department of Agriculture: Agricultural Research Service, Lincoln, Nebraska
Date of this Version
1-1-2020
Citation
Transactions of the ASABE, Vol. 64(4): 1173-1183
https://doi.org/10.13031/trans.14145
Abstract
Assessing corn (Zea Mays L.) emergence uniformity soon after planting is important for relating to grain production and for making replanting decisions. Unmanned aerial vehicle (UAV) imagery has been used for determining corn densities at vegetative growth stage 2 (V2) and later, but not as a tool for detecting emergence date. The objective of this study was to estimate days after corn emergence (DAE) using UAV imagery. A field experiment was designed with four planting depths to obtain a range of corn emergence dates. UAV imagery was collected during the first, second and third weeks after emergence. Acquisition height was approximately 5m above ground level resulted in a ground sampling distance 1.5 mm pixel-1. Seedling size and shape features derived from UAV imagery were used for DAE classification based on the Random Forest machine learning model. Results showed image features were distinguishable for different DAE (single day) within the first week after initial corn emergence with a moderate overall classification accuracy of 0.49. However, for the second week and beyond the overall classification accuracy diminished (0.20 to 0.35). When estimating DAE within a three-day window (± 1 DAE), overall 3-day classification accuracies ranged from 0.54 to 0.88. Diameter, area, and major axis length/area were important image features to predict corn DAE. Findings demonstrated that UAV imagery can detect newly-emerged corn plants and estimate their emergence date to assist in establishing emergence uniformity. Additional studies are needed for fine-tuning image collection procedures and image feature identification in order to improve accuracy.
Comments
U.S. government work