|VONG, CHINNEE - University Of Missouri|
|STEWART, STIRLING - University Of Missouri|
|ZHOU, JIANFENG - University Of Missouri|
|Sudduth, Kenneth - Ken|
Submitted to: Transactions of the ASABE
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 3/18/2021
Publication Date: 7/11/2021
Citation: Vong, C., Stewart, S.A., Zhou, J., Kitchen, N.R., Sudduth, K.A. 2021. Estimation of corn emergence date using UAV imagery. Transactions of the ASABE. 64(4):1173-1183. https://doi.org/10.13031/trans.14145.
Interpretive Summary: Corn stand may not be uniform when soils become cold and wet during the emergence period causing stress to the germinating seed. When plants don’t emerge from the soil at about the same time (i.e., within a few days of each other), grain yield can be reduced. When emergence is spread over many days, farmers must decide if they should replant portions or all of a field. To help make timely replanting decisions, automated tools are needed to help farmers quickly evaluate many acres. This research was conducted to evaluate if corn emergence could be accurately determined using unmanned aerial vehicle (UAV) images. The research showed corn plant features were distinguishable within the first week of emergence and the day of emergence could be estimated correctly about 50% of the time. However, for the second week after emergence, accuracy was much less. By relaxing the estimation window to one day before and after the actual day of emergence, estimates were correct 55 to 90% of the time. Findings demonstrate that UAV imagery can detect newly-emerged corn plants and estimate their emergence date. If this process could be more completely automated, farmers could utilize UAV scouting to help determine fields or portions of fields that need replanting.
Technical Abstract: Assessing corn (Zea Mays L.) emergence uniformity soon after planting is important for relating to grain production and 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, which resulted in a ground sampling distance of 1.5 mm/pixel. Seedling size and shape features derived from UAV imagery were used for DAE classification based on a random forest machine learning model. Results showed DAE could be distinguished based on image features 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 the ratio of major axis length to 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 assessing emergence uniformity. Additional studies are needed for fine-tuning image collection procedures and image feature identification in order to improve accuracy.