Plant height of maize is related to lodging resistance and yield and is highly heritable but also polygenic, and thus is an important trait in maize breeding. Various manual methods exist to determine the plant height of maize, yet they are labor-intensive and time consuming. Therefore, we established digital surface models (DSM) based on RGB-images captured by an unmanned aerial vehicle (UAV) at five different dates throughout the growth period to rapidly estimate plant height of 400 maize genotypes. The UAV-based estimation of plant height (PH_UAV) was compared to the manual measurement from the ground to the highest leaf (PH_L), to the tip of the manually straightened highest leaf (PH_S) and, on the final date, to the top of the tassel (PH_T). The best results were obtained for estimating both PH_L (0.44 ≤ R² ≤ 0.51) and PH_S (0.50 ≤ R² ≤ 0.61) from 39 to 68 days after sowing (DAS). After calibration the mean absolute percentage error (MAPE) between PH_UAV and PH_S was in a range from 12.07% to 19.62%. It is recommended to apply UAV-based maize height estimation from 0.2 m average plant height to maturity before the plants start to senesce and change the leaf color.

Increasingly many applications of machine vision and artificial intelligence (AI) can be observed in agriculture. Yet, high-quality training data remains a bottleneck in the development of many AI solutions, particularly for image segmentation. Therefore, ARAMSAM (agricultural rapid annotation module based on segment anything models) was developed, a user interface that orchestrates the pre-labelling capabilities of both the segment anything models (SAM 1, SAM 2) and conventional annotation tools. One in silico experiment on zero-shot performance of SAM 1 and SAM 2 on three unseen agricultural datasets and another experiment on hyperparameter optimization of the automatic mask generators (AMG) were conducted. In a user experiment, 14 agricultural experts applied ARAMSAM to quantify the reduction of annotation times. SAM 2 benefited greatly from hyperparameter optimization of its AMG. Based on ground-truth masks matched with predicted masks, the F ₂ -score of SAM 2 improved from 0.05 to 0.74, while that of SAM 1 was improved from 0.87 to 0.93. The user interaction time could be reduced to 2.1 s/mask on single images (SAM 1) and to 1.6 s/mask on image sequences (SAM 2) compared to polygon drawing (9.7 s/mask). This study demonstrates the potential of segment anything models as incorporated into ARAMSAM to significantly accelerate the process of segmentation mask annotation in agriculture and other fields. ARAMSAM will be released as open-source software (AGPL-3.0 license) at https://github.com/DerOehmer/ARAMSAM .

Increasingly many applications of machine vision and artificial intelligence (AI) can be observed in agriculture. Yet, high quality training data remains a bottleneck in the development of many AI solutions which is particularly true for image segmentation. Therefore, ARAMSAM (agricultural rapid annotation module based on segment anything models) was developed, a user interface orchestrating the pre-labelling capabilities of both the segment anything models (SAM 1, SAM 2) as well as conventional annotation tools. One in silico experiment on zero-shot performance of SAM 1 and SAM 2 on three unseen agricultural datasets and another experiment on hyperparameter optimization of the automatic mask generators (AMG) were conducted. In a user experiment, 14 agricultural experts applied ARAMSAM to quantify the reduction of annotation times. SAM 2 benefitted greatly from hyperparameter optimization of its AMG. Based on ground truth masks matched with predicted masks, the F₂-score of SAM 2 improved from 0.05 to 0.74 while SAM 1 was improved from 0.87 to 0.93. The user interaction time could be reduced to 2.1 s/mask on single images (SAM 1) and to 1.6 s/mask on image sequences (SAM 2) compared to polygon drawing (9.7 s/mask). This study demonstrates the potential of segment anything models as incorporated in ARAMSAM to significantly accelerate the process of segmentation mask annotation in agriculture and other fields. ARAMSAM will be released as open-source software (AGPL-3.0 license) at https://github.com/DerOehmer/ARAMSAM.