As one of the key crop traits, plant height is traditionally evaluated manually, which can be slow, laborious and prone to error. Rapid development of remote and proximal sensing technologies in recent years allows plant height to be estimated in more objective and efficient fashions, while research regarding direct comparisons between different height measurement methods seems to be lagging. In this study, a ground-based multi-sensor phenotyping system equipped with ultrasonic sensors and light detection and ranging (LiDAR) was developed. Canopy heights of 100 wheat plots were estimated five times during a season by the ground phenotyping system and an unmanned aircraft system (UAS), and the results were compared to manual measurements. Overall, LiDAR provided the best results, with a root-mean-square error (RMSE) of 0.05 m and an R² of 0.97. UAS obtained reasonable results with an RMSE of 0.09 m and an R² of 0.91. Ultrasonic sensors did not perform well due to our static measurement style. In conclusion, we suggest LiDAR and UAS are reliable alternative methods for wheat height evaluation.

Iron deficiency chlorosis (IDC) is an abiotic stress in soybean that can cause significant biomass and yield reduction. IDC is characterized by stunted growth and yellowing and interveinal chlorosis of early trifoliate leaves. Scoring IDC severity in the field is conventionally done by visual assessment. The goal of this study was to investigate the usefulness of Red Green Blue (RGB) images of soybean plots captured under the field condition for IDC scoring. A total of 64 soybean lines with four replicates were planted in 6 fields over 2 years. Visual scoring (referred to as Field Score, or FS) was conducted at V3–V4 growth stage; and concurrently RGB images of the field plots were recorded with a high-throughput field phenotyping platform. A second set of IDC scores was done on the plot images (displayed on a computer screen) consistently by one person in the office (referred to as Office Score, or OS). Plot images were then processed to remove weeds and extract six color features, which were used to train computer-based IDC scoring models (referred to as Computer Score, or CS) using linear discriminant analysis (LDA) and support vector machine (SVM). The results showed that, in the fields where severe IDC symptoms were present, FS and OS were strongly positively correlated with each other, and both of them were strongly negatively correlated with yield. CS could satisfactorily predict IDC scores when evaluated using FS and OS as the reference (overall classification accuracy > 81%). SVM models appeared to outperform LDA models; and the SVM model trained to predict IDC OS gave the highest prediction accuracy. It was anticipated that coupling RGB imaging from the high-throughput field phenotyping platform with real-time image processing and IDC CS models would lead to a more rapid, cost-effective, and objective scoring pipeline for soybean IDC field screening and breeding.

Global crop production is facing the challenge of a high projected demand, while the yields of major crops are not increasing at sufficient speeds. Crop breeding is an important way to boost crop productivity, however its improvement rate is partially hindered by the long crop generation cycles. If end-season crop traits such as yield can be predicted through early-season phenotypic measurements, crop selection can potentially be made before a full crop generation cycle finishes. This study explored the possibility of predicting soybean end-season traits through the color and texture features of early-season canopy images. Six thousand three hundred and eighty-three images were captured at V4/V5 growth stage over 6039 soybean plots growing at four locations. One hundred and forty color features and 315 gray-level co-occurrence matrix-based texture features were derived from each image. Another two variables were also introduced to account for location and timing differences between the images. Five regression and five classification techniques were explored. Best results were obtained using all 457 predictor variables, with Cubist as the regression technique and Random Forests as the classification technique. Yield (RMSE = 9.82, R² = 0.68), Maturity (RMSE = 3.70, R² = 0.76) and Seed Size (RMSE = 1.63, R² = 0.53) were identified as potential soybean traits that might be early predictable.

Frost is a natural disaster that can cause catastrophic damages in agriculture, while traditional temperature monitoring in orchards has disadvantages such as being imprecise and laborious, which can lead to inadequate or wasteful frost protection treatments. In this article, we presented a heating requirement assessment methodology for frost protection in an apple orchard utilizing unmanned aerial vehicle (UAV)-based thermal and RGB cameras. A thermal image stitching algorithm using the BRISK feature was developed for creating georeferenced orchard temperature maps, which attained a sub-centimeter map resolution and a stitching speed of 100 thermal images within 30 s. YOLOv4 classifiers for six apple flower bud growth stages in various network sizes were trained based on 5040 RGB images, and the best model achieved a 71.57% mAP for a test dataset consisted of 360 images. A flower bud mapping algorithm was developed to map classifier detection results into dense growth stage maps utilizing RGB image geoinformation. Heating requirement maps were created using artificial flower bud critical temperatures to simulate orchard heating demands during frost events. The results demonstrated the feasibility of the proposed orchard heating requirement determination methodology, which has the potential to be a critical component of an autonomous, precise frost management system in future studies.

Uncooled thermal cameras have been employed as common UAV payloads for aerial temperature surveillance in recent years. Due to the lack of internal cooling systems, such cameras often suffer from thermal-drift-induced nonuniformity or vignetting despite having built-in mechanisms to minimize the noise. The current study examined a UAV-based uncooled thermal camera vignetting regarding camera warmup time, ambient temperature, and wind speed and direction, and proposed a simple calibration-based vignetting migration method. The experiments suggested that the camera needed to undergo a warmup period to achieve stabilized performance. The required warmup duration ranged from 20 to 40 min depending on ambient temperature. Camera vignetting severity increased with camera warmup time, decreasing ambient temperature, and wind presence, while wind speed and direction did not make a difference to camera vignetting during the experiments. Utilizing a single image of a customized calibration target, we were able to mitigate vignetting of outdoor images captured in a 30 min duration by approximately 70% to 80% in terms of the intra-image pixel standard deviation (IISD) and 75% in terms of the pixel-wise mean (PWMN) range. The results indicated that outdoor environmental conditions such as air temperature and wind speed during short UAV flights might only minimally influence the thermal camera vignetting severity and pattern. Nonetheless, frequent external shutter-based corrections and considering the camera nonlinear temperature response in future studies have the potential to further improve vignetting correction efficacy for large scene temperature ranges.

Object detection is one of the most promising research topics currently, whose application in agriculture, however, can be challenged by the difficulty of annotating complex and crowded scenes. This study presents a brief performance assessment of YOLOv7, the state-of-the-art object detector, in comparison to YOLOv4 for apple flower bud classification using datasets with artificially manipulated image annotation qualities from 100% to 5%. Seven YOLOv7 models were developed and compared to corresponding YOLOv4 models in terms of average precisions (APs) of four apple flower bud growth stages and mean APs (mAPs). Based on the same test dataset, YOLOv7 outperformed YOLOv4 for all growth stages at all training image annotation quality levels. A 0.80 mAP was achieved by YOLOv7 with 100% training image annotation quality, meanwhile a 0.63 mAP was achieved with only 5% training image annotation quality. YOLOv7 improved YOLOv4 APs by 1.52% to 166.48% and mAPs by 3.43% to 53.45%, depending on the apple flower bud growth stage and training image annotation quality. Fewer training instances were required by YOLOv7 than YOLOv4 to achieve the same levels of classification accuracies. The most YOLOv7 AP increase was observed in the training instance number range of roughly 0 to 2000. It was concluded that YOLOv7 is undoubtedly a superior apple flower bud classifier than YOLOv4, especially when training image annotation quality is suboptimal.