Corn (Zea mays L.) is one of the most sensitive crops to planting pattern and early-season uniformity. The most common method to determine number of plants is by visual inspection on the ground but this field activity becomes time-consuming, labor-intensive, biased, and may lead to less profitable decisions by farmers. The objective of this study was to develop a reliable, timely, and unbiased method for counting corn plants based on ultra-high-resolution imagery acquired from unmanned aerial systems (UAS) to automatically scout fields and applied to real field conditions. A ground sampling distance of 2.4 mm was targeted to extract information at a plant-level basis. First, an excess greenness (ExG) index was used to individualized green pixels from the background, then rows and inter-row contours were identified and extracted. A scalable training procedure was implemented using geometric descriptors as inputs of the classifier. Second, a decision tree was implemented and tested using two training modes in each site to expose the workflow to different ground conditions at the time of the aerial data acquisition. Differences in performance were due to training modes and spatial resolutions in the two sites. For an object classification task, an overall accuracy of 0.96, based on the proportion of corrected assessment of corn and non-corn objects, was obtained for local (per-site) classification, and an accuracy of 0.93 was obtained for the combined training modes. For successful model implementation, plants should have between two to three leaves when images are collected (avoiding overlapping between plants). Best workflow performance was reached at 2.4 mm resolution corresponding to 10 m of altitude (lower altitude); higher altitudes were gradually penalized. The latter was coincident with the larger number of detected green objects in the images and the effectiveness of geometry as descriptor for corn plant detection.

Label assignment plays a significant role in modern object detection models. Detection models may yield totally different performances with different label assignment strategies. For anchor-based detection models, the IoU (Intersection over Union) threshold between the anchors and their corresponding ground truth bounding boxes is the key element since the positive samples and negative samples are divided by the IoU threshold. Early object detectors simply utilize the fixed threshold for all training samples, while recent detection algorithms focus on adaptive thresholds based on the distribution of the IoUs to the ground truth boxes. In this paper, we introduce a simple while effective approach to perform label assignment dynamically based on the training status with predictions. By introducing the predictions in label assignment, more high-quality samples with higher IoUs to the ground truth objects are selected as the positive samples, which could reduce the discrepancy between the classification scores and the IoU scores, and generate more high-quality boundary boxes. Our approach shows improvements in the performance of the detection models with the adaptive label assignment algorithm and lower bounding box losses for those positive samples, indicating more samples with higher-quality predicted boxes are selected as positives.

Automation continues to play a greater role in agricultural production with commercial systems now available for machine vision identification of weeds and other pests, autonomous weed control, and robotic harvesters for fruits and vegetables. The growing availability of autonomous machines in agriculture indicates that there are opportunities to increase automation in cotton production. This article considers how current and future advances in automation has, could, or will impact cotton production practices. The results are organized to follow the cotton production process from land preparation to planting to within season management through harvesting and ginning. For each step, current and potential opportunities to automate processes are discussed. Specific examples include advances in automated weed control and progress made in the use of robotic systems for cotton harvesting.

Pest infestation causes significant crop damage during crop production, which reduces the crop yield in terms of quality and quantity. Accurate, precise, and timely information on pest infestation is a crucial aspect of integrated pest management practices. The current manual scouting methods are time-consuming and laborious, particularly for large fields. Therefore, a fleet of scouting vehicles is proposed to monitor and collect crop information at the sub-canopy level. These vehicles would traverse large fields and collect real-time information on pest type, concentration, and infestation level. In addition to this, the developed vehicle platform would assist in collecting information on soil moisture, nutrient deficiency, and disease severity during crop growth stages. This study established a proof-of-concept of a crop scouting vehicle that can navigate through the row crops. A reconfigurable ground vehicle (RGV) was designed and fabricated. The developed prototype was tested in the laboratory and an actual field environment. Moreover, the concept of corn row detection was established by utilizing an array of low-cost ultrasonic sensors. The RGV was successful in navigating through the corn field. The RGV’s reconfigurable characteristic provides the ability to move anywhere in the field without damaging the crops. This research shows the promise of using reconfigurable robots for row crop navigation for crop scouting and monitoring which could be modular and scalable, and can be mass-produced in quick time. A fleet of these RGVs would empower the farmers to make meaningful and timely decisions for their cropping system.

Alfalfa (Medicago sativa L.) is one of the most relevant forage crops due to its importance for livestock. Timely harvesting is critical to secure adequate forage quality. However, farmers face challenges not only to decide the optimal harvesting time but to predict the optimum levels for both forage production and quality. Fortunately, remote sensing technologies can significantly contribute to obtaining production and quality insights, providing scalability, and supporting complex farming decision-making. Therefore, we aim to develop a systematic review of the current scientific literature to identify the current status of research in remote sensing for alfalfa and to evaluate new perspectives for enhancing prediction of both biomass and quality (herein defined as crude protein and fibers) for alfalfa. Twelve papers were included in the database from a total of 198 studies included in the initial screening process. The main findings were (i) more than two-thirds of the studies focused on predicting biomass; (ii) half of the studies used terrestrial platforms, with only 33% using drones and 17% using satellite for remote sensing; (iii) no studies have used satellites assessed alfalfa quality traits; (iv) improved biomass and quality estimations were obtained when remote sensing data was combined with environmental information; (v) due to a direct relationship between biomass and quality, modeling them algorithmically improves the accuracy of estimation as well; (vi) from spectral wavelengths, dry biomass was better estimated in regions near 398, 551, 670, 730, 780, 865, and 1077 nm, wet biomass in regions near 478, 631, 670, 730, 780, 834, 933, 1034, and 1538 nm, and quality traits identified with narrow and very specific wavelengths (e.g., 398, 461, 551, 667, 712, and 1077 nm). Our findings might serve as a foundation to guide further research and the development of handheld sensors for assessing alfalfa biomass and quality.

The spatial information about crop grain protein concentration (GPC) can be an important layer (i.e., a map that can be utilized in a geographic information system) with uses from nutrient management to grain marketing. Recently, on- and off-combine harvester sensors have been developed for creating spatial GPC layers. The quality of these GPC layers, as measured by the coefficient of determination (R²) and the root mean squared error (RMSE) of the relationship between measured and predicted GPC, is affected by different sensing characteristics. The objectives of this synthesis analysis were to (i) contrast GPC prediction R² and RMSE for different sensor types (on-combine, off-combine proximal and remote); (ii) contrast and discuss the best spatial, temporal, and spectral resolutions and features, and the best statistical approach for off-combine sensors; and (iii) review current technology limitations and provide future directions for spatial GPC research and application. On-combine sensors were more accurate than remote sensors in predicting GPC, yet with similar precision. The most optimal conditions for creating reliable GPC predictions from off-combine sensors were sensing near anthesis using multiple spectral features that include the blue and green bands, and that are analyzed by complex statistical approaches. We discussed sensor choice in regard to previously identified uses of a GPC layer, and further proposed new uses with remote sensors including same season fertilizer management for increased GPC, and in advance segregated harvest planning related to field prioritization and farm infrastructure. Limitations of the GPC literature were identified and future directions for GPC research were proposed as (i) performing GPC predictive studies on a larger variety of crops and water regimes; (ii) reporting proper GPC ground-truth calibrations; (iii) conducting proper model training, validation, and testing; (iv) reporting model fit metrics that express greater concordance with the ideal predictive model; and (v) implementing and benchmarking one or more uses for a GPC layer.