Pest control is essential for increasing agricultural production. Agricultural drones with spraying systems for pest control have generated great interest among farmers. However, spraying systems installed on unmanned aerial vehicles, like any other sprayer, can cause damage to the environment due to drift of the agent. Air induction (AI) nozzles are known to produce less drift (e.g., larger spray drops) than other nozzles, but there is a lack of research analyzing their effectiveness in combination with drones. In this study, AI and flat fan nozzles were installed on drones to evaluate their spray and pest control performance. Aerial spraying was conducted on rice and soybeans to measure the coverage and penetration ratio and analyze the crop production as well as the crop damage due to pests and diseases. The drone flight was conducted at an altitude of 3 m and a velocity of 2 m/s. Spray droplets were collected using water-sensitive paper at two heights above the soil surface. The experiments showed that the crop coverage with the AI nozzle was 130% higher than that with the flat fan nozzle. The drift reduction of AI nozzles increased the coverage of spray droplets. But the difference in the penetration ratios, which is the ratio of agents to be delivered inside the crop, was not significant between the nozzles. Also, there was no significant difference in crop yield and pest control efficacy. Consequently, the performance of the AI nozzle did not show differences from that of the XR nozzle, except for coverage. However, the AI nozzle raised less drift, so it should be considered for use in aerial control.

Unmanned aerial spraying systems (UASSs) are widely used today for the effective control of pests affecting crops, and more advanced UASS techniques are now being developed. To evaluate such systems, artificial targets are typically used to assess droplet coverage through image processing. To evaluate performance accurately, high-quality binary image processing is necessary; however, this involves labor for sample collection, transportation, and storage, as well as the risk of potential contamination during the process. Therefore, rapid assessment in the field is essential. In the present study, we evaluated droplet coverage on water-sensitive papers (WSPs) under field conditions. A dataset was constructed consisting of paired training examples, each comprising source and target data. The source data were high-quality labeled images obtained from WSP samples through image processing, while the target data were aligned RoIs within field images captured in situ. Droplet coverage estimation was performed using an encoder–decoder model, trained on the labeled images, with features adapted to field images via self-supervised learning. The results indicate that the proposed method detected droplet coverage in field images with an error of less than 5%, demonstrating a strong correlation between measured and estimated values (R² = 0.99). The method proposed in this paper enables immediate and accurate evaluation of the performance of UASSs in situ.

Direct seeding has gained prominence as a labor-efficient and environmentally sustainable alternative to conventional transplanting in rice cultivation. In direct seeding systems, early-stage management is crucial for stable seedling establishment, with sowing uniformity measured by seed counts being a critical indicator of success. However, conventional manual seed counting methods are time-consuming, prone to human error, and impractical for large-scale or repetitive tasks, necessitating advanced automated solutions. Recent advances in computer vision technologies and precision agriculture tools, offer the potential to automate seed counting tasks. Nevertheless, challenges such as domain discrepancies and limited labeled data restrict robust real-world deployment. To address these issues, we propose a density estimation-based seed counting framework integrating semi-supervised learning and background augmentation. This framework includes a cost-effective data acquisition system enabling diverse domain data collection through indoor background augmentation, combined with semi-supervised learning to utilize augmented data effectively while minimizing labeling costs. The experimental results on field data from unknown domains show that our approach reduces seed counting errors by up to 58.5% compared to conventional methods, highlighting its potential as a scalable and effective solution for agricultural applications in real-world environments.

Advances in sensor technology have significantly improved the efficiency and precision of agricultural spraying. Unmanned aerial vehicles (UAVs) are widely utilized for applying plant protection products (PPPs) and fertilizers, offering enhanced spatial control and operational flexibility. This study evaluated the performance of an autonomous UAV-based precision spraying system that applies variable rates based on zone levels defined in a prescription map. The system integrates real-time kinematic global navigation satellite system positioning with a proximity-triggered spray algorithm. Field experiments on a rice field were conducted to assess spray accuracy and fertilization efficacy with liquid fertilizer. Spray deposition patterns on water-sensitive paper showed that the graded strategy distinguished among zone levels, with the highest deposition in high-spray zones, moderate in medium zones, and minimal in no-spray zones. However, entry and exit deviations—used to measure system response delays—averaged 0.878 m and 0.955 m, respectively, indicating slight lags in spray activation and deactivation. Fertilization results showed that higher application levels significantly increased the grain-filling rate and thousand-grain weight (both p < 0.001), but had no significant effect on panicle number or grain count per panicle (p > 0.05). This suggests that increased fertilization primarily enhances grain development rather than overall plant structure. Overall, the system shows strong potential to optimize inputs and yields, though UAV path tracking errors and system response delays require further refinement to enhance spray uniformity and accuracy under real-world applications.

Multispectral sensors are integral to vegetation analysis, particularly in the calculation of various vegetation indices (VIs). The use of integrated multispectral sensors has become prevalent in research, although their effectiveness is influenced by several factors. This highlights the need for ongoing research into enhancement techniques to improve the accuracy and reliability of vegetation status estimation. This study investigated the impact of field of view (FOV) variability on normalized differential vegetation index (NDVI) accuracy using a multispectral sensor. Data were collected from a wheat field at four growth stages (GS) (GS 1, GS 2, GS 3, and GS 4, at 10, 34, 70, and 84 days after sowing (DAS), respectively) and the sensors were mounted around 100 cm above the crop canopy. An active sensor was used to provide reference data for assessing multispectral measurement. A program was developed using the Python (ver. 3.10) programming language to process the global navigation satellite system (GNSS) coordinates and segment the images to align with the FOV of the active sensor and extracting the reflectance data for NDVI calculation. The results showed that proper FOV alignment significantly improved regression metrics (R² and RMSE) at all growth stages, with R² improvements ranging from 3% to 33%, and RMSE reductions from 0.03 to 0.06, respectively. The high vegetative growth stage was less affected due to the FOV misalignment. These techniques are promising toward improving NDVI accuracy, especially during early and mid-growth stages of the crop.

Sensing distance and speed have crucial effects on the data of active and passive sensors, providing valuable information relevant to crop growth monitoring and environmental conditions. The objective of this study was to evaluate the effects of sensing speed and sensor height on the variation in proximal canopy reflectance data to improve rice vegetation monitoring. Data were collected from a rice field using active and passive sensors with calibration procedures including downwelling light sensor (DLS) calibration, field of view (FOV) alignment, and radiometric calibration, which were conducted per official guidelines. The data were collected at six sensor heights (30–130 cm) and speeds (0–0.5 ms^–1). Analyses, including peak signal-to-noise ratio (PSNR) and normalized difference vegetation index (NDVI) calculations and statistical assessments, were conducted to explore the impacts of these parameters on reflectance data variation. PSNR analysis was performed on passive sensor image data to evaluate image data variation under varying data collection conditions. Statistical analysis was conducted to assess the effects of sensor speed and height on the NDVI derived from active and passive sensor data. The PSNR analysis confirmed that there were significant impacts on data variation for passive sensors, with the NIR and G bands showing higher noise sensitivity at increased speeds. The NDVI analysis showed consistent patterns at sensor heights of 70–110 cm and sensing speeds of 0–0.3 ms^–1. Increased sensing speeds (0.4–0.5 ms^–1) introduced motion-related variability, while lower heights (30–50 cm) heightened ground interference. An analysis of variance (ANOVA) indicated significant individual effects of speed and height on four spectral bands, red (R), green (G), blue (B), and near-infrared (NIR), in the passive sensor images, with non-significant interaction effects observed on the red edge (RE) band. The analysis revealed that sensing speed and sensor height influence NDVI reliability, with the configurations of 70–110 cm height and 0.1–0.3 ms^–1 speed ensuring the stability of NDVI measurements. This study notes the importance of optimizing sensor height and sensing speed for precise vegetation index calculations during field data acquisition for agricultural crop monitoring.