Jaesung Park

Deep learning technologies have been increasingly applied to precision weed management, and You Only Look Once (YOLO) has become widely adopted owing to its real-time detection capability and high accuracy. This systematic review analyzes YOLO-based weed recognition models with emphasis on field challenges and architectural optimization strategies. A structured search of Web of Science and Scopus, supplemented by manual searching, was conducted in accordance with the PRISMA 2020 guidelines. Following screening and eligibility assessment, 45 studies were included in the systematic synthesis. The main categories of analysis included attention mechanisms that enhance discrimination among vegetation with similar shapes and colors, multi-scale feature-fusion architectures that integrate information across feature pyramid levels to improve the detection of weeds of varying sizes and viewpoints, and lightweight architectures designed to support real-time operation on resource-constrained hardware, along with other optimization strategies. Recent developments increasingly combine these approaches to address crop–weed similarity, occlusion, scale variation, and complex field backgrounds while improving computational efficiency. The review further examines how architectural enhancement strategies contribute to detection accuracy and computational efficiency and discusses their implications for practical applications such as selective spraying and robotic weeding. Overall, this review links major field-level weed-recognition challenges with corresponding architectural optimization strategies and provides a systematic framework for developing accurate and efficient YOLO-based weed recognition systems for site-specific weed management.

Greenhouse structural steel pipes are susceptible to internal and external corrosion under hot and humid service conditions, leading to cross-sectional loss and reduced structural strength. This study proposes a cold infrared thermography method for screening corroded pipes and identifies effective indicators for different cooling-affected regions. Experiments were performed using three non-corroded and five salt-spray-corroded SPVHS-grade specimens and three field-corroded specimens. After a cooling stimulus was applied using an ice pack, time-series mean surface-temperature data were acquired using an infrared camera. For the direct cooling region, the recovery phase was fitted with an exponential model to estimate the time constant (τ). For the indirect cooling region, located approximately 50 mm from the direct cooling region, the cooling phase was fitted with a linear model to obtain R² and the root mean square error (RMSE). Mean τ was consistently higher in the non-corroded group than in the combined corroded group across all four environmental conditions. The linearity indices in the indirect cooling region showed only exploratory, condition-dependent group differences. These findings suggest that the recovery time constant may support corrosion screening under controlled conditions.

Advances in micro-electromechanical systems (MEMS) technology have markedly improved inertial sensors, driving down cost, size, and power consumption while enhancing performance. The resulting growth in supply and demand has created tiered performance classes and price points, enabling broader adoption of inertial sensing in agriculture. In this study, we comprehensively analyzed cases of agricultural application of inertial measurement unit (IMU) or single inertial sensors by classifying them into machine and living objects. In machine targeting research, it has been used as a key element in position estimation and navigation systems for autonomous driving of mobile objects such as agricultural vehicles and robots to detect rapid attitude changes and improve the accuracy of position estimation and path tracking of the mobile object. Cases targeting living objects can be largely divided into livestock and fruit trees. In the case of livestock, wearable IMUs were attached to body parts and combined with various deep learning techniques to detect specific behaviors of livestock or classify behavioral patterns. In the case of fruit trees, a study on vibration harvesting was conducted to analyze the vibration characteristics of fruit trees by attaching acceleration sensors to tree branches or fruits and to optimize vibration parameters. The analysis focused on the types of sensors and data utilization techniques used in each research case, and based on this, we plan to explore ways to utilize IMUs in agriculture in the future.

Plastic greenhouses, which account for the majority of protected horticulture facilities in East Asia, are highly susceptible to wind-induced uplift failures that can lead to severe structural and economic damage. To address this issue, this study developed a low-power and low-cost wireless monitoring system applying the concept of structural health monitoring (SHM) to greenhouse foundations. Each sensor node integrates a MEMS-based inertial measurement unit (IMU) for attitude estimation, a LoRa module for long-range alert transmission, and a microSD module for data logging, while a gateway relays anomaly alerts to users through an IP network. Uplift tests were conducted on standard steel-pipe foundations commonly used in plastic greenhouses, and the proposed sensor nodes were evaluated alongside a commercial IMU to validate attitude estimation accuracy and anomaly detection performance. Despite the approximately 30-fold cost difference, comparable attitude estimation results were achieved. The system demonstrated low power consumption, confirming its feasibility for long-term operation using batteries or small solar cells. These results demonstrate the applicability of low-cost IMUs for real-time structural monitoring of lightweight greenhouse foundations.

Soil water content (SWC) critically governs the physical and mechanical behavior of soils. However, conventional methods such as oven drying are laborious, time-consuming, and difficult to replicate in the field. To overcome these limitations, we developed an image-based interpolation framework that leverages histogram statistics from 12 soil surface photographs spanning 3.83% to 19.75% SWC under controlled lighting. For each image, pixel-level values of red, green, blue (RGB) channels and hue, saturation, value (HSV) channels were extracted to compute per-channel histograms, whose empirical means and standard deviations were used to parameterize Gaussian probability density functions. Linear interpolation of these parameters yielded synthetic histograms and corresponding images at 1% SWC increments across the 4–19% range. Validation against the original dataset, using dice score (DS), Bhattacharyya distance (BD), and Earth Mover’s Distance (EMD) metrics, demonstrated that the interpolated images closely matched observed color distributions. Average BD was below 0.014, DS above 0.885, and EMD below 0.015 for RGB channels. For HSV channels, average BD was below 0.074, DS above 0.746, and EMD below 0.022. These results indicate that the proposed method reliably generates intermediate SWC data without additional direct measurements, especially with RGB. By reducing reliance on exhaustive sampling and offering a cost-effective dataset augmentation, this approach facilitates large-scale, noninvasive soil moisture estimation and supports machine learning applications where field data are scarce.

Recent advances in artificial intelligence and computer vision have led to significant progress in the use of agricultural technologies for yield prediction, pest detection, and real-time monitoring of plant conditions. However, collecting large-scale, high-quality image datasets in the agriculture sector remains challenging, particularly for specialized datasets such as plant disease images. This study analyzed the effects of the image size (320–640+) and the number of labels on the performance of a YOLO-based object detection model using diverse agricultural datasets for strawberries, tomatoes, chilies, and peppers. Model performance was evaluated using the intersection over union and average precision (AP), where the AP curve was smoothed using the Savitzky–Golay filter and EEM. The results revealed that increasing the number of labels improved the model performance to a certain degree, after which the performance gradually diminished. Furthermore, while increasing the image size from 320 to 640 substantially enhanced the model performance, additional increases beyond 640 yielded only marginal improvements. However, the training time and graphics processing unit usage scaled linearly with increasing image sizes, as larger size images require greater computational resources. These findings underscore the importance of an optimal strategy for selecting the image size and label quantity under resource constraints in real-world model development.

Determining the size or area of a plant's leaves is an important factor in predicting plant growth and improving the productivity of indoor farms. In this study, we developed a convolutional neural network (CNN)-based model to accurately predict the length and width of lettuce leaves using photographs of the leaves. A callback function was applied to overcome data limitations and overfitting problems, and K-fold cross-validation was used to improve the generalization ability of the model. In addition, ImageDataGenerator function was used to increase the diversity of training data through data augmentation. To compare model performance, we evaluated pre-trained models such as VGG16, Resnet152, and NASNetMobile. As a result, NASNetMobile showed the highest performance, especially in width prediction, with an R_squared value of 0.9436, and RMSE of 0.5659. In length prediction, the R_squared value was 0.9537, and RMSE of 0.8713. The optimized model adopted the NASNetMobile architecture, the RMSprop optimization tool, the MSE loss functions, and the ELU activation functions. The training time of the model averaged 73 minutes per Epoch, and it took the model an average of 0.29 seconds to process a single lettuce leaf photo. In this study, we developed a CNN-based model to predict the leaf length and leaf width of plants in indoor farms, which is expected to enable rapid and accurate assessment of plant growth status by simply taking images. It is also expected to contribute to increasing the productivity and resource efficiency of farms by taking appropriate agricultural measures such as adjusting nutrient solution in real time.