This study investigated the interoperability of a tomato fruit detection model trained using nighttime images from two greenhouses. The goal was to evaluate the performance of the models in different environmets, including different facilities, cultivation methods, and imaging times. An innovative imaging approach is introduced to eliminate the background, highlight the target plants, and test the adaptability of the model under diverse conditions. The results demonstrate that the tomato fruit detection accuracy improves when the domain of the training dataset contains the test environment. The quantitative results showed high interoperability, achieving an average accuracy (AP₅₀) of 0.973 in the same greenhouse and a stable performance of 0.962 in another greenhouse. The imaging approach controlled the lighting conditions, effectively eliminating the domain-shift problem. However, training on a dataset with low diversity or inferring plant appearance images but not on the training dataset decreased the average accuracy to approximately 0.80, revealing the need for new approaches to overcome fruit occlusion. Importantly, these findings have practical implications for the application of automated tomato fruit set monitoring systems in greenhouses to enhance agricultural efficiency and productivity.

The scale of horticultural facilities in Japan is expanding, making the efficient management of labor costs essential, particularly in large-scale tomato production. This study developed a consistent and practical system for predicting harvest working time and estimating the quantity and weight of harvested fruit using panoramic images of cultivation rows. The system integrates a deep learning model, the Mask ResNet-50 convolutional neural network, to count harvestable fruits from images and a predictive algorithm to estimate working time based on the fruit count. The results indicated that the average for all workers could be predicted with an error margin of 30.1% when predicted three days before the harvest date and 15.6% when predicted on the harvest date. The trial also revealed that the accuracy of the predictions varied based on workers’ experience and cultivation methods. This study highlights the system’s potential to optimize harvesting plans and labor allocation, providing a novel tool for reducing labor costs while maintaining efficiency in large-scale tomato greenhouse production.

In our previous study, we developed a monitoring system for automatically counting tomatoes produced in protected horticulture using deep learning–based object detection. In this study, we adapted the system for sweet peppers and developed a monitoring system tailored to this crop. We evaluated its fruit detection and counting performance in a large-scale commercial greenhouse. Furthermore, we investigated the relationship between fruit counts at different ripeness stages and the total yield in the cultivation area, and we assessed the accuracy when predicting the yield for the following week. The results confirmed that the system maintained a stable fruit detection performance throughout the trial, and that its outputs were reliable enough to indicate its potential to replace manual counting. In addition, the average number of fruits at the 1–40% and 41–80% ripeness stages across six planting rows showed a correlation with the total weekly yield in the entire 0.6 ha cultivation area the following week. A yield prediction model using average fruit counts at these two ripeness stages as explanatory variables achieved a WAPE of 21.35%, indicating that the monitoring system is effective for yield prediction.

Accurate estimation of the leaf area index (LAI), a key indicator of canopy development and light interception, is essential for improving productivity in greenhouse tomato cultivation. This study presents a non-destructive LAI estimation method using side-view images captured by a vertical scanning system. The system recorded the full vertical profile of tomato plants grown under two deleafing strategies: modifying leaf height (LH) and altering leaf density (LD). Vegetative and leaf areas were extracted using color-based masking and semantic segmentation with the Segment Anything Model (SAM), a general-purpose deep learning tool. Regression models based on leaf or all vegetative pixel counts showed strong correlations with destructively measured LAI, particularly under LH conditions (R² > 0.85; mean absolute percentage error ≈ 16%). Under LD conditions, accuracy was slightly lower due to occlusion and leaf orientation. Compared with prior 3D-based methods, the proposed 2D approach achieved comparable accuracy while maintaining low cost and a labor-efficient design. However, the system has not been tested in real production, and its generalizability across cultivars, environments, and growth stages remains unverified. This proof-of-concept study highlights the potential of side-view imaging for LAI monitoring and calls for further validation and integration of leaf count estimation.

Fruit instance segmentation models are widely researched for inference tasks such as yield prediction and automated harvesting. Previous studies evaluated these models only on the basis of mask average precision; they overlooked segmentation quality and confidence score reliability—both crucial for inference tasks. This study proposes an evaluation method that incorporates, in addition to mask average precision, the Aggregated Jaccard Index to assess segmentation quality and the coefficient of determination between confidence scores and Intersection over Union for reliability evaluation. We compared YOLO11, Mask R-CNN, and their improved variants using a dataset that included stable and comprehensive imaging obtained by monitoring equipment in a large-scale commercial paprika greenhouse. Results show that mask scoring R-CNN excels in segmentation quality, while YOLO11 performs better in mask average precision and confidence score reliability. These findings suggest that when evaluating instance segmentation models for real-world application scenarios, we should not rely solely on mask average precision, but a combination of multiple metrics that assess different aspects of the model must be utilized.