Kota Shimomoto
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Kota Shimomoto has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Hiroki Naito
Graduate School of Agricultural and Life Sciences, the University of Tokyo, 1-1-1 Yayoi, Bunkyo, Tokyo 113-8657, Japan
6 shared publications Hiroshige Nishina
Department of Food Production Science, Graduate School of Agriculture, Ehime University
5 shared publicationsKotaro Takayama
Department of Food Production Science, Graduate School of Agriculture, Ehime University
5 shared publications- Tokihiro Fukatsu
The Institute of Agricultural Machinery, National Agriculture and Food Research Organization, Tsukuba 3050856, Japan
5 shared publications - Fumiki Hosoi
Graduate School of Agricultural and Life Sciences, the University of Tokyo, 1-1-1 Yayoi, Bunkyo, Tokyo 113-8657, Japan
3 shared publications Kazue Inaba
The United Graduate School of Agricultural Sciences, Ehime University
3 shared publications
Latest Publications
- Open Access
- 1 July 2025
- Published by MDPI AG in Agriengineering
- Vol. 7 (7) , 206
Leaf Area Estimation in High-Wire Tomato Cultivation Using Plant Body Scanning
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.
- 1 July 2025
- Published by MDPI AG in Agriengineering
- Vol. 7 (7) , 206
Open AccessLeaf Area Estimation in High-Wire Tomato Cultivation Using Plant Body Scanning
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.
- Open Access
- 20 June 2025
- Published by MDPI AG in Horticulturae
- Vol. 11 (7) , 718
Predicting Sweet Pepper Yield Based on Fruit Counts at Multiple Ripeness Stages Monitored by an AI-Based System Mounted on a Pipe-Rail Trolley
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.
- 20 June 2025
- Published by MDPI AG in Horticulturae
- Vol. 11 (7) , 718
Open AccessPredicting Sweet Pepper Yield Based on Fruit Counts at Multiple Ripeness Stages Monitored by an AI-Based System Mounted on a Pipe-Rail Trolley
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.
- Open Access
- 13 May 2025
- Published by MDPI AG in Horticulturae
- Vol. 11 (5) , 525
Comprehensive Evaluation of Paprika Instance Segmentation Models Based on Segmentation Quality and Confidence Score Reliability
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.
- 13 May 2025
- Published by MDPI AG in Horticulturae
- Vol. 11 (5) , 525
Open AccessComprehensive Evaluation of Paprika Instance Segmentation Models Based on Segmentation Quality and Confidence Score Reliability
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.
- 1 April 2025
- Published by International Society for Horticultural Science (ISHS) in Acta Horticulturae
- No. 1426,p. 355-360
Development of double-camera AI system for efficient monitoring of paprika fruits
ISHS International Symposium on New Technologies for Sustainable Greenhouse Systems: GreenSys2023 Development of double-camera AI system for efficient monitoring of paprika fruits
- 1 April 2025
- Published by International Society for Horticultural Science (ISHS) in Acta Horticulturae
- No. 1426,p. 355-360
Development of double-camera AI system for efficient monitoring of paprika fruits
ISHS International Symposium on New Technologies for Sustainable Greenhouse Systems: GreenSys2023 Development of double-camera AI system for efficient monitoring of paprika fruits
- Open Access
- 1 January 2025
- Published by Asian Agricultural and Biological Engineering Association in Engineering in Agriculture, Environment and Food
- Vol. 18 (1) , 23-31
Development of an AI-based fruit monitoring system with a focus illumination unit for tomatoes grown in greenhouse horticulture
The objective of this study is to develop an AI-based fruit monitoring system to address the issue of image background noise when automatically counting tomatoes grown in greenhouse horticulture. The system consists of a scanning device and a rail-guided vehicle. This system creates a panoramic image of the crop canopy and automatically counts the number of fruits using deep learning-based fruit detection model (Mask R-CNN). A focused illumination unit on our scanning device creates a light-dark contrast between the near and far sides of the camera, removing unnecessary objects from the background of the images. We applied our system to detect tomato fruits grown in an experimental greenhouse and successfully achieved good performance (AP50 = 0.95).
- 1 January 2025
- Published by Asian Agricultural and Biological Engineering Association in Engineering in Agriculture, Environment and Food
- Vol. 18 (1) , 23-31
Open AccessDevelopment of an AI-based fruit monitoring system with a focus illumination unit for tomatoes grown in greenhouse horticulture
The objective of this study is to develop an AI-based fruit monitoring system to address the issue of image background noise when automatically counting tomatoes grown in greenhouse horticulture. The system consists of a scanning device and a rail-guided vehicle. This system creates a panoramic image of the crop canopy and automatically counts the number of fruits using deep learning-based fruit detection model (Mask R-CNN). A focused illumination unit on our scanning device creates a light-dark contrast between the near and far sides of the camera, removing unnecessary objects from the background of the images. We applied our system to detect tomato fruits grown in an experimental greenhouse and successfully achieved good performance (AP50 = 0.95).
- Open Access
- 10 December 2024
- Published by MDPI AG in Agriculture
- Vol. 14 (12) , 2257
Accuracy Assessment of Tomato Harvest Working Time Predictions from Panoramic Cultivation Images
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.
- 10 December 2024
- Published by MDPI AG in Agriculture
- Vol. 14 (12) , 2257
Open AccessAccuracy Assessment of Tomato Harvest Working Time Predictions from Panoramic Cultivation Images
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.
- Open Access
- 19 June 2024
- Published by MDPI AG in Agriengineering
- Vol. 6 (2) , 1827-1846
Interoperability Analysis of Tomato Fruit Detection Models for Images Taken at Different Facilities, Cultivation Methods, and Times of the Day
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.
- 19 June 2024
- Published by MDPI AG in Agriengineering
- Vol. 6 (2) , 1827-1846
Open AccessInteroperability Analysis of Tomato Fruit Detection Models for Images Taken at Different Facilities, Cultivation Methods, and Times of the Day
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.
- 1 January 2022
- Published by Japanese Society of Agricultural, Biological and Environmental Engineers and Scientists in Environmental Control in Biology
- Vol. 60 (1) , 13-21
Method to Calculate Net CO2 Exchange Rate of Whole Plants under Continuously Increasing or Decreasing CO2 Concentrations in a Greenhouse Using a Real-time Photosynthesis and Transpiration Monitoring System
We developed an open-chamber system to monitor photosynthesis and transpiration of whole plants with high time resolution. The system may be promising for environmental controls based on plant stress diagnoses; however, the conventional method used to calculate net CO2 exchange rate (NCER) should be improved to avoid overestimation and underestimation of NCER under greenhouse conditions. To calculate NCER, the conventional method uses the difference in CO2 concentration between inlet and outlet air of the open-chamber system. The CO2 concentrations are alternately recorded by a single sensor every 5 min. With this method, inherently delayed response of outlet CO2 concentration causes overestimation and underestimation of NCER especially when CO2 concentration in a greenhouse continuously increases or decreases. We developed a calculation method considering the number of air exchanges, and then compared the NCER calculated with the new method (NCERex) to that calculated with the conventional method (NCERconv). During the night, when the CO2 concentration in the greenhouse continuously increased, NCERex (with the average NCERexs being -0.78, -0.71, and -0.96 μmol s-1 at different timeframes) was lower than NCERconv (with the average NCERconvs being -0.30, -0.32, and -0.65 μmol s-1). The higher values of NCERconv indicated overestimation by the conventional calculation method during the night. The total amount of night respiration calculated using NCERex was 2.2 times greater than that calculated using NCERconv. The new calculation method is useful to measure the NCER of whole plants validly under greenhouse conditions.
- 1 January 2022
- Published by Japanese Society of Agricultural, Biological and Environmental Engineers and Scientists in Environmental Control in Biology
- Vol. 60 (1) , 13-21
Method to Calculate Net CO2 Exchange Rate of Whole Plants under Continuously Increasing or Decreasing CO2 Concentrations in a Greenhouse Using a Real-time Photosynthesis and Transpiration Monitoring System
We developed an open-chamber system to monitor photosynthesis and transpiration of whole plants with high time resolution. The system may be promising for environmental controls based on plant stress diagnoses; however, the conventional method used to calculate net CO2 exchange rate (NCER) should be improved to avoid overestimation and underestimation of NCER under greenhouse conditions. To calculate NCER, the conventional method uses the difference in CO2 concentration between inlet and outlet air of the open-chamber system. The CO2 concentrations are alternately recorded by a single sensor every 5 min. With this method, inherently delayed response of outlet CO2 concentration causes overestimation and underestimation of NCER especially when CO2 concentration in a greenhouse continuously increases or decreases. We developed a calculation method considering the number of air exchanges, and then compared the NCER calculated with the new method (NCERex) to that calculated with the conventional method (NCERconv). During the night, when the CO2 concentration in the greenhouse continuously increased, NCERex (with the average NCERexs being -0.78, -0.71, and -0.96 μmol s-1 at different timeframes) was lower than NCERconv (with the average NCERconvs being -0.30, -0.32, and -0.65 μmol s-1). The higher values of NCERconv indicated overestimation by the conventional calculation method during the night. The total amount of night respiration calculated using NCERex was 2.2 times greater than that calculated using NCERconv. The new calculation method is useful to measure the NCER of whole plants validly under greenhouse conditions.
- 1 July 2021
- Published by Japanese Society of Agricultural, Biological and Environmental Engineers and Scientists in Environmental Control in Biology
- Vol. 59 (3) , 107-115
Averaging Techniques in Processing the High Time-resolution Photosynthesis Data of Cherry Tomato Plants for Model Development
We evaluated averaging techniques in data processing for the estimation of canopy net photosynthetic rates (Pn) of two cherry tomato plants using a multiple linear regression analysis with variables of aerial environmental factors. Whole canopy Pn and the environmental factors were measured in a high time resolution with a 5-minute interval under a commercial greenhouse by using a novel photosynthesis chamber. We processed the data by using a moving average (MA) and simple average (SA) with several time frames (30-minute, 1-hour, 2-hour). The canopy Pn was expressed as a general linear function of PAR irradiance (I), air temperature (T), relative humidity (RH), vapor pressure deficit (VPD), and CO2 concentration (C). Model accuracy generally increased with longer time frames; however, it can be varied depending on the datasets and the variables used in the models. The 2-hour-SA datasets gave the best accuracy for both 5-variable model (I, T, RH, VPD, C) and 3-variable model (I, VPD, C) with R2 of 0.81 and 0.67, respectively. This study indicates that datasets of 2-hour time frame with simple average are promising to make a practical general linear regression model for the estimation of Pn of cherry tomato by using the high time-resolution Pn data.
- 1 July 2021
- Published by Japanese Society of Agricultural, Biological and Environmental Engineers and Scientists in Environmental Control in Biology
- Vol. 59 (3) , 107-115
Averaging Techniques in Processing the High Time-resolution Photosynthesis Data of Cherry Tomato Plants for Model Development
We evaluated averaging techniques in data processing for the estimation of canopy net photosynthetic rates (Pn) of two cherry tomato plants using a multiple linear regression analysis with variables of aerial environmental factors. Whole canopy Pn and the environmental factors were measured in a high time resolution with a 5-minute interval under a commercial greenhouse by using a novel photosynthesis chamber. We processed the data by using a moving average (MA) and simple average (SA) with several time frames (30-minute, 1-hour, 2-hour). The canopy Pn was expressed as a general linear function of PAR irradiance (I), air temperature (T), relative humidity (RH), vapor pressure deficit (VPD), and CO2 concentration (C). Model accuracy generally increased with longer time frames; however, it can be varied depending on the datasets and the variables used in the models. The 2-hour-SA datasets gave the best accuracy for both 5-variable model (I, T, RH, VPD, C) and 3-variable model (I, VPD, C) with R2 of 0.81 and 0.67, respectively. This study indicates that datasets of 2-hour time frame with simple average are promising to make a practical general linear regression model for the estimation of Pn of cherry tomato by using the high time-resolution Pn data.
- Open Access
- 1 January 2021
- Published by Society of Agricultural Meteorology of Japan in Journal of Agricultural Meteorology
- Vol. 77 (4) , 270-277
Comparison of photosynthetic rates, transpiration rates, and total conductance of greenhouse-grown tomato plants measured with two open chambers with different ventilation rates
A real-time monitoring system was developed and applied to monitor the time course of photosynthesis and transpiration in fully-grown tomato plants in a semi-commercial greenhouse. The system was based on an open chamber method in which the ventilator airflow rate is an important parameter affecting the environmental factors in the chamber and physiological response of plants enclosed inside the chamber. So, we assumed that the effects of this parameter on these responses should be evaluated for an agricultural production site. In this study, we investigated differences in the environmental factors in the chamber and physiological response of whole-tomato plants obtained from two chambers (0.5 m [W]×1.0 m [D]×2.2 m [H]) implemented with a single ventilator (SV, 0.36 m3 min-1) or double ventilators (DV, 0.72 m3 min-1). The relative humidity and vapor pressure deficit inside the SV chamber were about 10% higher and 0.5 kPa lower than those inside the DV chamber because of the difference in air exchange rates. However, we found no significant effect of airflow rate on net photosynthetic rate, transpiration rate and total conductance of the plants in the SV and DV chambers by analyzing with weighted Deming regression. This simultaneous monitoring method, undertaken in multiple chambers, and weighted Deming regression analysis can be used to check whether measurement conditions are appropriate for on-site monitoring.
- 1 January 2021
- Published by Society of Agricultural Meteorology of Japan in Journal of Agricultural Meteorology
- Vol. 77 (4) , 270-277
Open AccessComparison of photosynthetic rates, transpiration rates, and total conductance of greenhouse-grown tomato plants measured with two open chambers with different ventilation rates
A real-time monitoring system was developed and applied to monitor the time course of photosynthesis and transpiration in fully-grown tomato plants in a semi-commercial greenhouse. The system was based on an open chamber method in which the ventilator airflow rate is an important parameter affecting the environmental factors in the chamber and physiological response of plants enclosed inside the chamber. So, we assumed that the effects of this parameter on these responses should be evaluated for an agricultural production site. In this study, we investigated differences in the environmental factors in the chamber and physiological response of whole-tomato plants obtained from two chambers (0.5 m [W]×1.0 m [D]×2.2 m [H]) implemented with a single ventilator (SV, 0.36 m3 min-1) or double ventilators (DV, 0.72 m3 min-1). The relative humidity and vapor pressure deficit inside the SV chamber were about 10% higher and 0.5 kPa lower than those inside the DV chamber because of the difference in air exchange rates. However, we found no significant effect of airflow rate on net photosynthetic rate, transpiration rate and total conductance of the plants in the SV and DV chambers by analyzing with weighted Deming regression. This simultaneous monitoring method, undertaken in multiple chambers, and weighted Deming regression analysis can be used to check whether measurement conditions are appropriate for on-site monitoring.