Search

Automatic fruit counting systems have garnered interest from farmers and agronomists to monitor fruit production, predict yields in advance, and identify production variability across orchards. However, accurately counting fruits poses challenges, particularly due to occlusions. This study proposes a multi-view sensing approach using continuous motion videos captured by a camera moved along the row of trees, followed by fruit detection in all video frames and application of Multi-Object Tracking (MOT) algorithms to prevent double-counting. Three tracking methods, namely SORT, DeepSORT, and ByteTrack, are compared for fruit counting using the YOLOv5x object detector. The methodology is applied to map fruit production in an experimental apple orchard at two different dates: four weeks and one week before harvest. The results demonstrate that ByteTrack (MOTA=0.682; IDF1=0.837; HOTA=0.689) outperforms SORT and DeepSORT, indicating its superior tracking performance. Computational efficiency analysis reveals similar processing times between SORT and ByteTrack (about 15 ms), while DeepSORT requires significantly more processing time per image (128 ms). Fruit counting evaluation shows reasonably accurate yield predictions on both dates, with reduced errors and improved performance closer to the harvest date (MAPE=7.47 %; R2=0.70). The system proves effective in estimating orchard fruit production using computer vision technology, offering valuable insights for yield forecasting. These findings contribute to optimizing fruit production and supporting precision agriculture practices. The code and the dataset have been made publicly available and a video visualization of results is accessible at http://www.grap.udl.cat/en/publications/video_fruit_counting., This work was partly funded by the Departament de Recerca i Universitats de la Generalitat de Catalunya (grant 2021 LLAV 00088), the Spanish Ministry of Science, Innovation and Universities (grants RTI2018-094222-B-I00 [PAgFRUIT project], PID2021-126648OB-I00 [PAgPROTECT project] and PID2020-117142GB-I00 [DeeLight project] by MCIN/AEI/10.13039/501100011033 and by “ERDF, a way of making Europe”, by the European Union). The work of Jordi Gené Mola was supported by the Spanish Ministry of Universities through a Margarita Salas postdoctoral grant funded by the European Union - NextGenerationEU. The Secretariat of Universities and Research of the Department of Business and Knowledge of the Generalitat de Catalunya and European Social Fund (ESF) are also thanked for financing Juan Carlos Miranda’s predoctoral fellowship (2020 FI_B 00586)., Peer Reviewed, Postprint (author's final draft)

There is a growing body of literature that recognises the importance of UAVs in precision agriculture tasks. Currently, flowering thinning tasks in orchard management rely on the decisions derived from time-consuming manual flower cluster counting in the field by an agrotechnician. Yet it is hard to guarantee the counting accuracy due to numerous human factors. The present dataset contains UAV images during the full blooming period of an apple orchard for three consecutive years, 2018, 2019, and 2020. It is directly linked to a research article entitled “Feasibility assessment of tree-level flower intensity quantification from UAV RGB imagery: A triennial study in an apple orchard”. The data collection site was an apple orchard located at Randwijk, Overbetuwe, The Netherlands (51.938, 5.7068 in WGS84 UTM 31U). Moreover, the flower cluster number and floridity ground truth are also provided in one row from the orchard. The UAV flights were conducted with different flying altitudes, camera resolutions, and lighting conditions. This dataset aims to support researchers focussing on remote sensing, machine vision, deep learning, and image classification, and the stakeholders interested in precision horticulture and orchard management. It can be used for flowering intensity estimation and prediction, and spatial and temporal flowering variability mapping by using digital photogrammetry and 3D reconstruction.

The present dataset contains UAV images during the full blooming period of an apple orchard for three consecutive years, 2018, 2019, and 2020. It is directly linked to a research article entitled “Feasibility assessment of tree-level flower intensity quantification from UAV RGB imagery: A triennial study in an apple orchard”. The data collection site was an apple orchard located at Randwijk, Overbetuwe, The Netherlands (51.938, 5.7068 in WGS84 UTM 31U). This dataset aims to support researchers focussing on remote sensing, machine vision, deep learning, and image classification, and the stakeholders interested in precision horticulture and orchard management. It can be used for flowering intensity estimation and prediction, and spatial and temporal flowering variability mapping by using digital photogrammetry and 3D reconstruction

The present dataset contains colour images acquired in a commercial Fuji apple orchard (Malus domestica Borkh. cv. Fuji) to reconstruct the 3D model of 11 trees by using structure-from-motion (SfM) photogrammetry. The data provided in this article is related to the research article entitled “Fruit detection and 3D location using instance segmentation neural networks and structure-from-motion photogrammetry” [1]. The Fuji-SfM dataset includes: (1) a set of 288 colour images and the corresponding annotations (apples segmentation masks) for training instance segmentation neural networks such as Mask-RCNN; (2) a set of 582 images defining a motion sequence of the scene which was used to generate the 3D model of 11 Fuji apple trees containing 1455 apples by using SfM; (3) the 3D point cloud of the scanned scene with the corresponding apple positions ground truth in global coordinates. With that, this is the first dataset for fruit detection containing images acquired in a motion sequence to build the 3D model of the scanned trees with SfM and including the corresponding 2D and 3D apple location annotations. This data allows the development, training, and test of fruit detection algorithms either based on RGB images, on coloured point clouds or on the combination of both types of data., This work was partly funded by the Secretaria d'Universitats i Recerca del Departament d'Empresa i Coneixement de la Generalitat de Catalunya (grant 2017 SGR 646), the Spanish Ministry of Economy and Competitiveness (project AGL2013-48297-C2-2-R) and the Spanish Ministry of Science, Innovation and Universities (project RTI2018-094222-B-I00). Part of the work was also developed within the framework of the project TEC2016-75976-R, financed by the Spanish Ministry of Economy, Industry and Competitiveness and the European Regional Development Fund (ERDF). The Spanish Ministry of Education is thanked for Mr. J. Gené’s pre-doctoral fellowships (FPU15/03355). We would also like to thank Nufri (especially Santiago Salamero and Oriol Morreres) and Vicens Maquinària Agrícola S.A. for their support during data acquisition, and Ernesto Membrillo and Roberto Maturino for their support in dataset labelling., Peer Reviewed, Postprint (published version)

In Anbetracht des Kompromisses zwischen der Erzielung des höchsten Gewinns und der geringsten Umweltbelastung ist ein tiefes Verständnis der ökonomischen Folgen der Stickstoff (N) Düngung erforderlich. Die vorliegende Doktorarbeit liefert umfassende Einblicke in (i) die Auswirkungen des standortspezifischen N-Managements (SSNM) auf die Rentabilität und Risikominderung, (ii) die Auswirkungen von Unsicherheiten und Risikoeinflüssen auf optimale N-Düngergaben und (iii) das Potenzial und die Kosten der Vermeidung von Treibhausgas (THG) Emissionen durch N-Düngereduktion. Ein Modellierungsansatz wurde entwickelt, um die Wirkung von Ertrag und Proteingehalt, Wirtschafts- und Risikoauswirkungen sowie THG-Emissionen auf die N-Düngung zu simulieren. Die Ergebnisse der Arbeit zeigen, dass SSNM die Wirtschaftlichkeit verbessert, indem es eine höhere Weizenqualität und damit Preisprämien erzielt. SSNM reduziert das Risiko, die Backqualität nicht zu erreichen, und es gibt keine wesentlichen Nachteile beim Verlustrisikomanagement im Vergleich zum einheitlichen Management. Preisprämien für eine höhere Weizenqualität bieten Anreize für höhere N-Düngergaben. Prämien verflachen die Gewinnfunktion weiter, was unzureichende Argumente für eine Absenkung des N-Inputs aus der Wirtschaftlichkeitssicht liefert, selbst bei einer hohen Risikoaversion der Landwirte. Eine moderate Reduzierung der mineralischen N-Düngung kann die THG-Emissionen bei moderaten Opportunitätskosten mindern. Die THG-Vermeidung durch N-Düngereduktion in einer bestimmten Region kann unter Berücksichtigung kultur- und ertragszonenspezifischer Ertragswirkungen optimiert werden. Insgesamt liefert diese Arbeit wichtige Erkenntnisse über die Chancen und Nachteile der Anpassung der N-Düngergaben. Darüber hinaus leistet sie einen direkten Beitrag zur Identifizierung von kosten- und risikoeffizienten N-Managementoptionen und bildet die Grundlage für effektive politische Ansätze zur THG-Vermeidung durch selektive N-Düngereduktio, Considering the tradeoff between achieving the highest profit and causing the lowest environmental impact, there is a need for a profound understanding of the economic consequences of nitrogen (N) fertilizer application. The present doctoral research provides comprehensive insights into (i) effects of site-specific N management (SSNM) on profitability and risk mitigation; (ii) impacts of uncertainties and risk implications on optimal N fertilizer rates; and (iii) potential and costs of mitigating greenhouse gas (GHG) emissions by N fertilizer reduction. A modelling approach was developed to simulate the response of yield, protein, economic and risk implications, and GHG emissions to N fertilizer application. Findings of the thesis show that SSNM improves profitability by achieving higher grain quality, thus, price premiums. SSNM reduces the risk of not reaching the baking grain quality and poses no considerable disadvantage on downside risk management compared to uniform management. Price premiums for higher wheat quality provide incentives for higher N input rates. Premiums further flatten the profit function, giving insufficient arguments for lowering N input from a farm profitability perspective, even in presence of high risk aversion of farmers. Moderate reduction of mineral N fertilizer can mitigate GHG emissions at moderate opportunity costs. GHG mitigation by N fertilizer reduction in a given region can be optimized considering crop and yield-zone-specific yield responses. Overall, this thesis provides important insights on chances and drawbacks of adjusting N fertilizer rates. Moreover, it makes a direct contribution in identifying cost- and risk-efficient N management options and provides a basis for effective policy approaches to reduce GHG emissions by selective N fertilizer reduction.

In Anbetracht des Kompromisses zwischen der Erzielung des höchsten Gewinns und der geringsten Umweltbelastung ist ein tiefes Verständnis der ökonomischen Folgen der Stickstoff (N) Düngung erforderlich. Die vorliegende Doktorarbeit liefert umfassende Einblicke in (i) die Auswirkungen des standortspezifischen N-Managements (SSNM) auf die Rentabilität und Risikominderung, (ii) die Auswirkungen von Unsicherheiten und Risikoeinflüssen auf optimale N-Düngergaben und (iii) das Potenzial und die Kosten der Vermeidung von Treibhausgas (THG) Emissionen durch N-Düngereduktion. Ein Modellierungsansatz wurde entwickelt, um die Wirkung von Ertrag und Proteingehalt, Wirtschafts- und Risikoauswirkungen sowie THG-Emissionen auf die N-Düngung zu simulieren. Die Ergebnisse der Arbeit zeigen, dass SSNM die Wirtschaftlichkeit verbessert, indem es eine höhere Weizenqualität und damit Preisprämien erzielt. SSNM reduziert das Risiko, die Backqualität nicht zu erreichen, und es gibt keine wesentlichen Nachteile beim Verlustrisikomanagement im Vergleich zum einheitlichen Management. Preisprämien für eine höhere Weizenqualität bieten Anreize für höhere N-Düngergaben. Prämien verflachen die Gewinnfunktion weiter, was unzureichende Argumente für eine Absenkung des N-Inputs aus der Wirtschaftlichkeitssicht liefert, selbst bei einer hohen Risikoaversion der Landwirte. Eine moderate Reduzierung der mineralischen N-Düngung kann die THG-Emissionen bei moderaten Opportunitätskosten mindern. Die THG-Vermeidung durch N-Düngereduktion in einer bestimmten Region kann unter Berücksichtigung kultur- und ertragszonenspezifischer Ertragswirkungen optimiert werden. Insgesamt liefert diese Arbeit wichtige Erkenntnisse über die Chancen und Nachteile der Anpassung der N-Düngergaben. Darüber hinaus leistet sie einen direkten Beitrag zur Identifizierung von kosten- und risikoeffizienten N-Managementoptionen und bildet die Grundlage für effektive politische Ansätze zur THG-Vermeidung durch selektive N-Düngereduktio, Considering the tradeoff between achieving the highest profit and causing the lowest environmental impact, there is a need for a profound understanding of the economic consequences of nitrogen (N) fertilizer application. The present doctoral research provides comprehensive insights into (i) effects of site-specific N management (SSNM) on profitability and risk mitigation; (ii) impacts of uncertainties and risk implications on optimal N fertilizer rates; and (iii) potential and costs of mitigating greenhouse gas (GHG) emissions by N fertilizer reduction. A modelling approach was developed to simulate the response of yield, protein, economic and risk implications, and GHG emissions to N fertilizer application. Findings of the thesis show that SSNM improves profitability by achieving higher grain quality, thus, price premiums. SSNM reduces the risk of not reaching the baking grain quality and poses no considerable disadvantage on downside risk management compared to uniform management. Price premiums for higher wheat quality provide incentives for higher N input rates. Premiums further flatten the profit function, giving insufficient arguments for lowering N input from a farm profitability perspective, even in presence of high risk aversion of farmers. Moderate reduction of mineral N fertilizer can mitigate GHG emissions at moderate opportunity costs. GHG mitigation by N fertilizer reduction in a given region can be optimized considering crop and yield-zone-specific yield responses. Overall, this thesis provides important insights on chances and drawbacks of adjusting N fertilizer rates. Moreover, it makes a direct contribution in identifying cost- and risk-efficient N management options and provides a basis for effective policy approaches to reduce GHG emissions by selective N fertilizer reduction.

The present dataset contains colour images acquired in a commercial Fuji apple orchard (Malus domestica Borkh. cv. Fuji) to reconstruct the 3D model of 11 trees by using structure-from-motion (SfM) photogrammetry. The data provided in this article is related to the research article entitled “Fruit detection and 3D location using instance segmentation neural networks and structure-from-motion photogrammetry” [1]. The Fuji-SfM dataset includes: (1) a set of 288 colour images and the corresponding annotations (apples segmentation masks) for training instance segmentation neural networks such as Mask-RCNN; (2) a set of 582 images defining a motion sequence of the scene which was used to generate the 3D model of 11 Fuji apple trees containing 1455 apples by using SfM; (3) the 3D point cloud of the scanned scene with the corresponding apple positions ground truth in global coordinates. With that, this is the first dataset for fruit detection containing images acquired in a motion sequence to build the 3D model of the scanned trees with SfM and including the corresponding 2D and 3D apple location annotations. This data allows the development, training, and test of fruit detection algorithms either based on RGB images, on coloured point clouds or on the combination of both types of data., This work was partly funded by the Secretaria d'Universitats i Recerca del Departament d'Empresa i Coneixement de la Generalitat de Catalunya (grant 2017 SGR 646), the Spanish Ministry of Economy and Competitiveness (project AGL2013-48297-C2-2-R) and the Spanish Ministry of Science, Innovation and Universities (project RTI2018-094222-B-I00). Part of the work was also developed within the framework of the project TEC2016-75976-R, financed by the Spanish Ministry of Economy, Industry and Competitiveness and the European Regional Development Fund (ERDF). The Spanish Ministry of Education is thanked for Mr. J. Gené’s pre-doctoral fellowships (FPU15/03355). We would also like to thank Nufri (especially Santiago Salamero and Oriol Morreres) and Vicens Maquinària Agrícola S.A. for their support during data acquisition, and Ernesto Membrillo and Roberto Maturino for their support in dataset labelling., Peer Reviewed, Postprint (published version)

Currently, industry standard yield predictions in viticulture are generated by manual sampling of the weight and number of components such as bunches and berries. The data collection takes significant time and despite requiring trained labour still results in inaccurate yield estimates which in turn lead ton substantial inefficiencies in scheduling and logistics through the entire wine industry supply chain.Therefore, this thesis introduces an automated visual yield estimation system using computer vision and data mining with the aim of improving crop estimation. Firstly, a biological baseline for yield estimation is proposed and implemented together with novel algorithms for shoot and bunch detection. A method for transforming the object counts extracted from videos of individual rows to a prediction of crop yield without requiring GPS is introduced, with the additional benefit of generating a production variation map during the season. In addition, a novel fully automated 3D bunch reconstruction algorithm has been developed which is based on a single input image to assist berry counting in vivo.Shoot detection using only a low-cost camera (GoPro) was achieved using a combination of a novel unsupervised dynamic feature selection procedure and unsupervised clustering and shown to be robust to varying light conditions, multiple varieties and shoot densities. Bunch detection was achieved using an SVM classifier including the introduction of two novel features and shown to outperform existing approaches. The bunch reconstruction algorithm achieved an accuracy of 13-15% across multiple cultivars at multiple stages of maturity. The shoot detection algorithm was used to generate yield forecasts which were within 15% of the final fruit tonnage delivered to the winery, despite being calculated five months prior to harvest.The overall automated visual yield estimation system has thus been demonstrated to be feasible and to reduce the error and cost associated with existing m

Precision agriculture is a management approach for sustainable agriculture. It can be applied even in small fields. It aims to optimize inputs, improve profits, and reduce adverse environmental impacts. In this study, a series of measurements were conducted over three growing seasons to assess variability in a 0.55 ha pear orchard located in central Greece. Soil ECa was measured using EM38 sensor, while soil samples were taken from a grid 17 × 8 m and analysed for texture, pH, P, K, Mg, CaCO3, and organic matter content. Data analysis indicated that most of the nutrients were at sufficient levels. Soil and yield maps showed considerable variability while fruit quality presented small variations across the orchard. Yield fluctuations were observed, possibly due to climatic conditions. Prescription maps were developed for nitrogen variable rate application (VRA) for two years based on the replacement of the nutrients removed by the crop. VRA application resulted in 56% and 50% reduction of N fertiliser compared to uniform application.

Precision agriculture is a management approach for sustainable agriculture. It can be applied even in small fields. It aims to optimize inputs, improve profits, and reduce adverse environmental impacts. In this study, a series of measurements were conducted over three growing seasons to assess variability in a 0.55 ha pear orchard located in central Greece. Soil ECa was measured using EM38 sensor, while soil samples were taken from a grid 17 × 8 m and analysed for texture, pH, P, K, Mg, CaCO3, and organic matter content. Data analysis indicated that most of the nutrients were at sufficient levels. Soil and yield maps showed considerable variability while fruit quality presented small variations across the orchard. Yield fluctuations were observed, possibly due to climatic conditions. Prescription maps were developed for nitrogen variable rate application (VRA) for two years based on the replacement of the nutrients removed by the crop. VRA application resulted in 56% and 50% reduction of N fertiliser compared to uniform application.

Sensors, communication systems and geo-reference units are required to achieve an optimized management of agricultural inputs with respect to the economic and environmental aspects of olive groves. In this study, three commercial olive harvesters were tracked in Spain and Chile using remote and autonomous equipment to determine their time efficiency and field capacity. An experimental methodology for analyzing the data to determine the field capacity and efficiency is proposed, which, along with a conventional methodology, was used to analyze the data to determine field capacity and efficiency. The results of both methodologies are compared to validate the suitability of the experimental methodology. Furthermore, a yield monitor was developed and evaluate using one of the tested olive harvesters. The results show that yield monitoring of olives is possible, but further research is needed to archieve a more reliable methodology.

Sensors, communication systems and geo-reference units are required to achieve an optimized management of agricultural inputs with respect to the economic and environmental aspects of olive groves. In this study, three commercial olive harvesters were tracked in Spain and Chile using remote and autonomous equipment to determine their time efficiency and field capacity. An experimental methodology for analyzing the data to determine the field capacity and efficiency is proposed, which, along with a conventional methodology, was used to analyze the data to determine field capacity and efficiency. The results of both methodologies are compared to validate the suitability of the experimental methodology. Furthermore, a yield monitor was developed and evaluate using one of the tested olive harvesters. The results show that yield monitoring of olives is possible, but further research is needed to archieve a more reliable methodology.

Sensors, communication systems and geo-reference units are required to achieve an optimized management of agricultural inputs with respect to the economic and environmental aspects of olive groves. In this study, three commercial olive harvesters were tracked in Spain and Chile using remote and autonomous equipment to determine their time efficiency and field capacity. An experimental methodology for analyzing the data to determine the field capacity and efficiency is proposed, which, along with a conventional methodology, was used to analyze the data to determine field capacity and efficiency. The results of both methodologies are compared to validate the suitability of the experimental methodology. Furthermore, a yield monitor was developed and evaluate using one of the tested olive harvesters. The results show that yield monitoring of olives is possible, but further research is needed to archieve a more reliable methodology.

Sensors, communication systems and geo-reference units are required to achieve an optimized management of agricultural inputs with respect to the economic and environmental aspects of olive groves. In this study, three commercial olive harvesters were tracked in Spain and Chile using remote and autonomous equipment to determine their time efficiency and field capacity. An experimental methodology for analyzing the data to determine the field capacity and efficiency is proposed, which, along with a conventional methodology, was used to analyze the data to determine field capacity and efficiency. The results of both methodologies are compared to validate the suitability of the experimental methodology. Furthermore, a yield monitor was developed and evaluate using one of the tested olive harvesters. The results show that yield monitoring of olives is possible, but further research is needed to archieve a more reliable methodology.

Sensors, communication systems and geo-reference units are required to achieve an optimized management of agricultural inputs with respect to the economic and environmental aspects of olive groves. In this study, three commercial olive harvesters were tracked in Spain and Chile using remote and autonomous equipment to determine their time efficiency and field capacity. An experimental methodology for analyzing the data to determine the field capacity and efficiency is proposed, which, along with a conventional methodology, was used to analyze the data to determine field capacity and efficiency. The results of both methodologies are compared to validate the suitability of the experimental methodology. Furthermore, a yield monitor was developed and evaluate using one of the tested olive harvesters. The results show that yield monitoring of olives is possible, but further research is needed to archieve a more reliable methodology.

Die Getreideernte in den Industrieländern wird heute ausschließlich mit dem Mähdrescher durchgeführt. Durch eine gleichzeitige Ertragskartierung werden die Voraussetzungen für eine teilflächenspezifische Feldbewirtschaftung geschaffen. Aus den geokartierten Ertragsdaten lassen sich Rückschlüsse über kleinräumige Unterscheide in den Wachstumsbedingungen innerhalb eines Feldes ziehen. In der vorliegenden Arbeit werden die theoretischen Grundlagen zur Ertragskartierung und ein Verfahren zum Betrieb des Mähdreschers mit geokodierten Teilflächendaten entwickelt und untersucht. Zu deren Realisierung werden Module für die Erfassung, Übertragung, Verarbeitung und Umsetzung geokodierter Teilflächendaten benötigt.

Die Getreideernte in den Industrieländern wird heute ausschließlich mit dem Mähdrescher durchgeführt. Durch eine gleichzeitige Ertragskartierung werden die Voraussetzungen für eine teilflächenspezifische Feldbewirtschaftung geschaffen. Aus den geokartierten Ertragsdaten lassen sich Rückschlüsse über kleinräumige Unterscheide in den Wachstumsbedingungen innerhalb eines Feldes ziehen. In der vorliegenden Arbeit werden die theoretischen Grundlagen zur Ertragskartierung und ein Verfahren zum Betrieb des Mähdreschers mit geokodierten Teilflächendaten entwickelt und untersucht. Zu deren Realisierung werden Module für die Erfassung, Übertragung, Verarbeitung und Umsetzung geokodierter Teilflächendaten benötigt.