@article{Bono:2026, author = {Bono, Annaclaudia and Guaragnella, Cataldo}, year = {2026}, month = {03}, pages = {62-84}, title = {A perspective analysis of imaging-based monitoring systems in precision viticulture: Technologies, intelligent data analyses and research challenges}, volume = {16}, journal = {Artificial Intelligence in Agriculture}, doi = {10.1016/j.aiia.2025.08.001} } @article{Vineyard1:2025, author = {Sofia, Serena and Agosta, Martina and Asciuto, Antonio and Crescimanno, Maria and Galati, Antonino}, year = {2025}, month = {03}, pages = {1-28}, title = {Unleashing profitability of vineyards through the adoption of unmanned aerial vehicles technology systems: the case of two Italian wineries}, volume = {26}, journal = {Precision Agriculture}, doi = {10.1007/s11119-025-10236-2} } @article{DronesPA:2024, author = {Guebsi, Ridha and Mami, Sonia and Chokmani, Karem}, year = {2024}, month = {11}, pages = {686}, title = {Drones in Precision Agriculture: A Comprehensive Review of Applications, Technologies, and Challenges}, volume = {8}, journal = {Drones}, doi = {10.3390/drones8110686} } @article{DIMITRI2024e31648, title = {Precision agriculture for wine production: A machine learning approach to link weather conditions and wine quality}, journal = {Heliyon}, volume = {10}, number = {11}, pages = {e31648}, year = {2024}, issn = {2405-8440}, doi = {10.1016/j.heliyon.2024.e31648}, url = {https://www.sciencedirect.com/science/article/pii/S2405844024076795}, author = {Giovanna Maria Dimitri and Alberto Trambusti}, keywords = {Precision agriculture, Machine learning, Clustering, Wine production, Climate change}, abstract = {The agricultural sector, in particular viticulture, is highly susceptible to variations in the environment, crop conditions, and operational factors. Effectively managing these variables in the field necessitates observation, measurement, and responsive actions. Leveraging new technologies within the realm of precision agriculture, vineyards can enhance their long-term efficiency, productivity, and profitability. In our work we propose a novel analysis of the impact of pedoclimatic factors on wine, with a case study focusing on the Denomination of Controlled and Guaranteed Origin Chianti Classico (DOCG), a prime wine-producing region located in Tuscany, between the provinces of Siena and Florence. We first collected a novel dataset, where geographic information as well as wine quality information were collected, using publicly available sources. Using such geographic information retrieved and an unsupervised machine learning approach, we conducted an in-depth examination of pedoclimatic and production data. To collect the whole set of possibly relevant features, we first assessed the region's morphological attributes, including altitude, exposure, and slopes, while pinpointing individual wineries. Subsequently we then calculated crucial viticultural indices such as the Winkler, Huglin, Fregoni, and Freshness Index by utilizing daily temperature records from Chianti Classico, and we further related them to an assessment of wine quality. In addition to this, we designed and distributed a survey conducted among a sample of wineries situated in the Chianti Classico area, obtaining valuable insights into local data. The primary goal of this study is to elucidate the interrelationships between various parameters associated with the region, considering influential factors such as the environment, viticulture, and field operations that significantly impact wine production. By doing so, wineries could potentially unlock the full potential of their resources. In fact, through the unsupervised and correlation analysis we could elucidate the relationships existing between the pedoclimatic parameters of the region, considering the most important factors such as viticulture and field operations, and relate them to wine quality as for instance using the survey data collected. This study represents an unprecedent in the literature, and it could pave the path for future studies focusing on the importance of climatic factors into production and quality of wines.} } @article{UAVAI:2018, author = {Gambella, Filippo}, year = {2018}, month = {05}, pages = {}, title = {UAV and Artificial Intelligence in Precision Viticulture}, volume = {1}, journal = {JOJ Horticulture \& Arboriculture}, doi = {10.19080/JOJHA.2018.01.555569} } @article{Wang:2025, author = {Wang, Dashuai and Zhao, Minghu and Li, Zhuolin and Xu, Sheng and Wu, Xiaohu and Ma, Xuan and Liu, Xiaoguang}, year = {2025}, month = {03}, pages = {127477}, title = {A survey of unmanned aerial vehicles and deep learning in precision agriculture}, volume = {164}, journal = {European Journal of Agronomy}, doi = {10.1016/j.eja.2024.127477} } @article{Molnar:2025, author = {Molnár, Szilárd and Tamas, Levente}, year = {2025}, month = {01}, pages = {}, title = {Close proximity aerial image for precision viticulture. A review}, volume = {132}, journal = {Journal of Plant Diseases and Protection}, doi = {10.1007/s41348-024-01050-5} } @article{GALATI2025487, title = {Economics and barriers of precision viticulture technologies: A comprehensive systematic literature review}, journal = {Information Processing in Agriculture}, volume = {12}, number = {4}, pages = {487-500}, year = {2025}, issn = {2214-3173}, doi = {10.1016/j.inpa.2025.04.001}, url = {https://www.sciencedirect.com/science/article/pii/S2214317325000198}, author = {Antonino GALATI and Serena SOFIA and Maria CRESCIMANNO} } @Article{agronomy15112569, AUTHOR = {Vera-Esmeraldas, Adrián and Pizarro-Oteíza, Sebastián and Labbé, Mariela and Rojo, Francisco and Salazar, Fernando}, TITLE = {UAV-Based Spectral and Thermal Indices in Precision Viticulture: A Review of NDVI, NDRE, SAVI, GNDVI, and CWSI}, JOURNAL = {Agronomy}, VOLUME = {15}, YEAR = {2025}, NUMBER = {11}, ARTICLE-NUMBER = {2569}, URL = {https://www.mdpi.com/2073-4395/15/11/2569}, ISSN = {2073-4395}, DOI = {10.3390/agronomy15112569} } @article{IoTinPV, author = {Pascoal, David and Silva, Nuno and Adão, Telmo and Lopes, Rui and Peres, Emanuel and Morais, Raul}, year = {2024}, month = {11}, pages = {}, title = {A technical survey on practical applications and guidelines for IoT sensors in precision agriculture and viticulture}, volume = {14}, journal = {Scientific Reports}, doi = {10.1038/s41598-024-80924-y} } @INPROCEEDINGS{8276822, author={Pérez-Expósito, Josman P. and Fernández-Caramés, Tiago M. and Fraga-Lamas, Paula and Castedo, Luis}, booktitle={2017 IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData)}, title={An IoT Monitoring System for Precision Viticulture}, year={2017}, volume={}, number={}, pages={662-669}, keywords={Diseases;Monitoring;Pipelines;Wireless sensor networks;Meteorology;Temperature measurement;Agriculture;wireless sensor networks;IoT;vineyards;smart viticulture;precision agriculture}, doi={10.1109/iThings-GreenCom-CPSCom-SmartData.2017.104}} @article{GPS_PA, author = {Radocaj, Dorijan and Plaščak, Ivan and Jurišić, Mladen}, year = {2023}, month = {07}, pages = {1417}, title = {Global Navigation Satellite Systems as State-of-the-Art Solutions in Precision Agriculture: A Review of Studies Indexed in the Web of Science}, volume = {13}, journal = {Agriculture}, doi = {10.3390/agriculture13071417} } @Article{su15043866, AUTHOR = {Tziolas, Emmanouil and Karapatzak, Eleftherios and Kalathas, Ioannis and Karampatea, Aikaterini and Grigoropoulos, Antonios and Bajoub, Aadil and Pachidis, Theodore and Kaburlasos, Vassilis G.}, TITLE = {Assessing the Economic Performance of Multipurpose Collaborative Robots toward Skillful and Sustainable Viticultural Practices}, JOURNAL = {Sustainability}, VOLUME = {15}, YEAR = {2023}, NUMBER = {4}, ARTICLE-NUMBER = {3866}, URL = {https://www.mdpi.com/2071-1050/15/4/3866}, ISSN = {2071-1050}, DOI = {10.3390/su15043866} } @article{AIreview:2025, author = {Mustaza, Seri and Pauzi, Nurul and Zainal, Nasharuddin and M Moubark, Asraf and Mohd Zaman, Mohd Hairi}, year = {2025}, month = {05}, pages = {1515-1538}, title = {Artificial Intelligence in Precision Agriculture: A Review}, volume = {37}, journal = {Jurnal Kejuruteraan}, doi = {10.17576/jkukm-2025-37(3)-34} } @article{Gupta2025ApplicationsOA, title={Applications of AI in precision agriculture}, author={Garima Gupta and Sudhir Kumar Pal}, journal={Discover Agriculture}, year={2025}, volume={3}, url={https://api.semanticscholar.org/CorpusID:278080574} } @Article{agronomy12102463, AUTHOR = {Mohimont, Lucas and Alin, François and Rondeau, Marine and Gaveau, Nathalie and Steffenel, Luiz Angelo}, TITLE = {Computer Vision and Deep Learning for Precision Viticulture}, JOURNAL = {Agronomy}, VOLUME = {12}, YEAR = {2022}, NUMBER = {10}, ARTICLE-NUMBER = {2463}, URL = {https://www.mdpi.com/2073-4395/12/10/2463}, ISSN = {2073-4395}, DOI = {10.3390/agronomy12102463} } @InProceedings{practical2025frugal, author="Wasielewska-Michniewska, Katarzyna and Ho{\l}da, Przemys{\l}aw and Paprzycki, Marcin and Ganzha, Maria and Lacalle, Ignacio and Garc{\'i}a, Jorge Jim{\'e}nez", editor="Sachdeva, Shelly and Watanobe, Yutaka and Bhalla, Subhash", title="Practical Considerations for Deploying Frugal AI in the IoT-Edge-Cloud Continuum", booktitle="Big Data Analytics in Astronomy, Science, and Engineering", year="2026", publisher="Springer Nature Switzerland", address="Cham", pages="343--358", doi="10.1007/978-3-032-23241-0_21", abstract="The proliferation of IoT devices and IoT-Edge-Cloud infrastructures has created the need to deploy artificial intelligence applications on resource-constrained devices to achieve efficient decision-making closer to the edge. Frugal AI is an approach that focuses on optimizing machine learning and AI models to be resource-efficient, cost-effective, and scalable, particularly in environments with limited computational resources or energy constraints. Applying frugal techniques to AI models is challenging because of complex trade-off to consider and the lack of silver-bullet approaches. This contribution covers practical considerations when deploying frugal AI and discusses quality metrics that can be used to ensure its effective application. These are considered in the analysis of results of an experimental evaluation of compression techniques, applied to AI-based operation of, real-life anchored scenarios materializing in smart buildings. Results show how frugal methods balance model quality and size compression. Following discussion overviews opportunities for effective deployment on the edge by reducing model size and accelerating inference.", isbn="978-3-032-23241-0" } @article{frugal2026case, title={A case study of artificial neural network compression methods for resource-constrained multi-label classification}, author={Ho{\l}da, Przemys{\l}aw and Wasielewska-Michniewska, Katarzyna and Ganzha, Maria and Paprzycki, Marcin}, journal={Informatica}, volume={37}, number={1}, pages={87--107}, year={2026}, publisher={Vilnius University Institute of Data Science and Digital Technologies} } @article{Franczyk:2020, author = {Franczyk, Bogdan and Hernes, Marcin and Kozierkiewicz-Hetmańska, Adrianna and Kozina, Agata and Pietranik, Marcin and Römer, Ingolf and Schieck, Martin}, year = {2020}, month = {01}, pages = {1211-1220}, title = {Deep learning for grape variety recognition}, volume = {176}, journal = {Procedia Computer Science}, doi = {10.1016/j.procs.2020.09.117} } @article{VELEZ2023109686, title = {VineLiDAR: High-resolution UAV-LiDAR vineyard dataset acquired over two years in northern Spain}, journal = {Data in Brief}, volume = {51}, pages = {109686}, year = {2023}, issn = {2352-3409}, doi = {10.1016/j.dib.2023.109686}, url = {https://www.sciencedirect.com/science/article/pii/S2352340923007655}, author = {Sergio Vélez and Mar Ariza-Sentís and João Valente}, keywords = {Viticulture, Precision agriculture, LiDAR, Drone, Path planning, Woody crops, Photogrammetry, Structure From Motion (SfM)} } @article{VELEZ2024110497, title = {EscaYard: Precision viticulture multimodal dataset of vineyards affected by Esca disease consisting of geotagged smartphone images, phytosanitary status, UAV 3D point clouds and Orthomosaics}, author = {Sergio Vélez and Mar Ariza-Sentís and João Valente}, journal = {Data in Brief}, volume = {54}, pages = {110497}, year = {2024}, issn = {2352-3409}, doi = {10.1016/j.dib.2024.110497} } @Article{iot1010002, AUTHOR = {Spachos, Petros}, TITLE = {Towards a Low-Cost Precision Viticulture System Using Internet of Things Devices}, JOURNAL = {IoT}, VOLUME = {1}, YEAR = {2020}, NUMBER = {1}, PAGES = {5--20}, URL = {https://www.mdpi.com/2624-831X/1/1/2}, ISSN = {2624-831X}, ABSTRACT = {Precision Agriculture (PA) is an ever-expanding field that takes modern technological advancements and applies it to farming practices to reduce waste and increase output. One advancement that can play a significant role in achieving precision agriculture is wireless technology, and specifically the Internet of Things (IoT) devices. Small, inch scale and low-cost devices can be used to monitor great agricultural areas. In this paper, a system for precision viticulture which uses IoT devices for real-time monitoring is proposed. The different components of the system are programmed properly and the interconnection between them is designed to minimize energy consumption. Wireless sensor nodes measure soil moisture and soil temperature in the field and transmit the information to a base station. If the conditions are optimal for a disease or pest to occur, a drone flies towards the area. When the drone is over the node, pictures are captured and then it returns to the base station for further processing. The feasibility of the system is examined through experimentation in a realistic scenario.}, DOI = {10.3390/iot1010002} } @Article{s141223388, AUTHOR = {Di Gennaro, Salvatore Filippo and Matese, Alessandro and Mancin, Mirko and Primicerio, Jacopo and Palliotti, Alberto}, TITLE = {An Open-Source and Low-Cost Monitoring System for Precision Enology}, JOURNAL = {Sensors}, VOLUME = {14}, YEAR = {2014}, NUMBER = {12}, PAGES = {23388--23397}, URL = {https://www.mdpi.com/1424-8220/14/12/23388}, PubMedID = {25490596}, ISSN = {1424-8220}, ABSTRACT = {Winemaking is a dynamic process, where microbiological and chemical effects may strongly differentiate products from the same vineyard and even between wine vats. This high variability means an increase in work in terms of control and process management. The winemaking process therefore requires a site-specific approach in order to optimize cellar practices and quality management, suggesting a new concept of winemaking, identified as Precision Enology. The Institute of Biometeorology of the Italian National Research Council has developed a wireless monitoring system, consisting of a series of nodes integrated in barrel bungs with sensors for the measurement of wine physical and chemical parameters in the barrel. This paper describes an open-source evolution of the preliminary prototype, using Arduino-based technology. Results have shown good performance in terms of data transmission and accuracy, minimal size and power consumption. The system has been designed to create a low-cost product, which allows a remote and real-time control of wine evolution in each barrel, minimizing costs and time for sampling and laboratory analysis. The possibility of integrating any kind of sensors makes the system a flexible tool that can satisfy various monitoring needs.}, DOI = {10.3390/s141223388} } @Article{fi18010016, AUTHOR = {Vieira, António and Silva, Nuno and Pascoal, David and Morais, Raul}, TITLE = {A Versatile and Low-Cost IoT Solution for Bioclimatic Monitoring in Precision Viticulture}, JOURNAL = {Future Internet}, VOLUME = {18}, YEAR = {2026}, NUMBER = {1}, ARTICLE-NUMBER = {16}, URL = {https://www.mdpi.com/1999-5903/18/1/16}, ISSN = {1999-5903}, ABSTRACT = {Bioclimatic monitoring at vineyard scale is essential for irrigation management and disease-risk assessment, yet many systems rely on expensive commercial stations or generic IoT nodes with limited validation and little focus on small and medium-sized winegrowers. This application-driven engineering work investigates whether decision-support-grade bioclimatic data for precision viticulture can be obtained from a low-cost station, by proposing a solar-powered proximal node that integrates soil, plant, and atmospheric sensors on a dedicated PCB that communicates via LoRaWAN. The node operates in a 15-min cycle, with sensing parameters selected to provide the minimum information required for key Precision Viticulture applications. It was deployed in a commercial vineyard side by side with a commercial station, quantifying sensor agreement, communication reliability, and energy consumption. The results show low error rates and consistent agronomic interpretation of environmental conditions, disease risk, precipitation events, and soil and water dynamics. The LoRaWAN link reached a 97% packet-delivery ratio with an average consumption of about 2.5 Wh per day. Material cost is approximately 260 €, one order of magnitude lower than a comparable station. These results indicate that, under real vineyard conditions and compared with a commercial reference, the proposed low-cost system provides agronomically useful, reliable bioclimatic monitoring.}, DOI = {10.3390/fi18010016} } @Article{iot1020020, AUTHOR = {Kontogiannis, Sotirios and Asiminidis, Christodoulos}, TITLE = {A Proposed Low-Cost Viticulture Stress Framework for Table Grape Varieties}, JOURNAL = {IoT}, VOLUME = {1}, YEAR = {2020}, NUMBER = {2}, PAGES = {337--359}, URL = {https://www.mdpi.com/2624-831X/1/2/20}, ISSN = {2624-831X}, ABSTRACT = {Climate change significantly affects viticulture by reducing the production yield and the quality characteristics of its final products. In some observed cases, the consequences of climate outages such as droughts, hail and floods are absolutely devastating for the farmers and the sustained local economies. Hence, it is essential to develop new in implementation monitoring solutions that offer remote real-time surveillance, alert triggering, minimum maintenance and automated generation of incident alerts with precision responses. This paper presents a new framework and a system for vine stress monitoring called Vity-stress. The Vity-stress framework combines field measurements with precise viticulture suggestions and stress avoidance planning. The key points of the proposed framework’s system are that it is easy to develop, easy to maintain and cheap to implement applicability. Focusing on the Mediterranean cultivated table grape varieties that are strongly affected by climate change, we propose a new stress conditions monitoring system to support our framework. The proposition includes distributed field located sensors and a novel camera module implementing deep neural network algorithms to detect stress indicators. Additionally, a new wireless sensor network supported by the iBeacon protocol has been developed. The results of the sensory measurements’ data logging and imposed image detection process’s evaluation shows that the proposed system can successfully detect different stress levels in vineyards, which in turn can allow producers to identify specific areas for irrigation, thereby saving water, energy and time.}, DOI = {10.3390/iot1020020} } @InProceedings{10.1007/978-3-030-30241-2_20, author="Silva, Nuno and Mendes, Jorge and Silva, Renato and dos Santos, Filipe Neves and Mestre, Pedro and Ser{\^o}dio, Carlos and Morais, Raul", editor="Moura Oliveira, Paulo and Novais, Paulo and Reis, Lu{\'i}s Paulo ", title="Low-Cost IoT LoRa®Solutions for Precision Agriculture Monitoring Practices", booktitle="Progress in Artificial Intelligence", year="2019", publisher="Springer International Publishing", address="Cham", pages="224--235", abstract="Emergent and established paradigms, such as the Internet of Things (IoT), cloud and fog/edge computing, together with increasingly cheaper computing technologies -- with very low power requirements, available to exchange data with increased efficiency -- and intelligent systems, have evolved to a level where it is virtually possible to create and deploy monitoring solutions, even in Precision Agriculture (PA) practices. In this work, LoRa®(Long Range) technology and LoRaWAN{\texttrademark}protocol, are tested in a Precision Viticulture (PV) scenario, using low-power data acquisition devices deployed in a vineyard in the UTAD University Campus, distanced 400 m away from the nearest gateway. The main goal of this work is to evaluate sensor data integration in the mySense environment, a framework aimed to systematize data acquisition procedures to address common PA/PV issues, using LoRa®technology. mySense builds over a 4-layer technological structure: sensor and sensor nodes, crop field and sensor networks, cloud services and front-end applications. It makes available a set of free tools based on the Do-It-Yourself (DIY) concept and enables the use of low-cost platforms to quickly prototype a complete PA/PV monitoring application.", isbn="978-3-030-30241-2", doi="10.1007/978-3-030-30241-2_20" } @Article{rs16040635, AUTHOR = {Ortuani, Bianca and Mayer, Alice and Bianchi, Davide and Sona, Giovanna and Crema, Alberto and Modina, Davide and Bolognini, Martino and Brancadoro, Lucio and Boschetti, Mirco and Facchi, Arianna}, TITLE = {Effectiveness of Management Zones Delineated from UAV and Sentinel-2 Data for Precision Viticulture Applications}, JOURNAL = {Remote Sensing}, VOLUME = {16}, YEAR = {2024}, NUMBER = {4}, ARTICLE-NUMBER = {635}, URL = {https://www.mdpi.com/2072-4292/16/4/635}, ISSN = {2072-4292}, ABSTRACT = {How accurately do Sentinel-2 (S2) images describe vine row spatial variability? Can they produce effective management zones (MZs) for precision viticulture? S2 and UAV datasets acquired over two years for different drip-irrigated vineyards in the Colli Morenici region (northern Italy) were used to assess the actual need to use UAV-NDVI maps instead of S2 images to obtain effective MZ maps. First, the correlation between S2 and UAV-NDVI values was investigated. Secondly, contingency matrices and dichotomous tables (considering UAV-MZ maps as a reference) were developed to compare MZ maps produced using S2 and UAV imagery. Moreover, data on grape production and quality were analyzed through linear discrimination analyses (LDA) to evaluate the effectiveness of S2-MZs and UAV-MZs to explain spatial variability in yield and quality data. The outcomes highlight that S2 images can be quite good tools to manage fertilization based on the within-field vigor variability, of which they capture the main features. Nevertheless, as S2-MZs with low and high vigor were over-estimated, S2-MZ maps cannot be used for high-accuracy input management. From the LDA results, the UAV-MZs appeared slightly more performant than the S2-MZs in explaining the variability in grape quality and yield, especially in the case of low-vigor MZs.}, DOI = {10.3390/rs16040635} } @article{TARDAGUILA2021100005, title = {Smart applications and digital technologies in viticulture: A review}, journal = {Smart Agricultural Technology}, volume = {1}, pages = {100005}, year = {2021}, issn = {2772-3755}, doi = {10.1016/j.atech.2021.100005}, url = {https://www.sciencedirect.com/science/article/pii/S2772375521000058}, author = {Javier Tardaguila and Manfred Stoll and Salvador Gutiérrez and Tony Proffitt and Maria P. Diago}, keywords = {Digital viticulture, Precision viticulture, Vineyard monitoring, Remote and proximal sensing, Vineyard app, Vineyard robotics, Artificial intelligence}, abstract = {It is important to continuously monitor the long-term impact of viticultural management practices and assess opportunities for improving the environmental footprint of vineyard operations. This is particularly relevant to the wine industry as growers face disruptive challenges caused by climate change, shortages of labour and escalating production costs. In recent years there has been considerable development and testing of non-invasive digital technologies, some of which have already demonstrated an improvement in the way that wine grapes are grown, managed and harvested to produce quality wines in a manner that is both environmentally and economically sustainable. In this paper, we describe a number of sensing technologies including spectroscopy, multispectral and hyperspectral imaging, chlorophyll fluorescence, thermography, electrical resistivity, laser imaging detection and ranging, and computer vision and the platforms where they are generally mounted or embedded for either proximal or remote monitoring. Artificial intelligence is also discussed as it is useful as a means of transforming data into different pieces of information used by the grape grower for making informed decisions. A key objective of using these technologies is to obtain and supply data and information to grape growers and wine producers as a basis for improving land and vine management through a more-informed decision-making process. The current and future application of these technologies and artificial intelligence in vineyards are discussed in relation to soil properties and topography, vegetative growth, canopy architecture, nutrient and water status, pests and diseases, crop forecasting, yield and fruit composition, vineyard sampling, targeted management and selective harvesting. The principles behind how these technologies operate are also described. While the technologies have enormous potential for growers, their adoption and use will depend on user-friendly software and devices, together with affordable costs, at the field scale.} } @Article{agriculture11030201, AUTHOR = {Ammoniaci, Marco and Kartsiotis, Simon-Paolo and Perria, Rita and Storchi, Paolo}, TITLE = {State of the Art of Monitoring Technologies and Data Processing for Precision Viticulture}, JOURNAL = {Agriculture}, VOLUME = {11}, YEAR = {2021}, NUMBER = {3}, ARTICLE-NUMBER = {201}, URL = {https://www.mdpi.com/2077-0472/11/3/201}, ISSN = {2077-0472}, ABSTRACT = {Precision viticulture (PV) aims to optimize vineyard management, reducing the use of resources, the environmental impact and maximizing the yield and quality of the production. New technologies as UAVs, satellites, proximal sensors and variable rate machines (VRT) are being developed and used more and more frequently in recent years thanks also to informatics systems able to read, analyze and process a huge number of data in order to give the winegrowers a decision support system (DSS) for making better decisions at the right place and time. This review presents a brief state of the art of precision viticulture technologies, focusing on monitoring tools, i.e., remote/proximal sensing, variable rate machines, robotics, DSS and the wireless sensor network.}, DOI = {10.3390/agriculture11030201} } @article{Gano:2024, author = {Gano, Boubacar and Bhadra, Sourav and Vilbig, Justin and Ahmed, Nurzaman and Sagan, Vasit and Shakoor, Nadia}, year = {2024}, month = {04}, pages = {}, title = {Drone‐based imaging sensors, techniques, and applications in plant phenotyping for crop breeding: A comprehensive review}, volume = {7}, journal = {The Plant Phenome Journal}, doi = {10.1002/ppj2.20100} } @article{Orlandi:2025, author = {Orlandi, Giorgia and Matese, Alessandro and Ulrici, Alessandro and Calvini, Rosalba and Berton, Andrea and Di Gennaro, Salvatore}, year = {2025}, month = {03}, pages = {}, title = {Automated yield prediction in vineyard using RGB images acquired by a UAV prototype platform}, volume = {59}, journal = {OENO One}, doi = {10.20870/oeno-one.2025.59.1.8133} } @article{GrapeDetection:2025, author = {Vélez Martín, Sergio and Ariza, Mar and Triviño, Mario and Cob, Carlos and Mila, Miquel and Valente, João}, year = {2025}, month = {02}, pages = {e42525}, title = {Framework for Smartphone-based Grape Detection and Vineyard Management using UAV-Trained AI}, volume = {11}, journal = {Heliyon}, doi = {10.1016/j.heliyon.2025.e42525} } @article{Epifany:2024, author = {Epifani, Lorenzo and Caruso, Antonio}, year = {2024}, month = {10}, pages = {100625}, title = {A Survey on Deep Learning in UAV imagery for Precision Agriculture and Wild Flora Monitoring: Datasets, Models and Challenges}, volume = {9}, journal = {Smart Agricultural Technology}, doi = {10.1016/j.atech.2024.100625} } @Article{jimaging11020034, AUTHOR = {Quiñones, Rubi and Banu, Syeda Mariah and Gultepe, Eren}, TITLE = {GCNet: A Deep Learning Framework for Enhanced Grape Cluster Segmentation and Yield Estimation Incorporating Occluded Grape Detection with a Correction Factor for Indoor Experimentation}, JOURNAL = {Journal of Imaging}, VOLUME = {11}, YEAR = {2025}, NUMBER = {2}, ARTICLE-NUMBER = {34}, URL = {https://www.mdpi.com/2313-433X/11/2/34}, PubMedID = {39997536}, ISSN = {2313-433X}, DOI = {10.3390/jimaging11020034} } @InProceedings{ronneberger2015u, author="Ronneberger, Olaf and Fischer, Philipp and Brox, Thomas", editor="Navab, Nassir and Hornegger, Joachim and Wells, William M. and Frangi, Alejandro F.", title="U-Net: Convolutional Networks for Biomedical Image Segmentation", booktitle="Medical Image Computing and Computer-Assisted Intervention -- MICCAI 2015", year="2015", publisher="Springer International Publishing", address="Cham", pages="234--241", abstract="There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net.", isbn="978-3-319-24574-4" } @article{wang_incoherent_2025, title = {Incoherent {Region}-{Aware} {Occlusion} {Instance} {Synthesis} for {Grape} {Amodal} {Detection}}, volume = {25}, issn = {1424-8220}, url = {https://www.mdpi.com/1424-8220/25/5/1546}, doi = {10.3390/s25051546}, abstract = {Occlusion presents a significant challenge in grape phenotyping detection, where predicting occluded content (amodal detection) can greatly enhance detection accuracy. Recognizing that amodal detection performance is heavily influenced by the segmentation quality between occluder and occluded grape instances, we propose a grape instance segmentation model designed to precisely predict error-prone regions caused by mask size transformations during segmentation, with a particular focus on overlapping regions. To address the limitations of current occlusion synthesis methods in amodal detection, a novel overlapping cover strategy is introduced to replace the existing random cover strategy. This approach ensures that synthetic grape instances better align with real-world occlusion scenarios. Quantitative comparison experiments conducted on the grape amodal detection dataset demonstrate that the proposed grape instance segmentation model achieves superior amodal detection performance, with an IoU score of 0.7931. Additionally, the proposed overlapping cover strategy significantly outperforms the random cover strategy in amodal detection performance.}, language = {en}, number = {5}, urldate = {2026-02-25}, journal = {Sensors}, author = {Wang, Yihan and Xiao, Shide and Meng, Xiangyin}, month = {03}, year = {2025}, pages = {1546}, } @misc{li_amodal_2016, title = {Amodal {Instance} {Segmentation}}, url = {http://arxiv.org/abs/1604.08202}, doi = {10.48550/arXiv.1604.08202}, abstract = {We consider the problem of amodal instance segmentation, the objective of which is to predict the region encompassing both visible and occluded parts of each object. Thus far, the lack of publicly available amodal segmentation annotations has stymied the development of amodal segmentation methods. In this paper, we sidestep this issue by relying solely on standard modal instance segmentation annotations to train our model. The result is a new method for amodal instance segmentation, which represents the first such method to the best of our knowledge. We demonstrate the proposed method’s effectiveness both qualitatively and quantitatively.}, language = {en}, urldate = {2026-02-25}, publisher = {arXiv}, author = {Li, Ke and Malik, Jitendra}, month = {08}, year = {2016}, note = {arXiv:1604.08202 [cs]}, keywords = {Computer Science - Computer Vision and Pattern Recognition}, } @article{wang_occlusion-aware_2026, title = {Occlusion-{Aware} {Multi}-{Object} {Tracking} in {Vineyards} via {SAM}-{Based} {Visibility} {Modeling}}, volume = {15}, issn = {2079-9292}, url = {https://www.mdpi.com/2079-9292/15/3/621}, doi = {10.3390/electronics15030621}, abstract = {Multi-object tracking (MOT) in vineyard environments remains challenging due to frequent and long-term occlusions caused by dense foliage, overlapping grape clusters, and complex plant structures. These characteristics often result in identity switches and fragmented trajectories when using conventional tracking methods. This paper proposes OATSAMTrack, an occlusion-aware multi-object tracking framework designed for vineyard fruit monitoring. The framework integrates lightweight MobileSAM-assisted instance segmentation to estimate target visibility and occlusion severity. Occlusion-state reasoning is further incorporated into temporal association, appearance memory updating, and identity recovery. An adaptive temporal memory mechanism selectively updates appearance features according to predicted occlusion states, reducing identity drift under partial and severe occlusions. To facilitate occlusion-aware evaluation, an extended vineyard multiobject tracking dataset (GrapeOcclusionMOTS) with SAM-refined instance masks and fine-grained occlusion annotations is constructed. The experimental results demonstrate that OATSAM-Track improves identity consistency and tracking robustness compared to representative baseline trackers, particularly under medium and severe occlusion scenarios. These results indicate that explicit occlusion modeling is beneficial for reliable fruit monitoring in precision agriculture.}, language = {en}, number = {3}, urldate = {2026-02-25}, journal = {Electronics}, author = {Wang, Yanan and Kim, Hagsong and Fayaz, Muhammad and Dang, Lien Minh and Moon, Hyeonjoon and Lee, Kang-Won}, month = {02}, year = {2026}, pages = {621}, } @inproceedings{redmon2016you, title={You only look once: Unified, real-time object detection}, author={Redmon, Joseph and Divvala, Santosh and Girshick, Ross and Farhadi, Ali}, booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition}, pages={779--788}, year={2016} } @article{du2023strongsort, title={Strongsort: Make deepsort great again}, author={Du, Yunhao and Zhao, Zhicheng and Song, Yang and Zhao, Yanyun and Su, Fei and Gong, Tao and Meng, Hongying}, journal={IEEE Transactions on Multimedia}, volume={25}, pages={8725--8737}, year={2023}, publisher={IEEE}, keywords={Tracking;Task analysis;Computational modeling;Trajectory;Interpolation;Training;Kalman filters;Multi-object tracking;baseline;AFLink;GSI}, doi={10.1109/TMM.2023.3240881}} @misc{zhang2023sam, title={Faster Segment Anything: Towards Lightweight SAM for Mobile Applications}, author={Chaoning Zhang and Dongshen Han and Yu Qiao and Jung Uk Kim and Sung-Ho Bae and Seungkyu Lee and Choong Seon Hong}, year={2023}, eprint={2306.14289}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2306.14289}, doi = {10.48550/arXiv.2306.14289} } @inproceedings{kirillov2023segment, title={Segment anything}, author={Kirillov, Alexander and Mintun, Eric and Ravi, Nikhila and Mao, Hanzi and Rolland, Chloe and Gustafson, Laura and Xiao, Tete and Whitehead, Spencer and Berg, Alexander C and Lo, Wan-Yen and others}, booktitle={Proceedings of the IEEE/CVF international conference on computer vision}, pages={4015--4026}, year={2023} } @article{yang_real-time_2026, title = {A real-time semantic {3D} vineyard mapping and fruit localization system for yield estimation in dynamic vineyards}, volume = {13}, issn = {27723755}, url = {https://linkinghub.elsevier.com/retrieve/pii/S2772375526000080}, doi = {10.1016/j.atech.2026.101784}, abstract = {In precision viticulture, autonomous systems are increasingly deployed for inspection and yield estimation. However, mapping 3D vineyard environments and monitoring fruit distribution presents challenges due to fruit occlusion, moving objects, and unstructured backgrounds. To address these issues, this study presents a semantic 3D mapping and fruit localization system designed for yield estimation in dynamic environments. The proposed framework integrates the ORB-SLAM3 backend with a lightweight semantic segmentation model, named Edge Fusion Segmentation Network (EFSegNet). Derived from the PIDNet baseline, EFSegNet introduces a Gradient Feature Fusion Block (GFFM) and a Deformable Spatial Attention (DSA) module. These components are designed to refine fruit boundaries and separate overlapping grape bunches, a requirement for individual counting. The generated semantic masks guide the removal of dynamic feature points to maintain map consistency, while enabling semantic mapping of fruit clusters. Additionally, a three-stage point cloud filtering strategy is applied to refine the global map, followed by DBSCAN clustering and PCA-based modeling to extract the 3D location and quantity of grape bunches. Validation experiments in a real-world dynamic vineyard indicate that the system operated at 23.1 FPS, with an average 3D localization error of 21.02 mm. The average counting error was 5.95\%, demonstrating the system’s applicability for automated yield estimation.}, language = {en}, urldate = {2026-02-25}, journal = {Smart Agricultural Technology}, author = {Yang, Runbin and Zhang, Xilong and Chen, Yanyang and Huang, Xiaotao and Feng, Sang}, month = {03}, year = {2026}, pages = {101784}, } @ARTICLE{campos2021orb, author={Campos, Carlos and Elvira, Richard and Rodríguez, Juan J. Gómez and M. Montiel, José M. and D. Tardós, Juan}, journal={IEEE Transactions on Robotics}, title={ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual–Inertial, and Multimap SLAM}, year={2021}, volume={37}, number={6}, pages={1874-1890}, keywords={Simultaneous localization and mapping;Computer vision;Feature extraction;Inertial navigation;Robustness;Optimization;Computer vision;inertial navigation;simult- aneous localization and mapping}, doi={10.1109/TRO.2021.3075644}} @inproceedings{ester1996density, author = {Ester, Martin and Kriegel, Hans-Peter and Sander, J{\"o}rg and Xu, Xiaowei}, title = {A density-based algorithm for discovering clusters in large spatial databases with noise}, year = {1996}, publisher = {AAAI Press}, abstract = {Clustering algorithms are attractive for the task of class identification in spatial databases. However, the application to large spatial databases rises the following requirements for clustering algorithms: minimal requirements of domain knowledge to determine the input parameters, discovery of clusters with arbitrary shape and good efficiency on large databases. The well-known clustering algorithms offer no solution to the combination of these requirements. In this paper, we present the new clustering algorithm DBSCAN relying on a density-based notion of clusters which is designed to discover clusters of arbitrary shape. DBSCAN requires only one input parameter and supports the user in determining an appropriate value for it. We performed an experimental evaluation of the effectiveness and efficiency of DBSCAN using synthetic data and real data of the SEQUOIA 2000 benchmark. The results of our experiments demonstrate that (1) DBSCAN is significantly more effective in discovering clusters of arbitrary shape than the well-known algorithm CLAR-ANS, and that (2) DBSCAN outperforms CLARANS by a factor of more than 100 in terms of efficiency.}, booktitle = {Proceedings of the Second International Conference on Knowledge Discovery and Data Mining}, pages = {226–231}, numpages = {6}, keywords = {handling nlj4-275oise, efficiency on large spatial databases, clustering algorithms, arbitrary shape of clusters}, location = {Portland, Oregon}, series = {KDD'96} } @article{hotelling1933analysis, title={Analysis of a complex of statistical variables into principal components.}, author={Hotelling, Harold}, journal={Journal of educational psychology}, volume={24}, number={6}, pages={417-441}, year={1933}, publisher={Warwick \& York}, doi = {10.1037/h0071325} } @article{huang_review_2025, title = {A review of visual perception technology for intelligent fruit harvesting robots}, volume = {16}, issn = {1664-462X}, url = {https://www.frontiersin.org/articles/10.3389/fpls.2025.1646871/full}, doi = {10.3389/fpls.2025.1646871}, abstract = {With the development of smart agriculture, fruit picking robots have attracted widespread attention as one of the key technologies to improve agricultural productivity. Visual perception technology plays a crucial role in fruit picking robots, involving precise fruit identification, localization, and grasping operations. This paper reviews the research progress in the visual perception technology for fruit picking robots, focusing on key technologies such as camera types used in picking robots, object detection techniques, picking point recognition and localization, active vision, and visual servoing. First, the paper introduces the application characteristics and selection criteria of different camera types in the fruit picking process. Then, it analyzes how object detection techniques help robots accurately recognize fruits and achieve efficient fruit classification. Next, it discusses the picking point recognition and localization technologies, including vision-based 3D reconstruction and depth sensing methods. Subsequently, it elaborates on the adaptability of active vision technology in dynamic environments and how visual servoing technology achieves precise localization. Additionally, the review explores robot mobility perception technologies, focusing on V-SLAM, mobile path planning, and task scheduling. These technologies enhance harvesting efficiency across the entire orchard and facilitate better collaboration among multiple robots. Finally, the paper summarizes the challenges in current research and the future development trends, aiming to provide references for the optimization and promotion of fruit picking robot technology.}, language = {en}, urldate = {2026-02-12}, journal = {Frontiers in Plant Science}, author = {Huang, Yikun and Xu, Shuyan and Chen, Hao and Li, Gang and Dong, Heng and Yu, Jie and Zhang, Xi and Chen, Riqing}, month = {08}, year = {2025}, pages = {1646871}, } @article{taketomi2017visual, title={Visual SLAM algorithms: A survey from 2010 to 2016}, author={Taketomi, Takafumi and Uchiyama, Hideaki and Ikeda, Sei}, journal={IPSJ transactions on computer vision and applications}, volume={9}, number={1}, pages={16}, year={2017}, publisher={Springer}, doi = {10.1186/s41074-017-0027-2} } @article{tan_review_2025, title = {A {Review} of {Research} on {Fruit} and {Vegetable} {Picking} {Robots} {Based} on {Deep} {Learning}}, volume = {25}, issn = {1424-8220}, url = {https://www.mdpi.com/1424-8220/25/12/3677}, doi = {10.3390/s25123677}, abstract = {Fruit and vegetable picking robots are considered an important way to promote agricultural modernization due to their high efficiency, precision, and intelligence. However, most of the existing research has sporadically involved single application areas, such as object detection, classification, and path planning, and has not yet comprehensively sorted out the core applications of deep learning technology in fruit and vegetable picking robots, the current technological bottlenecks faced, and future development directions. This review summarizes the key technologies and applications of deep learning in the visual perception and target recognition, path planning and motion control, and intelligent control of end effectors of fruit and vegetable picking robots. It focuses on the optimization strategies and common problems related to deep learning and explores the challenges and development trends of deep learning in improving the perception accuracy, multi-sensor collaboration, multimodal data fusion, adaptive control, and human–computer interaction of fruit and vegetable picking robots in the future. The aim is to provide theoretical support and practical guidance for the practical application of deep learning technology in fruit and vegetable picking robots.}, language = {en}, number = {12}, urldate = {2026-02-04}, journal = {Sensors}, author = {Tan, Yarong and Liu, Xin and Zhang, Jinmeng and Wang, Yigang and Hu, Yanxiang}, month = {06}, year = {2025}, pages = {3677}, } @article{burusa_attention-driven_2024, title = {Attention-driven {Next}-best-view {Planning} for {Efficient} {Reconstruction} of {Plants} and {Targeted} {Plant} {Parts}}, volume = {246}, issn = {15375110}, url = {http://arxiv.org/abs/2206.10274}, doi = {10.1016/j.biosystemseng.2024.08.002}, abstract = {Robots in tomato greenhouses need to perceive the plant and plant parts accurately to automate monitoring, harvesting, and deleafing tasks. Existing perception systems struggle with the high levels of occlusion in plants and often result in poor perception accuracy. One reason for this is because they use fixed cameras or predefined camera movements. Next-best-view (NBV) planning presents a alternate approach, in which the camera viewpoints are reasoned and strategically planned such that the perception accuracy is improved. However, existing NBV-planning algorithms are agnostic to the task-at-hand and give equal importance to all the plant parts. This strategy is inefficient for greenhouse tasks that require targeted perception of specific plant parts, such as the perception of leaf nodes for de-leafing. To improve targeted perception in complex greenhouse environments, NBV planning algorithms need an attention mechanism to focus on the task-relevant plant parts. In this paper, we investigated the role of attention in improving targeted perception using an attention-driven NBV planning strategy. Through simulation experiments using plants with high levels of occlusion and structural complexity, we showed that focusing attention on task-relevant plant parts can significantly improve the speed and accuracy of 3D reconstruction. Further, with real-world experiments, we showed that these benefits extend to complex greenhouse conditions with natural variation and occlusion, natural illumination, sensor noise, and uncertainty in camera poses. Our results clearly indicate that using attention-driven NBV planning in greenhouses can significantly improve the efficiency of perception and enhance the performance of robotic systems in greenhouse crop production.}, language = {en}, urldate = {2026-02-25}, journal = {Biosystems Engineering}, author = {Burusa, Akshay K. and Henten, Eldert J. van and Kootstra, Gert}, month = {08}, year = {2024}, note = {arXiv:2206.10274 [cs]}, keywords = {Computer Science - Computer Vision and Pattern Recognition, Computer Science - Robotics}, pages = {248--262}, } @article{peng_vision-based_2025, title = {A {Vision}-{Based} {Information} {Processing} {Framework} for {Vineyard} {Grape} {Picking} {Using} {Two}-{Stage} {Segmentation} and {Morphological} {Perception}}, volume = {11}, issn = {2311-7524}, url = {https://www.mdpi.com/2311-7524/11/9/1039}, doi = {10.3390/horticulturae11091039}, abstract = {To achieve efficient vineyard grape picking, a vision-based information processing framework integrating two-stage segmentation with morphological perception is proposed. In the first stage, an improved YOLOv8s-seg model is employed for coarse segmentation, incorporating two key enhancements: first, a dynamic deformation feature aggregation module (DDFAM), which facilitates the extraction of complex structural and morphological features; and second, an efficient asymmetric decoupled head (EADHead), which improves boundary awareness while reducing parameter redundancy. Compared with mainstream segmentation models, the improved model achieves superior performance, attaining the highest mAP@0.5 of 86.75\%, a lightweight structure with 10.34 M parameters, and a realtime inference speed of 10.02 ms per image. In the second stage, the fine segmentation of fruit stems is performed using an improved OTSU thresholding algorithm, which is applied to a single-channel image derived from the hue component of the HSV color space, thereby enhancing robustness under complex lighting conditions. Morphological features extracted from the preprocessed fruit stem, including centroid coordinates and a skeleton constructed via medial axis transform (MAT), are further utilized to establish the spatial relationships with a picking point and cutting axis. The visualization analysis confirms the high feasibility and adaptability of the proposed framework, providing essential technical support for the automation of grape harvesting.}, language = {en}, number = {9}, urldate = {2026-02-25}, journal = {Horticulturae}, author = {Peng, Yifei and Sun, Jun and Wu, Zhaoqi and Gao, Jinye and Shi, Lei and Shi, Zhiyan}, month = {09}, year = {2025}, pages = {1039}, } @article{liu_visionassisted_2025, title = {Vision‐{Assisted} {Avocado} {Harvesting} with {Aerial} {Bimanual} {Manipulation}}, issn = {2943-9973, 2943-9973}, url = {https://advanced.onlinelibrary.wiley.com/doi/10.1002/adrr.202500003}, doi = {10.1002/adrr.202500003}, abstract = {Robotic fruit harvesting holds potential in precision agriculture to improve harvesting efficiency. While ground mobile robots are mostly employed in fruit harvesting, certain crops, like avocado trees, cannot be harvested efficiently from the ground alone. This is because of unstructured ground and planting arrangement and high-to-reach fruits. In such cases, aerial robots integrated with manipulation capabilities can pave new ways in robotic harvesting. This paper outlines the design and implementation of a bimanual aerial robot that employs visual perception and learning to detect avocados, reach, and harvest them autonomously. The dualarm system comprises a gripper and a fixer arm, to address a key challenge when harvesting avocados: once grasped, applying a rotational motion is the most mechanically efficient way to detach the avocado from the peduncle; however, the peduncle may store elastic energy preventing the avocado from being harvested. The fixer arm aims to stabilize the peduncle, allowing the gripper arm to harvest. The integrated visual perception process enables the detection of avocados and the determination of their pose; the latter is then used to determine target points for a bimanual manipulation planner. Several experiments are conducted in controlled indoor and outdoor settings to assess the efficacy of each component individually. Further, an integrated experiment in outdoor semicontrolled settings is used for feasibility assessment of the overall system. Results demonstrate that all different components can work synergistically to enable robotic avocado harvesting in (semi-)controlled settings. Results also highlight limitations of an airborne harvesting solution and reveal tradeoffs to be considered in the selection of a harvesting robot.}, language = {en}, urldate = {2026-02-12}, journal = {Advanced Robotics Research}, author = {Liu, Zhichao and Zhou, Jingzong and Mucchiani, Caio and Karydis, Konstantinos}, month = {05}, year = {2025}, pages = {202500003}, } @misc{samoili_2025_17748130, author = {Samoili, Sofia and Gaspar, João and Ferreira, Renato and Vieira Duque Carreira Monteiro, Maria da Graça and Sebastião, Pedro and Kalakou, Sofia}, title = {Drone-Enabled Data Collection for Sustainable Viticulture: A Practical Framework for Precision Viticulture }, month = {11}, year = 2025, publisher = {Springer}, doi = {10.5281/zenodo.17748130}, url = {https://doi.org/10.5281/zenodo.17748130}, } @article{debnath_review_2024, title = {A {Review} of {UAV} {Path}-{Planning} {Algorithms} and {Obstacle} {Avoidance} {Methods} for {Remote} {Sensing} {Applications}}, volume = {16}, issn = {2072-4292}, url = {https://www.mdpi.com/2072-4292/16/21/4019}, doi = {10.3390/rs16214019}, abstract = {The rapid development of uncrewed aerial vehicles (UAVs) has significantly increased their usefulness in various fields, particularly in remote sensing. This paper provides a comprehensive review of UAV path planning, obstacle detection, and avoidance methods, with a focus on its utilisation in both single and multiple UAV platforms. The paper classifies the algorithms into two main categories: (1) global and local path-planning approaches in single UAVs; and (2) multi-UAV path-planning methods. It further analyses obstacle detection and avoidance methods, as well as their capacity to adapt, optimise, and compute efficiently in different operational environments. The outcomes highlight the advantages and limitations of each method, offering valuable information regarding their suitability for remote sensing applications, such as precision agriculture, urban mapping, and ecological surveillance. Additionally, this review also identifies limitations in the existing research, specifically in multi-UAV frameworks, and provides recommendations for future developments to improve the adaptability and effectiveness of UAV operations in dynamic and complex situations.}, language = {en}, number = {21}, urldate = {2026-02-04}, journal = {Remote Sensing}, author = {Debnath, Dipraj and Vanegas, Fernando and Sandino, Juan and Hawary, Ahmad Faizul and Gonzalez, Felipe}, month = {10}, year = {2024}, pages = {4019}, } @article{hart1968formal, title={A formal basis for the heuristic determination of minimum cost paths}, author={Hart, Peter E and Nilsson, Nils J and Raphael, Bertram}, journal={IEEE transactions on Systems Science and Cybernetics}, volume={4}, number={2}, pages={100--107}, year={1968}, publisher={IEEE}, keywords={Costs;Mathematical programming;Minimization methods;Functional programming;Automatic control;Minimax techniques;Gradient methods;Chemical technology;Automatic programming;Instruction sets}, doi={10.1109/TSSC.1968.300136} } @Inbook{shapiro1999genetic, author="Shapiro, Jonathan", editor="Paliouras, Georgios and Karkaletsis, Vangelis and Spyropoulos, Constantine D.", title="Genetic Algorithms in Machine Learning", bookTitle="Machine Learning and Its Applications: Advanced Lectures", year="2001", publisher="Springer Berlin Heidelberg", address="Berlin, Heidelberg", pages="146--168", abstract="Genetic algorithms are stochastic search algorithms which act on a population of possible solutions. They are loosely based on the mechanics of population genetics and selection. The potential solutions are encoded as `genes' --- strings of characters from some alphabet. New solutions can be produced by `mutating' members of the current population, and by `mating' two solutions together to form a new solution. The better solutions are selected to breed and mutate and the worse ones are discarded. They are probabilistic search methods; this means that the states which they explore are not determined solely by the properties of the problems. A random process helps to guide the search. Genetic algorithms are used in artificial intelligence like other search algorithms are used in artificial intelligence --- to search a space of potential solutions to find one which solves the problem.", isbn="978-3-540-44673-6", doi="10.1007/3-540-44673-7_7", url="https://doi.org/10.1007/3-540-44673-7_7" } @INPROCEEDINGS{kennedy1995particle, author={Kennedy, J. and Eberhart, R.}, booktitle={Proceedings of ICNN'95 - International Conference on Neural Networks}, title={Particle swarm optimization}, year={1995}, volume={4}, number={}, pages={1942-1948 vol.4}, keywords={Particle swarm optimization;Birds;Educational institutions;Marine animals;Testing;Humans;Genetic algorithms;Optimization methods;Artificial neural networks;Performance evaluation}, doi={10.1109/ICNN.1995.488968}} @misc{thiago_santos_2019_3361736, author = {Thiago Santos and de Souza, Leonardo and dos Santos Andreza and Avila, Sandra}, title = {Embrapa Wine Grape Instance Segmentation Dataset – Embrapa WGISD }, month = {07}, year = 2019, publisher = {Zenodo}, version = {1.0.0}, doi = {10.5281/zenodo.3361736}, url = {https://doi.org/10.5281/zenodo.3361736}, } @Article{s24092953, AUTHOR = {Peng, Jialiang and Ouyang, Cheng and Peng, Hao and Hu, Wenwu and Wang, Yi and Jiang, Ping}, TITLE = {MultiFuseYOLO: Redefining Wine Grape Variety Recognition through Multisource Information Fusion}, JOURNAL = {Sensors}, VOLUME = {24}, YEAR = {2024}, NUMBER = {9}, ARTICLE-NUMBER = {2953}, URL = {https://www.mdpi.com/1424-8220/24/9/2953}, PubMedID = {38733058}, ISSN = {1424-8220}, DOI = {10.3390/s24092953} } @article{wgisd_uc2022, author = {Su, Shuzhi and Chen, Runbin and Fang, Xianjin and Zhu, Yanmin and Zhang, Tian and Xu, Zengbao}, year = {2022}, month = {09}, pages = {1364}, title = {A Novel Lightweight Grape Detection Method}, volume = {12}, journal = {Agriculture}, doi = {10.3390/agriculture12091364} } @article{ZHAO2022174, title = {An end-to-end lightweight model for grape and picking point simultaneous detection}, journal = {Biosystems Engineering}, volume = {223}, pages = {174-188}, year = {2022}, issn = {1537-5110}, doi = {10.1016/j.biosystemseng.2022.08.013}, url = {https://www.sciencedirect.com/science/article/pii/S1537511022001970}, author = {Ruzhun Zhao and Yuchang Zhu and Yuanhong Li}, keywords = {Deep learning, Object detection, Computer vision, Grape picking} } @misc{GrapeCS-ML:2019, author = {Seng, Jasmine and Ang, Kenneth and Schmidtke, Leigh and Rogiers, Suzy}, title = {Grape image database}, year = {2018}, publisher = {Charles Sturt University}, doi = {10.26189/5da7a8603c55c}, url = {https://researchoutput.csu.edu.au/en/datasets/grape-image-database/}, version = {v1}, note = {Includes GrapeDatabase.zip and Dyostem\_App\_Project\_2017\_Full\_Data\_Set.xlsx} } @Article{s21113908, AUTHOR = {Ghiani, Luca and Sassu, Alberto and Palumbo, Francesca and Mercenaro, Luca and Gambella, Filippo}, TITLE = {In-Field Automatic Detection of Grape Bunches under a Totally Uncontrolled Environment}, JOURNAL = {Sensors}, VOLUME = {21}, YEAR = {2021}, NUMBER = {11}, ARTICLE-NUMBER = {3908}, URL = {https://www.mdpi.com/1424-8220/21/11/3908}, PubMedID = {34198844}, ISSN = {1424-8220}, DOI = {10.3390/s21113908} } @article{ARIZASENTIS2023108848, title = {Dataset on UAV RGB videos acquired over a vineyard including bunch labels for object detection and tracking}, journal = {Data in Brief}, volume = {46}, pages = {108848}, year = {2023}, issn = {2352-3409}, doi = {10.1016/j.dib.2022.108848}, url = {https://www.sciencedirect.com/science/article/pii/S2352340922010514}, author = {Mar Ariza-Sentís and Sergio Vélez and João Valente}, keywords = {Viticulture, Precision agriculture, Object detection, Object tracking, Remote sensing, UAV} } @article{Polvara:2024, author = {Polvara, Riccardo and Molina, Sergi and Hroob, Ibrahim and Papadimitriou, Alexios and Tsiolis, Konstantinos and Giakoumis, Dimitrios and Likothanassis, Spiridon and Tzovaras, Dimitrios and Cielniak, Grzegorz and Hanheide, Marc}, title = {Bacchus Long-Term (BLT) data set: Acquisition of the agricultural multimodal BLT data set with automated robot deployment}, journal = {Journal of Field Robotics}, volume = {41}, number = {7}, pages = {2280-2298}, keywords = {agriculture, autonomous navigation, data set, field robotics, long-term, mobile robots, robot localization}, doi = {10.1002/rob.22228}, url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/rob.22228}, eprint = {https://onlinelibrary.wiley.com/doi/pdf/10.1002/rob.22228}, year = {2024} } @article{VELEZ2023108876, title = {Dataset on unmanned aerial vehicle multispectral images acquired over a vineyard affected by Botrytis cinerea in northern Spain}, journal = {Data in Brief}, volume = {46}, pages = {108876}, year = {2023}, issn = {2352-3409}, doi = {10.1016/j.dib.2022.108876}, url = {https://www.sciencedirect.com/science/article/pii/S2352340922010794}, author = {Sergio Vélez and Mar Ariza-Sentís and João Valente}, keywords = {Viticulture, Precision agriculture, Disease detection, UAV, Drone, Orthomosaic, Structure from motion, Photogrammetry} } @Article{rs18040659, AUTHOR = {Caroppo, Andrea and Diraco, Giovanni and Leone, Alessandro}, TITLE = {A Systematic Review of Available Multispectral UAV Image Datasets for Precision Agriculture Applications}, JOURNAL = {Remote Sensing}, VOLUME = {18}, YEAR = {2026}, NUMBER = {4}, ARTICLE-NUMBER = {659}, URL = {https://www.mdpi.com/2072-4292/18/4/659}, ISSN = {2072-4292}, ABSTRACT = {The proliferation of Unmanned Aerial Vehicles (UAVs) equipped with multispectral imaging sensors has revolutionized data collection in precision agriculture. These platforms provide high-resolution, temporally dense data crucial for monitoring crop health, optimizing resource management, and predicting yield. However, the development and validation of robust data-driven algorithms, from vegetation index analysis to complex deep learning models, are contingent upon the availability of high-quality, standardized, and publicly accessible datasets. This review systematically surveys and characterizes the current landscape of available datasets containing multispectral imagery acquired by UAVs in agricultural contexts. Following guidelines for reporting systematic reviews and meta-analyses (PRISMA methodology), 39 studies were selected and analyzed, categorizing them based on key attributes including spectral bands (e.g., RGB, Red Edge, Near-Infrared), spatial and temporal resolution, types of crops studied, presence of complementary ground-truth data (e.g., biomass, nitrogen content, yield maps), and the specific agricultural tasks they support (e.g., disease detection, weed mapping, water stress assessment). However, the review underscores a critical gap in standardization, with significant variability in data formats, annotation quality, and metadata completeness, which hampers reproducibility and comparative analysis. Furthermore, we identify a need for more datasets targeting specific challenges like early-stage disease identification and anomaly detection in complex crop canopies. Finally, we discuss future directions for the creation of more comprehensive, benchmark-ready open datasets that will be instrumental in accelerating research, fostering collaboration, and bridging the gap between algorithmic innovation and practical agricultural deployment. This work serves as a foundational guide for researchers and practitioners seeking suitable data for their work and contributes to the ongoing effort of standardizing open data practices in agricultural remote sensing.}, DOI = {10.3390/rs18040659} } @article{BR2025111825, title = {StarNet: Indian star gooseberries dataset for quality and maturity assessment}, journal = {Data in Brief}, volume = {61}, pages = {111825}, year = {2025}, issn = {2352-3409}, doi = {10.1016/j.dib.2025.111825}, url = {https://www.sciencedirect.com/science/article/pii/S2352340925005529}, author = {Pushpa {B. R.} and Manohar N. and N. Shobha Rani}, keywords = {Star gooseberry fruit classification, Deep learning, Machine learning analysis, Quality assessment, Object detection} } @article{UNNIKRISHNAN2026112545, title = {Multimodal perishable fruits and vegetables dataset}, journal = {Data in Brief}, volume = {65}, pages = {112545}, year = {2026}, issn = {2352-3409}, doi = {10.1016/j.dib.2026.112545}, url = {https://www.sciencedirect.com/science/article/pii/S2352340926000983}, author = {Devika Unnikrishnan and Krishna Deepak and Yogini Aishwaryaa {P T S} and Bagyammal T}, keywords = {Fruits classification, Computer vision, Machine learning, Thermal image, Methane gas sensor, Shelf-life prediction, Spoilage detection, Sustainable agriculture, Agriculture 5.0, SDG 2, SDG 12, SDG 13} } @article{AgriDataReuse, author = {Hafner, Alenka and DeLeo, Victoria and Deng, Cecilia and Elsik, Christine and Fleming, Damarius and Harrison, Peter and Kalbfleisch, Theodore and Petry, Bruna and Pucker, Boas and Quezada-Rodríguez, Elsa and Tuggle, Christopher and Koltes, James}, year = {2025}, volume = {14}, journal = {Gigascience}, title = {Data Reuse in Agricultural Genomics Research: Present Challenges and Future Solutions}, doi = {10.20944/preprints202401.0780.v1} } @article{DataReuse, author = {Sielemann, Katharina and Hafner, Alenka and Pucker, Boas}, year = {2020}, month = {09}, pages = {e9954}, title = {The reuse of public datasets in the life sciences: potential risks and rewards}, volume = {8}, journal = {PeerJ}, doi = {10.7717/peerj.9954} } @article{DLinAgri, author = {Kamilaris, Andreas and Prenafeta Boldú, Francesc}, year = {2018}, month = {04}, pages = {}, title = {Deep Learning in Agriculture: A Survey}, volume = {147}, journal = {Computers and Electronics in Agriculture}, doi = {10.1016/j.compag.2018.02.016} } @Article{agriculture12111773, AUTHOR = {Munz, Johannes and Schuele, Heinrich}, TITLE = {Influencing the Success of Precision Farming Technology Adoption—A Model-Based Investigation of Economic Success Factors in Small-Scale Agriculture}, JOURNAL = {Agriculture}, VOLUME = {12}, YEAR = {2022}, NUMBER = {11}, ARTICLE-NUMBER = {1773}, URL = {https://www.mdpi.com/2077-0472/12/11/1773}, ISSN = {2077-0472}, ABSTRACT = {Even more than 30 years after the introduction of precision farming technologies and studies of their benefits in terms of productivity gains and environmental improvements, adoption rates, especially for variable-rate technologies, are very low. In particular, in smallholder areas, farm managers are reluctant to adopt these technologies. Therefore, this study identifies factors that hinder or facilitate adoption from an economic perspective. Using a model-based sensitivity analysis with three farms of different sizes (11 ha, 57 ha and 303 ha), it is shown that larger farms have higher resilience to external factors due to economies of scale. In addition, it is clarified that the certainty of obtaining additional benefits with GPS guidance systems can explain the higher adoption rates in farming practice, although the additional benefits (per hectare and year) are much lower for this technology than for variable-rate technologies. Small farms (>30 ha) are by no means excluded from the use of digital technologies, as it is shown that the influence of learning costs on profitability is very low, low subsidies can lead to a drastic reduction in the minimum farm size and the presence of low-cost technologies is an efficient solution which allows small farms to participate in the digital transformation of agriculture.}, DOI = {10.3390/agriculture12111773} } @article{Matese:2015, author = {Matese, Alessandro and Di Gennaro, Salvatore}, year = {2015}, month = {05}, pages = {}, title = {Technology in precision viticulture: A state of the art review}, volume = {7}, journal = {International Journal of Wine Research}, doi = {10.2147/IJWR.S69405} } @Article{horticulturae9030399, AUTHOR = {Ferro, Massimo Vincenzo and Catania, Pietro}, TITLE = {Technologies and Innovative Methods for Precision Viticulture: A Comprehensive Review}, JOURNAL = {Horticulturae}, VOLUME = {9}, YEAR = {2023}, NUMBER = {3}, ARTICLE-NUMBER = {399}, URL = {https://www.mdpi.com/2311-7524/9/3/399}, ISSN = {2311-7524}, ABSTRACT = {The potential of precision viticulture has been highlighted since the first studies performed in the context of viticulture, but especially in the last decade there have been excellent results have been achieved in terms of innovation and simple application. The deployment of new sensors for vineyard monitoring is set to increase in the coming years, enabling large amounts of information to be obtained. However, the large number of sensors developed and the great amount of data that can be collected are not always easy to manage, as it requires cross-sectoral expertise. The preliminary section of the review presents the scenario of precision viticulture, highlighting its potential and possible applications. This review illustrates the types of sensors and their operating principles. Remote platforms such as satellites, unmanned aerial vehicles (UAV) and proximal platforms are also presented. Some supervised and unsupervised algorithms used for object-based image segmentation and classification (OBIA) are then discussed, as well as a description of some vegetation indices (VI) used in viticulture. Photogrammetric algorithms for 3D canopy modelling using dense point clouds are illustrated. Finally, some machine learning and deep learning algorithms are illustrated for processing and interpreting big data to understand the vineyard agronomic and physiological status. This review shows that to perform accurate vineyard surveys and evaluations, it is important to select the appropriate sensor or platform, so the algorithms used in post-processing depend on the type of data collected. Several aspects discussed are fundamental to the understanding and implementation of vineyard variability monitoring techniques. However, it is evident that in the future, artificial intelligence and new equipment will become increasingly relevant for the detection and management of spatial variability through an autonomous approach.}, DOI = {10.3390/horticulturae9030399} } @article{BECHAR201694, title = {Agricultural robots for field operations: Concepts and components}, journal = {Biosystems Engineering}, volume = {149}, pages = {94-111}, year = {2016}, issn = {1537-5110}, doi = {10.1016/j.biosystemseng.2016.06.014}, url = {https://www.sciencedirect.com/science/article/pii/S1537511015301914}, author = {Avital Bechar and Clément Vigneault}, keywords = {Agricultural robots, Robotics, Field operations, Autonomous}, abstract = {This review investigates the research effort, developments and innovation in agricultural robots for field operations, and the associated concepts, principles, limitations and gaps. Robots are highly complex, consisting of different sub-systems that need to be integrated and correctly synchronised to perform tasks perfectly as a whole and successfully transfer the required information. Extensive research has been conducted on the application of robots and automation to a variety of field operations, and technical feasibility has been widely demonstrated. Agricultural robots for field operations must be able to operate in unstructured agricultural environments with the same quality of work achieved by current methods and means. To assimilate robotic systems, technologies must be developed to overcome continuously changing conditions and variability in produce and environments. Intelligent systems are needed for successful task performance in such environments. The robotic system must be cost-effective, while being inherently safe and reliable—human safety, and preservation of the environment, the crop and the machinery are mandatory. Despite much progress in recent years, in most cases the technology is not yet commercially available. Information-acquisition systems, including sensors, fusion algorithms and data analysis, need to be adjusted to the dynamic conditions of unstructured agricultural environments. Intensive research is needed on integrating human operators into the system control loop for increased system performance and reliability. System sizes should be reduced while improving the integration of all parts and components. For robots to perform in agricultural environments and execute agricultural tasks, research must focus on: fusing complementary sensors for adequate localisation and sensing abilities, developing simple manipulators for each agricultural task, developing path planning, navigation and guidance algorithms suited to environments besides open fields and known a-priori, and integrating human operators in this complex and highly dynamic situation.} } @Article{s22082961, AUTHOR = {Kapetanović, Nadir and Goričanec, Jurica and Vatavuk, Ivo and Hrabar, Ivan and Stuhne, Dario and Vasiljević, Goran and Kovačić, Zdenko and Mišković, Nikola and Antolović, Nenad and Anić, Marina and Kozina, Bernard}, TITLE = {Heterogeneous Autonomous Robotic System in Viticulture and Mariculture: Vehicles Development and Systems Integration}, JOURNAL = {Sensors}, VOLUME = {22}, YEAR = {2022}, NUMBER = {8}, ARTICLE-NUMBER = {2961}, URL = {https://www.mdpi.com/1424-8220/22/8/2961}, PubMedID = {35458946}, ISSN = {1424-8220}, ABSTRACT = {There are activities in viticulture and mariculture that require extreme physical endurance from human workers, making them prime candidates for automation and robotization. This paper presents a novel, practical, heterogeneous, autonomous robotic system divided into two main parts, each dealing with respective scenarios in viticulture and mariculture. The robotic components and the subsystems that enable collaboration were developed as part of the ongoing HEKTOR project, and each specific scenario is presented. In viticulture, this includes vineyard surveillance, spraying and suckering with an all-terrain mobile manipulator (ATMM) and a lightweight autonomous aerial robot (LAAR) that can be used in very steep vineyards where other mechanization fails. In mariculture, scenarios include coordinated aerial and subsurface monitoring of fish net pens using the LAAR, an autonomous surface vehicle (ASV), and a remotely operated underwater vehicle (ROV). All robotic components communicate and coordinate their actions through the Robot Operating System (ROS). Field tests demonstrate the great capabilities of the HEKTOR system for the fully autonomous execution of very strenuous and hazardous work in viticulture and mariculture, while meeting the necessary conditions for the required quality and quantity of the work performed.}, DOI = {10.3390/s22082961} }