Search Results (23)

Accurate multi-level grape counting in natural orchard images provides useful visual information for image-based crop-load characterization and vineyard management. However, cluster overlap, occlusion, boundary adhesion, and illumination variation complicate berry localization and cluster-wise counting. Existing detection- and density-regression-based methods remain susceptible to missed detections, false positives, and cross-cluster misassignment, whereas approaches relying on pixel- or instance-level supervision typically require costly annotations. To address these challenges, this paper proposes UniGC, a unified framework for multi-level grape counting. At the berry level, UniGC employs CSD-P2PNet, a P2PNet-based point-regression branch equipped with a Condition-Structure Decoupled Frequency Enhancement Block (CSD-Block), to improve the localization and counting of image-visible berries under complex illumination and occlusion using only berry point annotations. At the cluster level, a You Only Look Once (YOLO) detector predicts grape-cluster bounding boxes, which are used as prompts for the Segment Anything Model (SAM) to generate cluster instance masks. We further propose Boundary-Depth Guided Mask-Point Assignment (BDMPA), which assigns each predicted berry point to at most one grape-cluster instance and thereby produces cluster-wise berry counts. Selected key experiments on the mixed dataset organized from WGISD and GBISC were repeated using three random seeds. CSD-P2PNet achieved an MAE of 23.4407 ± 0.1577, an RMSE of 32.8898 ± 1.2682, and a point-localization F1 score of 0.8374 ± 0.0097. YOLO12-S achieved an F1 score of 0.8433 ± 0.0056 and an AP50 of 0.8789 ± 0.0080 for grape-cluster detection. For BpGC counting, UniGC obtained a matched-cluster MRD of 0.1288 ± 0.0043, a $1-\mathrm{FVU}$ of 0.8589 ± 0.0098, and an all-cluster penalized mean relative deviation (ACP-MRD) of 0.5062 ± 0.0124. These results demonstrate that UniGC achieves competitive multi-level grape counting performance while requiring only point and bounding-box annotations for training. Full article

Berry thinning is a fundamental operation in modern vineyard management, and future robotic thinning systems have the potential to reduce labor intensity and improve operational consistency. However, automated berry thinning under field conditions is still constrained by insufficient berry-level segmentation accuracy, difficulty in recognizing occluded berries, and high missed-detection rates for small berries. These limitations mainly arise from dense berry arrangements, severe mutual occlusion, and the subtle visual features of small targets. To address these challenges, this study developed a lightweight grape berry instance segmentation and thinning decision-support method based on YOLOv8n-seg. A two-stage knowledge distillation strategy, using Mask R-CNN and YOLOv8l-seg as teacher models, was combined with 30% backbone pruning to improve the recognition of occluded and small berries while maintaining model efficiency. Subsequently, the DBSCAN clustering algorithm was used to analyze berry centroid coordinates and equivalent diameters extracted from instance segmentation masks, thereby generating preliminary thinning-target recommendations based on local berry density and berry size. The model was trained and evaluated on a self-constructed dataset containing 330 valid grape bunch images collected in 2025 from Yongming Vineyard, Lin’an District, Hangzhou, Zhejiang Province, China. The results showed that the optimized YOLOv8n-seg model achieved a box $mAP50\text{-}95$ of 0.8945 and a mask $mAP50\text{-}95$ of 0.7910, with an inference speed of 119.19 $FPS$ and 3.26 M parameters on an NVIDIA RTX 3060 Laptop GPU. Compared with the original YOLOv8n-seg model, the optimized model improved mask $mAP50\text{-}95$ by 1.20 percentage points, increased inference speed by 71.79 $FPS$, and reduced the number of parameters by 2.38 M. These results indicate that the proposed method improves grape berry instance segmentation performance while achieving a favorable balance among segmentation accuracy, lightweight characteristics, and inference efficiency. The proposed framework provides an offline RGB-based visual perception and preliminary thinning decision-support method for future grape berry thinning robots. However, because the current dataset was collected from Shine Muscat grape bunches at the berry enlargement stage in a single vineyard using the same imaging setup, the results should be interpreted as preliminary evidence under the specific cultivar, growth stage, vineyard, and imaging conditions of this study. Further validation across different grape cultivars, growth stages, vineyards, production seasons, camera systems, embedded platforms, and real robotic thinning operations is still required. Full article

Winter pruning is a key management practice in viticulture that directly affects vine architecture, yield balance, and grape quality. At the same time, it is a highly labor-intensive operation, and the selective identification of appropriate cutting locations remains one of the main challenges limiting the automation of pruning in vineyards. Advances in machine vision provide new opportunities to support the development of robotic pruning systems. The objective of this study was to develop and evaluate a vision-based method for estimating grapevine pruning points and cutting lines using instance segmentation outputs generated by YOLO models. A dataset of 1500 RGB images of dormant grapevines was collected under field conditions in the Nobilis vineyard located in southeastern Poland. Two annotation strategies were implemented to define pruning regions. YOLO-based instance segmentation models were trained and evaluated for detecting cutting-related structures. Based on the predicted segmentation masks, a geometry-based method termed PCAcutSeg-V was developed to estimate class-dependent cutting points and cutting lines using principal component analysis applied to object contours. The results indicate that YOLOv8 and YOLO11 architectures achieved the highest segmentation performance among the evaluated models. The simplified annotation strategy provided more stable geometric inputs for the PCAcutSeg-V method, enabling more reliable estimation of cutting points and cutting lines compared with the extended annotation approach. When combined with the PCAcutSeg-V method, the proposed perception–geometry pipeline achieved high effectiveness in pruning decision estimation. The method was further implemented in a real-time processing pipeline using an RGB camera and an edge computing platform, where it maintained performance consistent with the results obtained from offline image analysis. These findings demonstrate that combining deep learning-based instance segmentation with deterministic geometric reasoning enables accurate and interpretable estimation of grapevine pruning locations and provides a promising foundation for future autonomous pruning systems. Full article

The rapid and reliable acquisition of canopy-related metrics is essential for improving decision support in viticultural management, particularly when monitoring individual vines for targeted interventions. This study presents a spatially explicit workflow that integrates Uncrewed Aerial System (UAS) imagery, 3D point-cloud analysis, and Object-Based Image Analysis (OBIA) to detect and monitor individual grapevines throughout the growing season. Vines are identified directly from 3D point clouds without the need for prior training data or predefined row structures, achieving a mean Euclidean distance of 10.7 cm to the reference points. The OBIA framework segments vine vegetation based on spectral and geometric features without requiring pre-clipping or manual masking. All non-vine elements—including soil, grass, and infrastructure—are automatically excluded, and detailed canopy masks are created for each plant. Vegetation indices are computed exclusively from vine canopy objects, ensuring that soil signals and internal canopy gaps do not bias the results. This enables accurate per-vine assessment of vigour. NDRE values were calculated at three phenological stages—flowering, veraison, and harvest—and analyzed using Local Indicators of Spatial Association (LISA) to detect spatial clusters and outliers. In contrast to value-based clustering methods, LISA accounts for spatial continuity and neighborhood effects, allowing the detection of stable low-vigour zones, expanding high-vigour clusters, and early identification of isolated stressed vines. A strong correlation (R² = 0.73) between per-vine NDRE values and actual yield demonstrates that NDRE-derived vigour reliably reflects vine productivity. The method provides a transferable, data-driven framework for site-specific vineyard management, enabling timely interventions at the individual plant level before stress propagates spatially. Full article

The development of robots for automatic pruning of vineyards using deep learning techniques seems feasible in the medium term. In this context, it is essential to propose and study solutions that can be deployed on portable hardware, with artificial intelligence capabilities but reduced computing power. In this paper, we propose a novel approach to vineyard pruning by direct detection of cutting areas in real time by comparing Mask R-CNN and YOLOv8 performances. The studied object segmentation architectures are able to segment the image by locating the trunk, and pruned and not pruned vine shoots. Our study analyzes the performance of both frameworks in terms of segmentation efficiency and inference times on a Jetson AGX Orin GPU. To compare segmentation efficiency, we used the mAP50 and AP50 per category metrics. Our results show that YOLOv8 is superior both in segmentation efficiency and inference time. Specifically, YOLOv8-S exhibits the best tradeoff between efficiency and inference time, showing an mAP50 of 0.883 and an AP50 of 0.748 for the shoot class, with an inference time of around 55 ms on a Jetson AGX Orin. Full article

This study delves into the analysis of a vineyard in Carinthia, Austria, focusing on the automated derivation of ecosystem structures of individual vine parameters, including vine heights, leaf area index (LAI), leaf surface area (LSA), and the geographic positioning of single plants. For the derivation of these parameters, intricate segmentation processes and nuanced UAS-based data acquisition techniques are necessary. The detection of single vines was based on 3D point cloud data, generated at a phenological stage in which the plants were in the absence of foliage. The mean distance from derived vine locations to reference measurements taken with a GNSS device was 10.7 cm, with a root mean square error (RMSE) of 1.07. Vine height derivation from a normalized digital surface model (nDSM) using photogrammetric data showcased a strong correlation (R² = 0.83) with real-world measurements. Vines underwent automated classification through an object-based image analysis (OBIA) framework. This process enabled the computation of ecosystem structures at the individual plant level post-segmentation. Consequently, it delivered comprehensive canopy characteristics rapidly, surpassing the speed of manual measurements. With the use of uncrewed aerial systems (UAS) equipped with optical sensors, dense 3D point clouds were computed for the derivation of canopy-related ecosystem structures of vines. While LAI and LSA computations await validation, they underscore the technical feasibility of obtaining precise geometric and morphological datasets from UAS-collected data paired with 3D point cloud analysis and object-based image analysis. Full article

The invasive morning glory, Ipomoea purpurea (Convolvulaceae), poses a mounting challenge in vineyards by hindering grape harvest and as a secondary host of disease pathogens, necessitating advanced detection and control strategies. This study introduces a novel automated image analysis framework using aerial images obtained from a small fixed-wing unmanned aircraft system (UAS) and an RGB camera for the large-scale detection of I. purpurea flowers. This study aimed to assess the sampling fidelity of aerial detection in comparison with the actual infestation measured by ground validation surveys. The UAS was systematically operated over 16 vineyard plots infested with I. purpurea and another 16 plots without I. purpurea infestation. We used a semi-supervised segmentation model incorporating a Gaussian Mixture Model (GMM) with the Expectation-Maximization algorithm to detect and count I. purpurea flowers. The flower detectability of the GMM was compared with that of conventional K-means methods. The results of this study showed that the GMM detected the presence of I. purpurea flowers in all 16 infested plots with 0% for both type I and type II errors, while the K-means method had 0% and 6.3% for type I and type II errors, respectively. The GMM and K-means methods detected 76% and 65% of the flowers, respectively. These results underscore the effectiveness of the GMM-based segmentation model in accurately detecting and quantifying I. purpurea flowers compared with a conventional approach. This study demonstrated the efficiency of a fixed-wing UAS coupled with automated image analysis for I. purpurea flower detection in vineyards, achieving success without relying on data-driven deep-learning models. Full article

This article describes an experimentally tested approach using semi-supervised learning for generating new datasets for semantic segmentation of vine trunks with very little human-annotated data, resulting in significant savings in time and resources. The creation of such datasets is a crucial step towards the development of autonomous robots for vineyard maintenance. In order for a mobile robot platform to perform a vineyard maintenance task, such as suckering, a semantically segmented view of the vine trunks is required. The robot must recognize the shape and position of the vine trunks and adapt its movements and actions accordingly. Starting with vine trunk recognition and ending with semi-supervised training for semantic segmentation, we have shown that the need for human annotation, which is usually a time-consuming and expensive process, can be significantly reduced if a dataset for object (vine trunk) detection is available. In this study, we generated about 35,000 images with semantic segmentation of vine trunks using only 300 images annotated by a human. This method eliminates about 99% of the time that would be required to manually annotate the entire dataset. Based on the evaluated dataset, we compared different semantic segmentation model architectures to determine the most suitable one for applications with mobile robots. A balance between accuracy, speed, and memory requirements was determined. The model with the best balance achieved a validation accuracy of 81% and a processing time of only 5 ms. The results of this work, obtained during experiments in a vineyard on karst, show the potential of intelligent annotation of data, reducing the time required for labeling and thus paving the way for further innovations in machine learning. Full article

The ‘Kyoho’ (Vitis labruscana) grape is one of the mainly fresh fruits; it is important to accurately segment the grape bunch and to detect its maturity level for the construction of an intelligent grape orchard. Grapes in the natural environment have different shapes, occlusion, complex backgrounds, and varying illumination; this leads to poor accuracy in grape maturity detection. In this paper, an improved Mask RCNN-based algorithm was proposed by adding attention mechanism modules to establish a grape bunch segmentation and maturity level detection model. The dataset had 656 grape bunches of different backgrounds, acquired from a grape growing environment of natural conditions. This dataset was divided into four groups according to maturity level. In this study, we first compared different grape bunch segmentation and maturity level detection models established with YoloV3, Solov2, Yolact, and Mask RCNN to select the backbone network. By comparing the performances of the different models established with these methods, Mask RCNN was selected as the backbone network. Then, three different attention mechanism modules, including squeeze-and-excitation attention (SE), the convolutional block attention module (CBAM), and coordinate attention (CA), were introduced to the backbone network of the ResNet50/101 in Mask RCNN, respectively. The results showed that the mean average precision (mAP) and mAP_0.75 and the average accuracy of the model established with ResNet101 + CA reached 0.934, 0.891, and 0.944, which were 6.1%, 4.4%, and 9.4% higher than the ResNet101-based model, respectively. The error rate of this model was 5.6%, which was less than the ResNet101-based model. In addition, we compared the performances of the models established with MASK RCNN, adding different attention mechanism modules. The results showed that the mAP and mAP_0.75 and the accuracy for the Mask RCNN50/101 + CA-based model were higher than those of the Mask RCNN50/101 + SE- and Mask RCNN50/101 + CBAM-based models. Furthermore, the performances of the models constructed with different network layers of ResNet50- and ResNet101-based attention mechanism modules in a combination method were compared. The results showed that the performance of the ResNet101-based combination with CA model was better than the ResNet50-based combination with CA model. The results showed that the proposed model of Mask RCNN ResNet101 + CA was good for capturing the features of a grape bunch. The proposed model has practical significance for the segmentation of grape bunches and the evaluation of the grape maturity level, which contributes to the construction of intelligent vineyards. Full article

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. Full article

Characterizing the association of endophytic insect pathogenic fungi (EIPF) with plants is an important step in order to understand their ecology before using them in biological control programs. Since several methods are available, it is challenging to identify the most appropriate for such investigations. Here, we used two strains of Metarhizium robertsii: EF3.5(2) native to the French vineyard environment and ARSEF-2575-GFP a laboratory strain expressing a green fluorescent protein, to compare their potential of association with non-grafted grapevine Vitis vinifera. Three methods were used to evaluate the kinetics of rhizosphere and grapevine endospheric colonization: (i) Droplet Digital (ddPCR), a sensitive molecular method of M. robertsii DNA quantification in different plant parts, (ii) culture-based method to detect the live fungal propagules from plant tissues that grew on the medium, (iii) confocal imaging to observe roots segments. Both strains showed evidence of establishment in the rhizosphere of grapevines according to the culture-based and ddPCR methods, with a significantly higher establishment of strain EF3.5(2) (40% positive plants and quantified median of exp(4.61) c/μL) compared to strain ARSEF-2575-GFP (13% positive plants and quantified median of exp(2.25) c/μL) at 96–98 days post-inoculation. A low incidence of association of both strains in the grapevine root endosphere was found with no significant differences between strains and evaluation methods (15% positive plants inoculated with strain EF3.5(2) and 5% with strain ARSEF-2575-GFP according to culture-based method). ddPCR should be used more extensively to investigate the association between plants and EIPF but always accompanied with at least one method such as culture-based method or confocal microscopy. Full article

Pin nematodes (Paratylenchus spp.) currently comprise 132 species of polyphagous plant ectoparasites with at least seven species that are plant pathogenic emphasizing the need for correct identification to establish an appropriate management strategy. Sequences of highly conserved regions of ribosomal and mitochondrial RNA genes are a powerful species-level diagnostic tool within Tylenchulidae. A nematological survey was conducted from 2019 to 2021 in commercial vineyards distributed in four major wine-producing regions in the Central and South Portugal. Nine populations of Paratylenchus spp. were isolated from the rhizosphere of grapevines that were characterized from morphological data and molecular phylogenetic analysis using two rRNA genes (D2–D3 expansion segments of the 28S, and partial 18S) and a region partial of the COI mtRNA gene. Contrasting morphological hypotheses with molecular data provided rapid detection of six species, specifically P. goodeyi, P. hamatus, P. pedrami, P. tenicaudatus, P. variabilis, and P. veruculatus. Bayesian inference (BI) phylogenetic trees for these molecular markers established phylogenetic relationships underscore the importance of using genomic and molecular phylogenetic data for accurate pin nematode identification at the species level. To our knowledge, this is the first report of Paratylenchus spp. in Portugal, extending the geographical distribution of these species in the Mediterranean Basin, and the first record of P. goodeyi, P. pedrami, P.variabilis, P. veruculatus and P. tenicaudatus parasitizing grapevine. Full article

Yield assessment has been identified as critical topic for grape and wine industry. Computer vision has been applied for assessing yield, but the accuracy was greatly affected by fruit occlusion affected by leaves and other plant organs. The objective of this work was the consistent, continuous evaluation of the impact of leaf occlusions in different commercial vineyard plots at different defoliation stages. RGB (red, green and blue) images from five Tempranillo (Vitis vinifera L.) vineyards were manually acquired using a digital camera under field conditions at three different levels of defoliation: no defoliation, partial defoliation and full defoliation. Computer vision was used for the automatic detection of different canopy features, and for the calibration of regression equations for the prediction of yield computed per vine segment. Leaf occlusion rate (berry occlusion affected by leaves) was computed by machine vision in no defoliated vineyards. As occlusion rate increased, R² between bunch pixels and yield was gradually reduced, ranging from 0.77 in low occlusion, to 0.63. Full article

The increasing alarming impacts of climate change are already apparent in viticulture, with unexpected pest outbreaks as one of the most concerning consequences. The monitoring of pests is currently done by deploying chromotropic and delta traps, which attracts insects present in the production environment, and then allows human operators to identify and count them. While the monitoring of these traps is still mostly done through visual inspection by the winegrowers, smartphone image acquisition of those traps is starting to play a key role in assessing the pests’ evolution, as well as enabling the remote monitoring by taxonomy specialists in better assessing the onset outbreaks. This paper presents a new methodology that embeds artificial intelligence into mobile devices to establish the use of hand-held image capture of insect traps for pest detection deployed in vineyards. Our methodology combines different computer vision approaches that improve several aspects of image capture quality and adequacy, namely: (i) image focus validation; (ii) shadows and reflections validation; (iii) trap type detection; (iv) trap segmentation; and (v) perspective correction. A total of 516 images were collected, divided into three different datasets and manually annotated, in order to support the development and validation of the different functionalities. By following this approach, we achieved an accuracy of 84% for focus detection, an accuracy of 80% and 96% for shadows/reflections detection (for delta and chromotropic traps, respectively), as well as mean Jaccard index of 97% for the trap’s segmentation. Full article

New technologies for management, monitoring, and control of spatio-temporal crop variability in precision viticulture scenarios are numerous. Remote sensing relies on sensors able to provide useful data for the improvement of management efficiency and the optimization of inputs. unmanned aerial systems (UASs) are the newest and most versatile tools, characterized by high precision and accuracy, flexibility, and low operating costs. The work aims at providing a complete overview of the application of UASs in precision viticulture, focusing on the different application purposes, the applied equipment, the potential of technologies combined with UASs for identifying vineyards’ variability. The review discusses the potential of UASs in viticulture by distinguishing five areas of application: rows segmentation and crop features detection techniques; vineyard variability monitoring; estimation of row area and volume; disease detection; vigor and prescription maps creation. Technological innovation and low purchase costs make UASs the core tools for decision support in the customary use by winegrowers. The ability of the systems to respond to the current demands for the acquisition of digital technologies in agricultural fields makes UASs a candidate to play an increasingly important role in future scenarios of viticulture application. Full article