Search

International audience; Portable mid-infrared spectroscopy (pMIRS) combined with machine learning was used to predict selected parameters for soil organic carbon (SOC) storage. In particular, SOC, soil inorganic C (SIC), hot-water extractable C (hwC), clay and sand content were predicted for ten vineyards with varying geopedological settings. As a pre-test, spectra were collected from sieved and pressed tablets with 30 and 90 kPa respectively and compared to powdery samples in order to optimise sample preparation. Further, spectra from 30 kPa tablets were used to calibrate prediction models for a sample set (n = 540) of 10 vineyards with pronounced geopedological variation using Support Vector Machines (SVM). The calibrated SVM models performed well with R2 = 0.81–0.98 and RPIQ = 5.20–13.0 for all investigated parameters. Third, two years after the calibration samples, follow-up samples were collected from four of the vineyards. While the models performed excellent for hwC (R2 = 0.93), prediction accuracy for SOC was lower. Segmentation of the total dataset into SIC-free and SIC-containing samples resulted in better predictions of SOC of the first sampling period. For the prediction of the follow-up sampling dates, model performance could not be maintained. We conclude that pMIRS-SVM calibrations are suited for the prediction of parameters related to soil C storage under varying geopedological conditions and may provide potential for future C monitoring. Extending the database with additional samples from geopedological scenarios not included in this dataset may strengthen model robustness and help to evaluate effects of SIC content on model performance.

Over the last few years, an extensive set of technologies have been systematically included in precision agriculture (PA) and also in precision viticulture (PV) practices, as tools that allow efficient monitoring of nearly any parameter to achieve sustainable crop management practices and to increase both crop yield and quality. However, many technologies and standards are not yet included on those practices. Therefore, potential benefits that may result from putting together agronomic knowledge with electronics and computer technologies are still not fully accomplished. Both emergent and established paradigms, such as the Internet of Everything (IoE), Internet of Things (IoT), cloud and fog computing, together with increasingly cheaper computing technologies – with very low power requirements and a diversity of wireless technologies, available to exchange data with increased efficiency – and intelligent systems, have evolved to a level where it is virtually possible to expeditiously create and deploy any required monitoring solution. Pushed by all of these technological trends and recent developments, data integration has emerged as the layer between crops and knowledge needed to efficiently manage it. In this paper, the mySense environment is presented, aimed to systematize data acquisition procedures to address common PA/PV issues. mySense builds over a 4-layer technological structure: sensor and sensor nodes, crop field and sensor networks, cloud services and support to front-end applications. It makes available a set of free tools based on the Do-It-Yourself (DIY) concept and enables the use of Arduino® and Raspberry Pi (RPi) low-cost platforms to quickly prototype a complete monitoring application. Field experiments provide compelling evidences that mySense environment represents an important step forward towards Smart Farming, by enabling the use of low-cost, fast deployment, integrated and transparent technologies to increase PA/PV monitoring applications adoption.

One of the key steps that would lead winegrowers to implement precision viticulture as a management tool would be the clear demonstration of the agronomic and oenological significance of the zones delineated within a vineyard based, totally or partially, on remote-acquired information. To perform this analysis, it is necessary to compare image-derived variables to crop characteristics. Classical ordinary least square (OLS) regression is not well suit for spatially structured data, while Moran’s index (MI) and local indicators of spatial autocorrelation (LISA) take autocorrelation into account. The aim of this work was to evaluate the performance of statistical methods to compare different maps of a vineyard, some including variables derived from UAV acquired imagery, and some from in situ ground characterization. The study was conducted during 2015 and 2016 seasons in an adult 7.5 ha cv. ‘Tempranillo’ vineyard located in Traibuenas, Navarra, Spain. The maps obtained out of UAV-imagery, volume index (VI) and normalized difference vegetation index (NDVI) were compared to the maps obtained for the agronomic variables measured (yield, berry weight and total soluble solids). The bivariate MI and the bivariate LISA cluster map obtained using Geoda software indicate depict the spatial cluster association between variables in 2015 and 2016 with different types of local spatial autocorrelation. The use of these methods that take into account data spatial structure, to compare ground autocorrelated data and spectral and geometric information derived from UAV-acquired imagery has been proved to be highly necessary and advisable.

Diseases and pests cause serious damage in crop production, reducing yield and fruit quality. Their identification is often time-consuming and requires trained personnel. New sensing technologies and artificial intelligence could be used for automatic identification of disease and pest symptoms on grapevine in precision viticulture. The aim of this work was to apply deep learning modelling and computer vision for the detection and differentiation of downy mildew and spider mite symptoms in grapevine leaves under field conditions. RGB images of grapevine canopy leaves with downy mildew symptoms, with spider mite symptoms and without symptoms were taken under field conditions in a commercial vineyard. The images were prepared using computer vision techniques to increase disease visual features. Finally, deep learning was used to train a model capable of differentiating leaf images of the three classes. An accuracy up to 0.94 (F1-score of 0.94) was obtained by classifying leaves with downy mildew, spider mite and without symptoms at the same time, using a hold-out validation. Additionally, accuracies between 0.89 and 0.91 (F1-scores between 0.89 and 0.91) were obtained in the binary classification of the disease and pest, obtaining the best results in differentiating downy mildew from spider mite symptoms. This high accuracy demonstrates the effectiveness of deep learning and computer vision techniques for the classification of grapevine leaf images taken under field conditions, automatically finding complex features capable of differentiating leaves with spider mite symptoms, with downy mildew symptoms and without any. These results prove the potential of these non-invasive techniques in the detection and differentiation of pests and diseases in commercial crop production.

Precise and reliable identification of specific plant diseases is a challenge within precision agriculture nowadays. This is the case of esca, a complex grapevine trunk disease, that represents a major threat to modern viticulture as it is responsible for large economic losses annually. The lack of effective control strategies and the complexity of esca disease expression make essential the identification of affected plants, before symptoms become evident, for a better management of the vineyard. This study evaluated the suitability of a near-infrared hyperspectral imaging (HSI) system to detect esca disease in asymptomatic grapevine leaves of Tempranillo red-berried cultivar. For this, 72 leaves from an experimental vineyard, naturally infected with esca, were collected and scanned with a lab-scale HSI system in the 900-1700 nm spectral range. Then, effective image processing and multivariate analysis techniques were merged to develop pixel-based classification models for the distinction of healthy, asymptomatic and symptomatic leaves. Automatic and interval partial least squares variable selection methods were tested to identify the most relevant wavelengths for the detection of esca-affected vines using partial least squares discriminant analysis and different pre-processing techniques. Three-class and two-class classifiers were carried out to differentiate healthy, asymptomatic and symptomatic leaf pixels, and healthy from asymptomatic pixels, respectively. Both variable selection methods performed similarly, achieving good classification rates in the range of 82.77-97.17% in validation datasets for either three-class or two-class classifiers. The latter results demonstrated the capability of hyperspectral imaging to distinguish two groups of seemingly identical leaves (healthy and asymptomatic). These findings would ease the annual monitoring of disease incidence in the vineyard and, therefore, better crop management and decision making. This research was supported by Public University of Navarre postgraduate scholarships (FPI-UPNA-2017), by the Spanish Ministry of Economy and Competitiveness (AGL2017-83738-C3-1R, AEI/EU-FEDER), and by the Spanish Ministry of Science, Innovation and Universities (PID2019-108392GB-I00, AEI/10.13039/ 501100011033).

An effective management of precision viticulture processes relies on robust crop monitoring procedures and, in the near future, to autonomous machine for automatic site-specific crop managing. In this context, the exact detection of vineyards from 3D point-cloud maps, generated from unmanned aerial vehicles (UAV) multispectral imagery, will play a crucial role, e.g. both for achieve enhanced remotely sensed data and to manage path and operation of unmanned vehicles. In this paper, an innovative unsupervised algorithm for vineyard detection and vine-rows features evaluation, based on 3D point-cloud maps processing, is presented. The main results are the automatic detection of the vineyards and the local evaluation of vine rows orientation and of inter-rows spacing. The overall point-cloud processing algorithm can be divided into three mains steps: (1) precise local terrain surface and height evaluation of each point of the cloud, (2) point-cloud scouting and scoring procedure on the basis of a new vineyard likelihood measure, and, finally, (3) detection of vineyard areas and local features evaluation. The algorithm was found to be efficient and robust: reliable results were obtained even in the presence of dense inter-row grassing, many missing plants and steep terrain slopes. Performances of the algorithm were evaluated on vineyard maps at different phenological phase and growth stages. The effectiveness of the developed algorithm does not rely on the presence of rectilinear vine rows, being also able to detect vineyards with curvilinear vine row layouts.

In viticulture, there are several applications where 3D bud detection and localization in vineyards is a necessary task susceptible to automation: measurement of sunlight exposure, autonomous pruning, bud counting, type-of-bud classification, bud geometric characterization, internode length, and bud development stage. This paper presents a workflow to achieve quality 3D localizations of grapevine buds based on well-known computer vision and machine learning algorithms when provided with images captured in natural field conditions (i.e., natural sunlight and the addition of no artificial elements), during the winter season and using a mobile phone RGB camera. Our pipeline combines the Oriented FAST and Rotated BRIEF (ORB) for keypoint detection, a Fast Local Descriptor for Dense Matching (DAISY) for describing the keypoint, and the Fast Approximate Nearest Neighbor (FLANN) technique for matching keypoints, with the Structure from Motion multi-view scheme for generating consistent 3D point clouds. Next, it uses a 2D scanning window classifier based on Bag of Features and Support Vectors Machine for classification of 3D points in the cloud. Finally, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) for 3D bud localization is applied. Our approach resulted in a maximum precision of 1.0 (i.e., no false detections), a maximum recall of 0.45 (i.e. 45% of the buds detected), and a localization error within the range of 259–554 pixels (corresponding to approximately 3 bud diameters, or 1.5 cm) when evaluated over the whole range of user-given parameters of workflow components. Fil: Díaz, Carlos Ariel. Universidad Tecnológica Nacional. Facultad Regional Mendoza. Departamento de Sistemas de Información. Laboratorio DHARMA; Argentina Fil: Pérez, Diego Sebastián. Universidad Tecnológica Nacional. Facultad Regional Mendoza. Departamento de Sistemas de Información. Laboratorio DHARMA; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina Fil: Miatello, Humberto. New Lab; Estados Unidos Fil: Bromberg, Facundo. Universidad Tecnológica Nacional. Facultad Regional Mendoza. Departamento de Sistemas de Información. Laboratorio DHARMA; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas. Centro Científico Tecnológico Conicet - Mendoza; Argentina

The quality of grapes and the drying process has a momentous impact on the quality of the final products (raisins). South Azerbaijan is the most important region for grape growing and raisin producing. However, the majority of the vineyards in the region are traditional, and the drying process is carried out in conventional structures that are not convenient. To increase the quality and productivity, it is necessary to modernize agricultural practices with reasonable cost suitable and affordable to traditional farming and farmers. To do this, the harsh environments and severe climate conditions of the vineyards and the drying buildings should be observed periodically to collect data. Wireless Sensor Networks are a key technology that can provide precise information, can update information, and can be a valuable resource to farmers to determine appropriate management practices. Using this technology, farmers can make real-time decisions such as scheduling irrigation periods, preventing diseases, choosing the right time for harvesting and so on. In this project, a Wireless Sensor Network system was designed and developed for remote real-time monitoring and collection of micrometeorological parameter data in three distant vineyards. The system was also used for monitoring the SO2 gas fumigation process and atmospheric parameters inside the drying structure. The system consists of a gateway and a series of peripheral wireless motes placed in the vineyards and inside the drying structure, which are equipped with agrometeorological sensors for environmental monitoring and for storing and transmitting data to the gateway. The gateway collects agrometeorological data and utilizes a wireless technology for data transmission and for communication between the motes and the central server (webpage). In addition, an on-line (real-time) warning system was embedded in the gateway to send alarm signals via SMS (Short Message Service). The devices were tested for software configuration functionality, hardware operation and data acquisition, energy consumption, and connectivity. Field experiment results demonstrated that the system represents a complete monitoring system, which provides efficient performance for developing information systems in precision viticulture.

The growth and collection of grapes or Viticulture is essential for producing various consumer products. Herein, we identified patents registered in the viticulture and wine areas, extracted specific information such as the applicant, country of origin and patent classification and analyzed the collected data. The filing frequencies and maps according to country and applicant were generated. Our analysis revealed two large patent groups and demonstrated that China is the top patent-producing country, rapidly acquiring substantial viticulture-related intellectual property. This study provides insights into the state of the art in viticulture and could be also be used to evaluate other business sectors.

The world of viticulture connected to wine making has become a very important activity in many inland areas permitting both the generation of important income and the sustaining of agriculture systems. Recent progress in both crop modeling and Decision Support Systems (DSS) applied to viticulture promises important changes that combine both high quality production and environmental sustainability. However, most of this progress is only addressed at the farm level and does not challenge the viticulture landscape, which is a key issue when facing DOC, DOCG areas, wine growers' cooperatives and consortiums and strategic viticulture planning. Thus, this paper aims to demonstrate that a new type of DSS, which is developed on a Geospatial Cyberinfrastructure (GCI) platform, may provide an important web-based operational tool for high quality viticulture as it connects farm and landscape levels better. The GCI platform supports acquisition, management, processing of both static and dynamic data (e.g. pedological, daily climatic, and vineyard distribution), data visualization, and on-the-fly computer applications in order to perform simulation modeling (e.g. grapevine water stress, evaluation of ecosystem services, etc.). These are all potentially accessible via the Web. This is possible thanks to the implementation of a set of modeling clusters that is strongly rooted in soil-plant-atmosphere and physically based simulation modeling. The DSS tool, applied to an area of 20,000 ha in Southern Italy, is designed to address viticulture planning and management by providing operational support for farmers, farmer associations and decision makers involved in the viticulture landscape. Output of the system includes viticulture planning and management scenario analysis, maps and evaluation of potential and current plant water stress. The tool will also be demonstrated through a short selection of practical case studies.

In viticulture, there are several applications where bud detection in vineyard images is a necessary task, susceptible of being automated through the use of computer vision methods. A common and effective family of visual detection algorithms are the scanning-window type, that slide a (usually) fixed size window along the original image, classifying each resulting windowed-patch as containing or not containing the target object. The simplicity of these algorithms finds its most challenging aspect in the classification stage. Interested in grapevine buds detection in natural field conditions, this paper presents a classification method for images of grapevine buds ranging 100–1600 pixels in diameter, captured in outdoor, under natural field conditions, in winter (i.e., no grape bunches, very few leaves, and dormant buds), without artificial background, and with minimum equipment requirements. The proposed method uses well-known computer vision technologies: Scale-Invariant Feature Transform for calculating low-level features, Bag of Features for building an image descriptor, and Support Vector Machines for training a classifier. When evaluated over images containing buds of at least 100 pixels in diameter, the approach achieves a recall higher than 0.9 and a precision of 0.86 over all windowed-patches covering the whole bud and down to 60% of it, and scaled up to window patches containing a proportion of 20–80% of bud versus background pixels. This robustness on the position and size of the window demonstrates its viability for use as the classification stage in a scanning-window detection algorithms. Fil: Pérez, Diego Sebastián. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Tecnológica Nacional; Argentina. Universidad Nacional de Cuyo; Argentina Fil: Bromberg, Facundo. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad Tecnológica Nacional; Argentina Fil: Díaz, Carlos Ariel. Universidad Tecnológica Nacional; Argentina

This research aims to test the discrimination of homogenized areas in traditional Galician vineyards of Vitis vinifera (L.) cv. Albarino, using a vegetation index and soil electrical conductivity and their relations with plant and soil measures (stem water potential and soil water content) and productivity and quality parameters. The study was conducted in a 4.8 ha commercial vineyard ( Vitis vinifera L., cv. Albarino) located in Galicia (Spain). The trellis system was ‘emparrado’, typical in this region, at 1.8 m in elevation; the vines were trained to quadrilateral cordons leaving 6–8 buds per spur. Several irrigation treatments – irrigation from flowering to harvest and irrigation from budburst to harvest- were conducted during the 2015 season, where a rainfed treatment was used as the control. Images acquisition – R, G and NIR bands – was developed in veraison using an unmanned aerial vehicle. Moreover, apparent electrical conductivity (EC a ) was measured in winter using a soil electrical conductivity metre (EM38) in a horizontal dipole. Soil water content measurements during veraison showed statistical significance differences between irrigation treatments ( p -value = 0.014) but none in the stem water potential ( p -value = 0.19). No significant differences were observed for production parameters. However, random forest models allowed a good estimation of stem water potential and quality parameters using topographic, soil and plant variables. NDVI details analysed, using a spherical buffer showed significant differences between treatments, especially for minimum and average NDVI pixel values. The process applied showed the capacity to discriminate between different quality grapes areas in a pergola trellis vineyards. This allows to winegrowers to have a selected vintage for several wine purposes as well as, a tool for irrigation management.

International audience; This article introduces a dataset of high-resolution colour images of grapevines. It contains 99 images acquired in the vineyard from a cruising tractor. Each image includes the full foliage of a grapevine plant. These images display a diverse range of symptoms caused by the grapevine downy mildew (Plasmopara viticola), a major fungal disease. The dataset also includes various confounding factors, i.e. anomalies that are not related to the disease. These anomalies are the natural and common phenomena affecting vineyards such as results of mechanical wounds, necroses, chemical burns or yellowing and discolorations due to nutritional or hydric deficiencies. Images were acquired in-situ on “Le Domaine de la Grande Ferrade” a public experimental facility of INRAE, in the area of Bordeaux. Acquisitions took place at early fruiting stages (BBCH 75-79) corresponding to the main sanitary pressure during growth. The acquisition device, embedded on a vine tractor, is composed of an industrial colour camera synchronised with powerful flashes. The purpose of this device is to produce a “day for night” effect that mitigates the variation of sunlight. It enables to homogenise images acquired during different weathers and time of the day and to ensure that the foreground (containing foliage) displays appropriate brightness, with minimum shadows while the background is darker. The images of the dataset were annotated manually by photo-interpretation with a careful review of expertise regarding phytopathology and physiological disorders. The annotation process consists in associating pixels with a class that defines its membership to a type of organ and its physiological state. Pixels from healthy, symptomatic or abnormal grapevine tissues were labelled into seven classes: “Limbus”, “Leaf edges”, “Berries”, “Stems”, “Foliar mildew”, “Berries mildew” and “Anomalies”. The annotation is achieved with the GIMP2 software as mask images where the value attributed to each pixel corresponds to one of the seven considered classes.

A classical approach in precision agriculture consists in validating within field zones defined from high spatial resolution observations by agronomic information (AI). Zones validation generally involves a two-step process. First, AI are obtained on a regular grid or following a target sampling strategy inside the field. Then, a statistical test, most often an ANOVA, is used to determine if the management zones created with the high spatial resolution auxiliary data explain differences in the AI values. Unfortunately, in precision agriculture, many of the works using such an approach omit a necessary condition for the implementation of the aforementioned ANOVA test, i.e. the observations need to be independent from each other. This condition is unfortunately seldom satisfied since AI are often spatially auto-correlated. In order to highlight this problem, simulated datasets with different and known AI spatial autocorrelation were used. Results show that as AI are more and more spatially auto-correlated, ANOVA tests almost always conclude that the management zones obtained with auxiliary data are significant whatever the zoning, i.e. even a completely random one. To overcome this problem, the paper introduces two methods directly inspired from published works in the field of ecology. Two cases were considered: the first one applies when large AI dataset (n>40) is available and the other one applies for small AI dataset (n

Canopy temperature (T C ) can be a robust indicator of grapevine water status. However, the assessment of T C by thermography in field conditions requires optimization, especially under variable environmental conditions (daily and seasonal) just like it occurs in Mediterranean areas. Besides, simplicity and robustness should be the basis of a wider use of thermography in field conditions. Therefore the comparison of simpler and more complex approaches in terms of thermal indicators is wise to test. Our major aims were: i) to assess the performance of four common thermal indicators (canopy temperature − T C , Crop Water Stress Index − CWSI, index of relative stomatal conductance − I G , and the difference between T C and the surrounding air − ΔT canopy-air ) to support irrigation decisions ii) to optimize the timing of thermal measurements for different genotypes and iii) to obtain mathematical functions to estimate leaf gas exchange parameters on the basis of thermal data. The trial was conducted in the summer of 2013, in south Portugal. Two V. vinifera red varieties, Touriga Nacional and Aragonez (syn. Tempranillo) were tested. Vines were subjected to two irrigation regimes: i) sustained-deficit irrigation (based on the farm’s schedule − control) and ii) regulated-deficit irrigation (∼50% of the control). We found that measurements done between 11:00 and 17:00 h provide the most significant correlations between T C , CWSI and I G and leaf stomatal conductance and net photosynthesis for both genotypes. Different linear mathematical functions were obtained to estimate leaf gas exchange based on the best performing thermal indicators under field conditions. Our results emphasize the value of T C as a relevant explanatory variable of vine’s physiological status, in spite of being a simpler and non-normalized thermal indicator. The potential relevance of T C for grapevine modelling and phenotyping is also discussed.

Vigor and vegetative expression are parameters of great interest in viticulture.Traditionally these parameters are estimated using a destructive method.We present a new method that determines these parameters based on an image.The method consists on a digital image processing of an on-field acquiring image. The vigor and the vegetative expression of vines are parameters of great interest in viticulture since they are indicative of the entire guidance system state. Traditionally these parameters are estimated and obtained using a destructive method by cutting the sticks, weighing them and finally obtain the medium weight of pruning sticks. This paper presents a non-destructive method that successfully determines the vine vigor based on a digital image processing. The method consists of acquiring a digital image of vines and applying a software to those images to determine vigor and vegetative expression. This application can be divided in two independent phases: the first one consists in a digital image processing, that isolate the vine sticks and determines the mean area per stick of the vine; the second one determines the vine vigor and vegetative expression based on a polynomial relationship between mean area and mean weight of stick. The software application was tested on thirty vines (Vitis vinifera cv. Touriga Nacional) characterized by low, medium and high vigor and selected during a three-year study. Since the mean weight of stick obtained using the mathematical expression and the values calculated using the real sticks present a 0.998 correlation, we can conclude that this new methodology successfully determines the vigor and the vegetative expression of vines. With this new methodology it is unnecessary determinate the pruning mass and the number of sticks per plant in the vineyard. It's a simple use application that determines vigor and vegetative expression, based on a digital image of the vine and independent of the pruning date. This new method has a patent register in Portugal, with the reference number 105163.

The harvest operation for table-grapes and fresh market horticultural fruits is a large and expensive logistical challenge with the choice of harvest dates and locations playing a crucial role in determining the quality of the yield and in determining the efficiency and productivity gain of the entire operation. The choice of harvest dates and locations, particularly in red varieties, is planned based upon the development of the color of the grape clusters. The traditional process to evaluate the amount of ripe, fully-colored fruit is visual assessment, which is subjective and prone to errors. The number of locations where a grower will evaluate the fruit development is statistically insufficient given the size of commercial vineyards and the variability in the color development. Therefore, an automated approach for evaluating color development is desirable. In this paper, we use a vision-based system to collect images of the fruit zone in a vineyard. We then use color image analysis to grade and predict the color development of grape clusters in the vineyard. Using our approach we are able to generate spatial maps of the vineyard showing the current and predicted distribution of color development. Our imaging measurement system achieves R 2 correlation values of 0.42-0.56 against human measurements. We our able to predict the color development to within 5% average absolute error of the imaging measurements. The prediction of spatial maps is important from the perspective of selective harvesting as it allows the precise targeting of productive zones during the harvest operation. To the best of our knowledge generation of these spatial maps that represent the current and predicted state of the color development of an entire vineyard block, before harvest and in high resolution, is a first of its kind.

Precise yield estimation in vineyards using image processing techniques has only been demonstrated conceptually on a small scale. Expanding this scale requires significant computational power where, by necessity, only small parts of the images of vines contain useful features. This paper introduces an image processing algorithm combining colour and texture information and the use of a support vector machine, to accelerate fruit detection by isolating and counting bunches in images. Experiments carried out on two varieties of red grapes (Shiraz and Cabernet Sauvignon) demonstrate an accuracy of 88.0% and recall of 91.6%. This method is also shown to remove the restriction on the field of view and background which plagued existing methods and is a first step towards precise and reliable yield estimation on a large scale.

New technologies in precision viticulture are increasingly being used to improve grape quality. One of the main challenges being faced by the scientific community in viticulture is early yield prediction. Within this framework, flowering as well as fruit set assessment is of special interest since these two physiological processes highly influence grapevine yield. In addition, an accurate fruit set evaluation can only be performed by means of flower counting. Herein a new methodology for segmenting inflorescence grapevine flowers in digital images is presented. This approach, based on mathematical morphology and pyramidal decomposition, constitutes an outstanding advance with respect to other previous approaches since it can be applied on images with uncontrolled background. The algorithm was tested on 40 images of 4 different Vitis vinifera L. varieties, and resulted in high performance. Specifically, values for Precision and Recall were 83.38% and 85.01%, respectively. Additionally, this paper also proposes a comprehensive study on models for estimating actual flower number per inflorescence. Results and conclusions that are developed in the literature and treated herewith are also clarified. Furthermore, the use of non-linear models as a promising alternative to previously-proposed linear models is likewise suggested in this study., Authors would like to thank the ADER agency of the La Rioja regional government and the Spanish Ministry for Economy and Competitiveness in the funding of the projects VINETICS and AGL2011-23673, respectively.

Display Omitted New algorithm to automatically detect vine rows in UAV aerial images.Based on dynamic segmentation, Hough Space Clustering and Total Least Squares.Robust to disturbance elements and non-crop vegetation.Able to process images with a limited intervention of the user. In viticulture, the adoption of precision agriculture techniques is nowadays increasingly essential to reach required high product quality standards. New reliable tools for mapping crop variability indexes in a vineyard or a single parcel are necessary to deploy site-specific management practices. In this paper, a new method to automatically detect vine rows in gray-scale aerial images is presented. The developed image processing algorithm is constituted by three main steps based on dynamic segmentation, Hough Space Clustering and Total Least Squares techniques. The procedure's reliability has also been proven in the presence of disturbance elements, like dense inter-row grassing, bushes and trees shadows, by properly detecting vine rows in the vineyard images. Moreover, its adaptive features allow it to obtain optimal results in the presence of uneven image illumination due, for example, to the presence of clouds or steep terrain slopes. The extracted row and inter-row information, besides being the basis for vineyard characterization maps computation, like vine plants vigor maps, could also be used as a reference for other precision viticulture tasks such as, for example, path planning of unmanned ground vehicles.

The goal of this research was to develop a procedure to minimize the cost of soil survey optimizing ARP© (Automatic Resistivity Profiling) deployment and selecting the best placement of the sampling sites to employ for soil profile description and analysis. In this respect, devoted tests were conducted in a 3.5 ha vineyard located in Tuscany (central Italy). ARP© produced close-spaced measurements (2335 points) of geo-referenced values of apparent electrical resistivity (ERa) related approximately to 0.5 m depth. A fast soil surface sampling (0.1–0.3 m depth) was contemporarily carried out for analyzing moisture, particle size distribution and electrical conductivity. Relationships between soil properties, elevation and ERa data were analyzed along with a comparative investigation about the cost for soil description, analysis and ARP survey. The best correlated soil property (clay) to ERa was then employed for evaluating its predictability starting from different combinations of reduced ARP measurements and sampling sites chosen by regression-driven method and the ESAP (ECe Sampling, Assessment and Prediction) software. It was noticed that the reduction of the soil sample number affects clay map predictability less than the decrease of ARP survey intensity. The regression approach provided higher clay predictability than ESAP for the densest ARP survey and loosest soil sampling. Such a procedure can be applied to fields once the geoelectrical calibration phase is performed. Given that the study case can be considered representative of many Mediterranean viticulture districts, we are confident that the methodology can be widely used. These findings indicate that ARP on-the-go sensor can fruitfully support traditional soil investigation, allowing the cost reduction for sampling and laboratory analyses.

Precision viticulture (PV) and precision agriculture (PA) requires the acquisition and proce ssing of a vast collection of data coming typically from large scale and heterogeneous sensor networks. Unfortunately, sensor integration is far from being simple due to the number of incompatible network specifications and platforms. The adoption of a common, standard communication interfa ce would allow the engineer to abstract the relation between the sensor and the network. This would reduce the development efforts and emerge as an important step towards the adoption of ‘‘plug-and-play’’ technology in PA/PV sensor networks. This paper explores this need and introduces a framework for smart data acquisition in PA/PV that relies on the IEEE 1451 family of standards, which addresses the transducer-to -network interoperability issues. The framework includes a ZigBee end device (sMPWiNodeZ), as an IEEE 1451 WTIM (Wireless Transducer Interface Module), and an IEEE 1451 NCAP (Network Capable Application Processor) that acts as gateway to an information service provider and WSN (Wireless Sensor Network) coordinator. The paper discusses the proposed IEEE 1451 system architecture and its benefits in PA/PV and closes with results/lessons learned from in-field trials towards smarter WSN. The authors would like to acknowledge the Portuguese Foundation of Science and Technology (FCT) that partially sponsors this research work through the scholarship reference SFRH/BD/38759/2007.

Despite the benefits of precision agriculture and precision viticulture production systems, its rate of adoption in the Portuguese Douro Demarcated Region remains low. We believe that one way to raise it is to address challenging real-world problems whose solution offers a clear benefit to the viticulturist. For example, one of the most demanding tasks in wine making is harvesting. Even for humans, the environment makes grape detection difficult, especially when the grapes and leaves have a similar color, which is generally the case for white grapes. In this paper, we propose a system for the detection and location, in the natural environment, of bunches of grapes in color images. This system is able to distinguish between white and red grapes, and at the same time, it calculates the location of the bunch stem. The system achieved 97% and 91% correct classifications for red and white grapes, respectively.

International audience; The increasing availability of Very High Spatial Resolution images enables accurate digital maps production as an aid for management in the agricultural domain. In this study we develop a comprehensive and automatic tool for vineyard detection, delineation and characterizationusing aerial images and without any parcel plan availability. In France, vineyard training methods in rows or grids generate periodic patterns which make frequency analysis a suitable approach. The proposed method computes a Fast Fourier Transform on an aerial image, providing the delineation of vineyards and the accurate evaluation of row orientation and interrow width. These characteristics are then used to extract individual vine rows, with the aim of detecting missing vine plants and characterizing cultural practices. Using the red channel of an aerial image, 90\% of the parcels have been detected; 92\% have been correctly classified according to their rate of missing vine plants and 81\% according to their cultural practice (weed control method). The automatic process developed can be easily integrated into the final user's Geographical Information System and produces useful information for vineyard management

In the last decade, wireless technologies have been increasingly applied in precision agriculture. Wireless monitoring systems in particular have been used in precision viticulture in order to understand vineyard variability, and therefore suggest appropriate management practices for improving the quality of the wines. The NAV (Network Avanzato per il Vigneto - Advanced Vineyard Network) system is a wireless sensor network designed and developed with the aim of remote real-time monitoring and collecting of micro- meteorological parameters in a vineyard. The system includes a base agrometeorological station (Master Unit) and a series of peripheral wireless nodes (Slave Units) located in the vineyard. The Master Unit is a typical single point monitoring station placed outside the vineyard in a representative site to collect agrometeorological data. It utilizes a wireless technology for data communication and transmission with the Slave Units and remote central server. The Slave Units are multiple stations placed in the vineyard and equipped with agrometeorological sensors for site-specific environmental monitoring, which store and transmit data to the Master Unit. Software was developed for setup and configuration functional- ity. A graphical user interface operating on the remote central server was implemented to collect and process data and provide real-time control. The devices were tested in a three-step process: hardware functionality and data acquisition, energy consumption and communication. The NAV system is a com- plete monitoring system that gave flexibility for planning and installation, which fully responded to the objectives of the work in terms of energy efficiency and performance.

In gravelly soils, surveys are generally time-consuming, labour-intensive and costly. This limits the possibility of adopting an appropriate sampling to determine within-field spatial variability. The potential use of electro-magnetic induction scans (EMI) to measure apparent electrical conductivity (EC) and improve the estimate accuracy of sparsely sampled primary variables was assessed in a 5-ha gravelly soil vineyard in Valpolicella, north-eastern Italy. EC was measured using a Geonics EM38DD operating in both horizontal and vertical mode. Geo-electrical investigations were also done in 18 positions with the electrical resistivity tomography (ERT) method to obtain high-resolution images of the soil profile. The spatial variability of soil properties and their relationships with EC in horizontal and vertical mode was estimated using multivariate geostatistical techniques. Spatial dependence between EC and physical soil properties (particle-size distribution) was explored with factorial kriging analysis (FKA) that could isolate and display sources of variation acting at different spatial scales, expressed as regionalised factors, which was followed by fuzzy c-means classification for zoning the vineyard. There was a generally close relationship between EC and the measured physical properties: EC was negatively correlated with the coarser texture components (gravel and sand) and positively with the finer ones (clay and silt). EC measurements were also consistent with ERT profiles, evidencing the presence of gravelly parent material, with low electrical conductivity, variably distributed in the 3 dimensions and affecting vine rooting depth. FKA isolated two significant regionalised factors which, with an acceptable loss of information, give a concise description of the soil physical variability at the different selected spatial scales. These factors, used in fuzzy c-means classification, allowed the delineation of zones to be managed separately. The results prove that EM38DD could be advantageously used to map soil spatial variability in gravelly soils, even if ground-truth soil samples are obligatory to understand and interpret the EC measurements.

This paper is part of a long-term effort to introduce precision viticulture in the region of Demarcated Region of Douro. It presents the architecture, hardware and software of a platform designed for that purpose, called MPWiNodeZ. A major feature of this platform is its power-management subsystem, able to recharge batteries with energy harvested from the surrounding environment from up to three sources. It allows the system to sustain operation as a general-purpose wireless acquisition device for remote sensing in large coverage areas, where the power to run the devices is always a concern. The MPWiNodeZ, as a ZigBee(TM) network element, provides a mesh-type array of acquisition devices ready for deployment in vineyards. In addition to describing the overall architecture, hardware and software of the monitoring system, the paper also reports on the performance of the module in the field, emphasising the energy issues, crucial to obtain self-sustained operation. The testing was done in two stages: the first in the laboratory, to validate the power management and networking solutions under particularly severe conditions, the second stage in a vineyard. The measurements about the behaviour of the system confirm that the hardware and software solutions proposed do indeed lead to good performance. The platform is currently being used as a simple and compact yet powerful building block for generic remote sensing applications, with characteristics that are well suited to precision viticulture in the DRD region. It is planned to be used as a network of wireless sensors on the canopy of vines, to assist in the development of grapevine powdery mildew prediction models.

The changes in the shape and size of vines during the growing season require a continuous adjustment of the applied dose to optimize spray application efficiency. Target detection with ultrasonic sensors can be used to adapt the applied dose following the principles of the variable rate technology. A multi-nozzle air-blast sprayer was fitted with three ultrasonic sensors and three electro-valves, to modify the flow rate from the nozzles in real time, in relation to the variability of crop width. A constant application rate of 300 l ha−1 was compared with a variable rate application using the tree row volume principle at a 0.095 l m−3 canopy. The total flow rate sprayed by the nozzles was modified according to the variations of crop width measured by the ultrasonic sensors. On average 58% less liquid was applied compared to the constant rate application, with similar deposition on leaves with both treatments. A detailed analysis of savings indicates differences between the lower, middle and top part of the crop, in accordance with the leaf area distribution with crop height. No significant differences between treatments were detected in uniformity of liquid distribution and capability to reach the inner parts of the crop. This important reduction in spray volume could be followed by an equivalent reduction of plant protection products but further research work is needed to guarantee biological efficacy of a reduced dose. This work was funded by the Spanish Ministry of Education and Science, and it is part of the funded research project AGL2002-04260-C04-03

Vineyard leaf area is a key determinant of grape characteristics and wine quality. As is frequently the case in agriculture, available ground-based leaf area measurements employed by growers are not well suited to larger area mapping. In this study, IKONOS high spatial resolution, multispectral satellite imagery was used to map leaf area throughout two commercial wine grape vineyards (approximately 800 ha) in California’s North Coast growing region. The imagery was collected near harvest during the 2000 growing season, converted to at-sensor radiance, geo-referenced and transformed to normalized difference vegetation index (NDVI) on a per pixel basis. Measurements at 24 ground calibration sites were used to convert NDVI maps to leaf area index (LAI; m 2 leaf area m � 2 ground area); planting density was then used to express leaf area on a per vine basis (LAv). Image-based LAv was significantly correlated with ground-based LAv estimates developed at 23 validation sites (r 2 � /0.72; P B/ 0.001). Despite challenges posed by the discontinuous nature of vineyard canopies and architectural differences imposed by shoot positioning trellis systems, remote sensing appears to offer a basis for mapping vineyard leaf area in low LAI vineyards. Such maps can potentially be used to parameterize plant growth models or provide decision support for irrigation and canopy management. # 2002 Elsevier Science B.V. All rights reserved.