An expertized grapevine disease image database including five grape varieties focused on Flavescence dorée and its confounding diseases, biotic and abiotic stresses.

The grapevine is vulnerable to diseases, deficiencies, and pests, leading to significant yield losses. Current disease controls involve monitoring and spraying phytosanitary products at the vineyard block scale. However, automatic detection of disease symptoms could reduce the use of these products and treat diseases before they spread. Flavescence dorée (FD), a highly infectious disease that causes significant yield losses, is only diagnosed by identifying symptoms on three grapevine organs: leaf, shoot, and bunch. Its diagnosis is carried out by scouting experts, as many other diseases and stresses, either biotic or abiotic, imply similar symptoms (but not all at the same time). These experts need a decision support tool to improve their scouting efficiency. To address this, a dataset of 1483 RGB images of grapevines affected by various diseases and stresses, including FD, was acquired by proximal sensing. The images were taken in the field at a distance of 1-2 meters to capture entire grapevines and an industrial flash was ensuring a constant luminance on the images regardless of the environmental circumstances. Images of 5 grape varieties (Cabernet sauvignon, Cabernet franc, Merlot, Ugni blanc and Sauvignon blanc) were acquired during 2 years (2020 and 2021). Two types of annotations were made: expert diagnosis at the grapevine scale in the field and symptom annotations at the leaf, shoot, and bunch levels on computer. On 744 images, the leaves were annotated and divided into three classes: 'FD symptomatic leaves', 'Esca symptomatic leaves', and 'Confounding leaves'. Symptomatic bunches and shoots were, in addition of leaves, annotated on 110 images using bounding boxes and broken lines, respectively. Additionally, 128 segmentation masks were created to allow the detection of the symptomatic shoots and bunches by segmentation algorithms and compare the results to those of the detection algorithms.

Designing a Proximal Sensing Camera Acquisition System for Vineyard Applications: Results and Feedback on 8 Years of Experiments.

The potential of image proximal sensing for agricultural applications has been a prolific scientific subject in the recent literature. Its main appeal lies in the sensing of precise information about plant status, which is either harder or impossible to extract from lower-resolution downward-looking image sensors such as satellite or drone imagery. Yet, many theoretical and practical problems arise when dealing with proximal sensing, especially on perennial crops such as vineyards. Indeed, vineyards exhibit challenging physical obstacles and many degrees of variability in their layout. In this paper, we present the design of a mobile camera suited to vineyards and harsh experimental conditions, as well as the results and assessments of 8 years' worth of studies using that camera. These projects ranged from in-field yield estimation (berry counting) to disease detection, providing new insights on typical viticulture problems that could also be generalized to orchard crops. Different recommendations are then provided using small case studies, such as the difficulties related to framing plots with different structures or the mounting of the sensor on a moving vehicle. While results stress the obvious importance and strong benefits of a thorough experimental design, they also indicate some inescapable pitfalls, illustrating the need for more robust image analysis algorithms and better databases. We believe sharing that experience with the scientific community can only benefit the future development of these innovative approaches.

An annotated image dataset of vegetable crops at an early stage of growth for proximal sensing applications.

This article introduces a dataset of 2 801 images of vegetable crops. Maize (Zea mays), bean (Phaseolus vulgaris) and leek (Allium ampeloprasum) crops at an early stage of development (between 2 and 5 weeks from seeding of transplanting) are supported. Two kinds of annotations are provided: (i) bounding boxes enclosing the crops of interest or their stems, weeds being left apart, and (ii) crop structures in the form of star graphs whose vertices are the plant organs (stems and leaves) and whose edges represent the connections between them. The images have been captured in various production and experimentation plots in France using an acquisition module which controls light conditions. They present a wide variety of soil conditions, weed infestation and growth stages. This dataset can benefit precision hoeing and in-field crop monitoring applications that are based on proximal imagery.

An annotated image dataset of downy mildew symptoms on Merlot grape variety.

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.

Texture Synthesis Using the Structure Tensor.

This paper proposes a two-stage texture synthesis algorithm. At the first stage, a structure tensor map carrying information about the local orientation is synthesized from the exemplar's data and used at the second stage to constrain the synthesis of the texture. Keeping in mind that the algorithm should be able to reproduce as faithfully as possible the visual aspect, statistics, and morphology of the input sample, the method is tested on various textures and compared objectively with existing methods, highlighting its strength in successfully synthesizing the output texture in many situations where traditional algorithms fail to reproduce the exemplar's patterns. The promising results pave the way towards the synthesis of accurately large and multi-scale patterns as it is the case for carbon material samples showing laminar structures, for example.

Maximum-likelihood based synthesis of volumetric textures from a 2D sample.

We propose a genuine 3D texture synthesis algorithm based on a probabilistic 2D Markov random field conceptualization, capable of capturing the visual characteristics of a texture into a unique statistical texture model. We intend to reproduce, in the volumetric texture, the interactions between pixels learned in an input 2D image. The learning is done by nonparametric Parzen-windowing. Optimization is handled voxel by a relaxation algorithm, aiming at maximizing the likelihood of each voxel in terms of its local conditional probability function. Variants are proposed regarding the relaxation algorithm and the heuristic strategies used for the simultaneous handling of the orthogonal slices containing the voxel. The procedures are materialized on various textures through a comparative study and a sensitivity analysis, highlighting the variants strengths and weaknesses. Finally, the probabilistic model is compared objectively with a nonparametric neighborhood-search-based algorithm.

Analyses of the temporal dynamics of fungal communities colonizing the healthy wood tissues of esca leaf-symptomatic and asymptomatic vines.

Esca, a Grapevine Trunk Disease (GTD), is of major concern for viticulture worldwide. Our study compares the fungal communities that inhabit the wood tissues of vines that expressed or not foliar esca-symptoms. The trunk and rootstock tissues were apparently healthy, whether the 10 year-old plants were symptomatic or not. The only difference was in the cordon, which contained white rot, a typical form of esca, in 79% of symptomatic plants. Observations over a period of one year using a fingerprint method, Single Strand Conformation Polymorphism (SSCP), and the ITS-DNA sequencing of cultivable fungi, showed that shifts occurred in the fungal communities colonizing the healthy wood tissues. However, whatever the sampling time, spring, summer, autumn or winter, the fungi colonizing the healthy tissues of asymptomatic or symptomatic plants were not significantly different. Forty-eight genera were isolated, with species of Hypocreaceae and Botryosphaeriaceae being the most abundant species. Diverse fungal assemblages, made up of potentially plant-pathogenic and -protective fungi, colonized these non-necrotic tissues. Some fungi, possibly involved in GTD, inhabited the non-necrotic wood of young plants, but no increase in necrosis areas was observed over the one-year period.

Stereological estimation of orientation distribution of generalized cylinders from a unique 2D slice.

Though three-dimensional (3D) imaging gives deep insight into the inner structure of complex materials, the stereological analysis of 2D snapshots of material sections is still necessary for large-scale industrial applications for reasons related to time and cost constraints. In this paper, we propose an original framework to estimate the orientation distribution of generalized cylindrical structures from a single 2D section. Contrary to existing approaches, knowledge of the cylinder cross-section shape is not necessary. The only requirement is to know the area distribution of the cross-sections. The approach relies on minimization of a least squares criterion under linear equality and inequality constraints that can be solved with standard optimization solvers. It is evaluated on synthetic data, including simulated images, and is applied to experimental microscopy images of fibrous composite structures. The results show the relevance and capabilities of the approach though some limitations have been identified regarding sensitivity to deviations from the assumed model.

Confidence bounds for the estimation of the volume phase fraction from a single image in a nickel base superalloy.

We propose an image-based framework to evaluate the uncertainty in the estimation of the volume fraction of specific microstructures based on the observation of a single section. These microstructures consist of cubes organized on a cubic mesh, such as monocrystalline nickel base superalloys. The framework is twofold: a model-based stereological analysis allows relating two-dimensional image observations to three-dimensional microstructure features, and a spatial statistical analysis allows computing approximate confidence bounds while assessing the representativeness of the image. The reliability of the method is assessed on synthetic models. Volume fraction estimation variances and approximate confidence intervals are computed on real superalloy images in the context of material characterization.

Assessment of texture stationarity using the asymptotic behavior of the empirical mean and variance.

Given textured images considered as realizations of 2-D stochastic processes, a framework is proposed to evaluate the stationarity of their mean and variance. Existing strategies focus on the asymptotic behavior of the empirical mean and variance (respectively EM and EV), known for some types of nondeterministic processes. In this paper, the theoretical asymptotic behaviors of the EM and EV are studied for large classes of second-order stationary ergodic processes, in the sense of the Wold decomposition scheme, including harmonic and evanescent processes. Minimal rates of convergence for the EM and the EV are derived for these processes; they are used as criteria for assessing the stationarity of textures. The experimental estimation of the rate of convergence is achieved using a nonparametric block sub-sampling method. Our framework is evaluated on synthetic processes with stationary or nonstationary mean and variance and on real textures. It is shown that anomalies in the asymptotic behavior of the empirical estimators allow detecting nonstationarities of the mean and variance of the processes in an objective way.