6533b824fe1ef96bd12807e1

RESEARCH PRODUCT

Analyse spectrale et texturale de données à haute résolution pour la détection automatique des maladies de la vigne

subject

description

‘Flavescence dorée’ is a contagious and incurable disease present on the vine leaves. In order to contain the infection, the regulations require growers to control each of the vine rows and to remove the suspect vine plants. This monitoring is done on foot during the harvest and mobilizes many people during a strategic period for viticulture. In order to solve this problem, the DAMAV project (Automatic detection of Vine Diseases) aims to develop a solution for automated detection of vine diseases using a micro-drone. The goal is to offer a turnkey solution for wine growers. This tool will allow the search for potential foci, and then more generally any type of vine diseases detectable on the foliage. To enable this diagnosis, the foliage is proposed to be studied using a dedicated high-resolution multispectral camera. The objective of this PhD-thesis in the context of DAMAV is to participate in the design and implementation of the Multi-Spectral (MS) image acquisition system and to develop the image pre-processing algorithms, based on the most relevant spectral and textural characteristics related to ‘Flavescence dorée’. Several grapevine varieties were considered such as red-berried and white-berried ones; furthermore, other diseases than ‘Flavescence dorée’ (FD) such as Esca and ‘Bois noir’ (BN) were also tested under real production conditions. The PhD work was basically performed at a leaf-level scale and involved an acquisition step followed by a data analysis step. Most imaging techniques, used to detect diseases in field crops or vineyards, operate in the visible electromagnetic radiation range. It turns out that for disease detection, when the symptoms are already present, the visible may be sufficient, although the colorimetric information is not the only one to consider. In our case, it is advised to detect the disease as early as possible, the information of the visible spectrum does not seem sufficient and it is therefore necessary to investigate broader information. Reflectance responses of plant leaves can be obtained from short to long wavelengths with convenient sensors. These reflectance signatures describe the internal constituents of leaves. This means that the presence of a disease can modify the internal structure of the leaves and hence cause an alteration of its reflectance signature. A spectro-radiometer is used in our study to characterize reflectance responses of leaves in the field. Several samples at different growth stages were used for the tests. To define optimal reflectance features for grapevine disease detection (FD, Esca, BN), a new methodology that designs Spectral Disease Indices (SDIs) has been developed. It is based on two dimension reduction techniques, coupled with a classifier. The first feature selection technique uses the Genetic Algorithms (GA) and the second one relies on the Successive Projection Algorithm (SPA). The new resulting SDIs outperformed traditional Spectral Vegetation Indices (SVIs) and GA performed, in general, better than SPA. The features finally chosen can then be implemented as filters in the MS sensor. In general, the reflectance information was satisfying for finding infections (higher than 90% of accuracy for the best method) but wasn’t enough. The images acquired with the developed MS device can further be pre- processed by low-level techniques based on the calculation of texture parameters. Several texture processing techniques have been tested but only on colored images. A method that combines many texture features is elaborated, allowing to choose the best ones. We found that the combination of optimal textural information could provide a complementary mean for not only differentiating healthy from infected grapevine leaves (higher than 85% of accuracy), but also for grading the disease severity stages (higher than 73% of accuracy) and for discriminating among diseases (higher than 72% of accuracy). This is in accordance with the hypothesis that a MS camera can enable detection and identification of diseases in grapevine fields. The first experiments of the whole system “sensor-UAV” will be done during future acquisition campaigns in 2019.