%Aigaion2 BibTeX export from Idiap Publications
%Thursday 09 May 2024 11:14:52 AM

@ARTICLE{Gentilhomme_COMPAG_2023,
         author = {Gentilhomme, Th{\'{e}}ophile and Villamizar, Michael and Corre, J{\'{e}}rome and Odobez, Jean-Marc},
       keywords = {convolutional network, deep learning, grapevine pruning, plant skeleton, precision viticulture, vineyard},
       projects = {Idiap},
          month = apr,
          title = {Towards Smart Pruning: ViNet, a Deep-Learning Approach for Grapevine Structure Estimation},
        journal = {Computers and Electronics in Agriculture},
         volume = {207},
           year = {2023},
          pages = {107736},
           issn = {0168-1699},
            url = {https://www.sciencedirect.com/science/article/pii/S0168169923001242},
            doi = {https://doi.org/10.1016/j.compag.2023.107736},
       abstract = {Image and video tools for analysing crop scenes and plants are essential for applying
precision agriculture to crop maintenance, harvesting, or pruning.
In this paper, we are interested in vine pruning, a task that requires a precise
understanding of the vine structure with branch type identification, orientations, and
node locations.
However, estimating such a structure is highly challenging, given the large variety in
grapevine appearances, lighting conditions, viewpoint, the interweaving of branches,
occlusions, and the level of details needed.
To address these challenges, we propose ViNet: a deep-learning approach for
estimating the structure of grapevine, which comprises two main steps:
The first one detects nodes and identifies the branch types of the plant, as well as the
spatial relation between them, whilst the second one uses the extracted nodes and
branches to build a graph, out of which the structure of the grapevine is inferred.
In doing so, we make three main contributions: (i) we put forward for the first time a
method for automatic segmentation and extraction of the grapevine structure from
images; (ii) we propose a novel approach leveraging powerful stacked hourglass
network to infer node location and branch types, along with a novel shortest path
weighted graph optimization step to extract connections between nodes and infer the
structure, allowing to address the problem of having an unknown number of branches
in the tree; (iii) we publicly release a dataset of more than 1500 grapevine images fully
annotated with the structure information.
Extensive experiments on this dataset demonstrate the efficiency of our approach at
predicting the structure of a grapevine, achieving a precision and recall for node
prediction of 95\% and 90\%, respectively, as well as ablation studies validating our
design choices.}
}