A5101881924- Horticultural and Viticultural Research
- Smart Agriculture and AI
- Tree Root and Stability Studies
- Control and Dynamics of Mobile Robots
- Soft Robotics and Applications
- Robotic Locomotion and Control
- Plant Pathogens and Fungal Diseases
- Generative Adversarial Networks and Image Synthesis
- Food Supply Chain Traceability
- Viral Infectious Diseases and Gene Expression in Insects
- EEG and Brain-Computer Interfaces
- Remote Sensing and LiDAR Applications
- Microbial infections and disease research
- Greenhouse Technology and Climate Control
- Human Pose and Action Recognition
- Plant Surface Properties and Treatments
- Hand Gesture Recognition Systems
- Gait Recognition and Analysis
- Aesthetic Perception and Analysis
- Conservation Techniques and Studies
- Big Data and Business Intelligence
Italian Institute of Technology
2021-2023
University of Genoa
2021
Istituto Nazionale di Fisica Nucleare, Sezione di Genova
2021
University of Trás-os-Montes and Alto Douro
2010-2011
Even though mechanization has dramatically decreased labor requirements, vineyard management costs are still affected by selective operations such as winter pruning. Robotic solutions becoming more common in agriculture, however, few studies have focused on grapevines. This work aims at fine-tuning and testing two different deep neural networks for: (i) detecting pruning regions (PRs), (ii) performing organ segmentation of spur-pruned dormant The Faster R-CNN network was fine-tuned using...
Grapevine winter pruning is a complex task, that requires skilled workers to execute it correctly. The complexity of this task also the reason why time consuming. Considering operation takes about 80–120 hours/ha be completed, and therefore even more crucial in large-size vineyards, an automated system can help speed up process. To end, paper presents novel multidisciplinary approach tackles challenging by performing object segmentation on grapevine images, used create representative model...
Mobile manipulators that combine manipulability and mobility, are increasingly being used for various unstructured application scenarios in the field, e.g. vineyards. Therefore, coordinated motion of manipulator mobile base is an essential feature overall performance. In this paper, we explore a whole-body controller robot which composed 2-DoFs non-holonomic wheeled with 7-DoFs (non-holonomic manipulator, NWMM). This robotic platform designed to efficiently undertake complex grapevine...
In recent years Sim2Real approaches have brought great results to robotics. Techniques such as model-based learning or domain randomization can help overcome the gap between simulation and reality, but in some situations accuracy is still needed. An example agricultural robotics, which needs detailed simulations, both terms of dynamics visuals. However, software not capable quality accuracy. Current techniques are helpful mitigating problem, for these specific tasks they enough.
This study addresses the segmentation of craquelure patterns in fine arts, a complex challenge due to varied textures, color transitions, and canvas deformations typical paintings. We advance this field by introducing supervised learning, manually labeling two distinct image datasets: one comprising grayscale images from established Bucklow's dataset, other consisting patches extracted historical paintings, reflecting more realistic scenarios. employ B-COSFIRE model, originally developed for...
Grapevine winter pruning is a complex task, that requires skilled workers to execute it correctly. The complexity makes time consuming. It an operation about 80-120 hours per hectare annually, making automated robotic system helps in speeding up the process crucial tool large-size vineyards. We will describe (a) novel expert annotated dataset for grapevine segmentation, (b) state of art neural network implementation and (c) generation points following agronomic rules, leveraging simplified...
Grapevine winter pruning is a complex task, that requires skilled workers to execute it correctly. The complexity of this task also the reason why time consuming. Considering operation takes about 80-120 hours/ha be completed, and therefore even more crucial in large-size vineyards, an automated system can help speed up process. To end, paper presents novel multidisciplinary approach tackles challenging by performing object segmentation on grapevine images, used create representative model...
Mobile manipulators that combine mobility and manipulability, are increasingly being used for various unstructured application scenarios in the field, e.g. vineyards. Therefore, coordinated motion of mobile base manipulator is an essential feature overall performance. In this paper, we explore a whole-body controller robot which composed 2-DoFs non-holonomic wheeled with 7-DoFs (non-holonomic manipulator, NWMM) This robotic platform designed to efficiently undertake complex grapevine pruning...