no code implementations • 30 Oct 2023 • Vittorio Mazzia, Alessandro Pedrani, Andrea Caciolai, Kay Rottmann, Davide Bernardi
That is expensive, unreliable, and incompatible with the current trend of large self-supervised pre-training, making it necessary to find more efficient and effective methods for adapting neural network models to changing data.
no code implementations • 7 Sep 2022 • Simone Angarano, Francesco Salvetti, Vittorio Mazzia, Giovanni Fantin, Dario Gandini, Marcello Chiaberge
Precise and accurate localization in outdoor and indoor environments is a challenging problem that currently constitutes a significant limitation for several practical applications.
1 code implementation • 2 Sep 2022 • Simone Angarano, Mauro Martini, Francesco Salvetti, Vittorio Mazzia, Marcello Chiaberge
Domain Generalization (DG) studies the capability of a deep learning model to generalize to out-of-training distributions.
no code implementations • 7 Dec 2021 • Simone Cerrato, Vittorio Mazzia, Francesco Salvetti, Mauro Martini, Simone Angarano, Alessandro Navone, Marcello Chiaberge
Expensive sensors and inefficient algorithmic pipelines significantly affect the overall cost of autonomous machines.
1 code implementation • 1 Jul 2021 • Diego Aghi, Simone Cerrato, Vittorio Mazzia, Marcello Chiaberge
Precision agriculture is a fast-growing field that aims at introducing affordable and effective automation into agricultural processes.
4 code implementations • 1 Jul 2021 • Vittorio Mazzia, Simone Angarano, Francesco Salvetti, Federico Angelini, Marcello Chiaberge
Deep neural networks based purely on attention have been successful across several domains, relying on minimal architectural priors from the designer.
no code implementations • 1 Apr 2021 • Mauro Martini, Vittorio Mazzia, Aleem Khaliq, Marcello Chiaberge
The increasing availability of large-scale remote sensing labeled data has prompted researchers to develop increasingly precise and accurate data-driven models for land cover and crop classification (LC&CC).
2 code implementations • 29 Jan 2021 • Vittorio Mazzia, Francesco Salvetti, Marcello Chiaberge
Deep convolutional neural networks, assisted by architectural design strategies, make extensive use of data augmentation techniques and layers with a high number of feature maps to embed object transformations.
Ranked #2 on Image Classification on MNIST
no code implementations • 30 Nov 2020 • Simone Angarano, Vittorio Mazzia, Francesco Salvetti, Giovanni Fantin, Marcello Chiaberge
Ultra-wideband (UWB) is the state-of-the-art and most popular technology for wireless localization.
no code implementations • 18 Nov 2020 • Enrico Sutera, Vittorio Mazzia, Francesco Salvetti, Giovanni Fantin, Marcello Chiaberge
Indoor autonomous navigation requires a precise and accurate localization system able to guide robots through cluttered, unstructured and dynamic environments.
1 code implementation • 30 Oct 2020 • Vittorio Mazzia, Francesco Salvetti, Diego Aghi, Marcello Chiaberge
Agriculture 3. 0 and 4. 0 have gradually introduced service robotics and automation into several agricultural processes, mostly improving crops quality and seasonal yield.
no code implementations • 30 Oct 2020 • Vittorio Mazzia, Francesco Salvetti, Diego Aghi, Marcello Chiaberge
Agriculture 3. 0 and 4. 0 have gradually introduced service robotics and automation into several agricultural processes, mostly improving crops quality and seasonal yield.
no code implementations • 31 Aug 2020 • Anna Boschi, Francesco Salvetti, Vittorio Mazzia, Marcello Chiaberge
The vital statistics of the last century highlight a sharp increment of the average age of the world population with a consequent growth of the number of older people.
Robotics
2 code implementations • 6 Jul 2020 • Francesco Salvetti, Vittorio Mazzia, Aleem Khaliq, Marcello Chiaberge
Convolutional Neural Networks (CNNs) have been consistently proved state-of-the-art results in image Super-Resolution (SR), representing an exceptional opportunity for the remote sensing field to extract further information and knowledge from captured data.
Ranked #1 on Image Super-Resolution on EPFL NIR-VIS
no code implementations • 26 May 2020 • Diego Aghi, Vittorio Mazzia, Marcello Chiaberge
Concurrently, a second back-up algorithm, based on representations learning and resilient to illumination variations, can take control of the machine in case of a momentaneous failure of the first block.
no code implementations • 29 Apr 2020 • Vittorio Mazzia, Lorenzo Comba, Aleem Khaliq, Marcello Chiaberge, Paolo Gay
To achieve this objective, a reliable and updated description of the local status of crops is required.
no code implementations • 28 Apr 2020 • Vittorio Mazzia, Francesco Salvetti, Aleem Khaliq, Marcello Chiaberge
Real-time apple detection in orchards is one of the most effective ways of estimating apple yields, which helps in managing apple supplies more effectively.
no code implementations • 27 Apr 2020 • Vittorio Mazzia, Aleem Khaliq, Marcello Chiaberge
The increasing spatial and temporal resolution of globally available satellite images, such as provided by Sentinel-2, creates new possibilities for researchers to use freely available multi-spectral optical images, with decametric spatial resolution and more frequent revisits for remote sensing applications such as land cover and crop classification (LC&CC), agricultural monitoring and management, environment monitoring.