no code implementations • 2 Nov 2022 • Matteo Vaghi, Augusto Luis Ballardini, Simone Fontana, Domenico Giorgio Sorrenti
In the literature, uncertainty estimation in Deep Neural Networks (DNNs) is often performed through sampling methods, such as Monte Carlo Dropout (MCD) and Deep Ensemble (DE), at the expense of undesirable execution time or an increase in hardware resources.
1 code implementation • 8 Mar 2021 • Daniele Cattaneo, Matteo Vaghi, Abhinav Valada
Loop closure detection is an essential component of Simultaneous Localization and Mapping (SLAM) systems, which reduces the drift accumulated over time.
1 code implementation • 28 Mar 2020 • Simone Fontana, Daniele Cattaneo, Augusto Luis Ballardini, Matteo Vaghi, Domenico Giorgio Sorrenti
In this way, we are able to cover many kinds of environment and many kinds of sensor that can produce point clouds.
no code implementations • 2 Oct 2019 • Daniele Cattaneo, Matteo Vaghi, Simone Fontana, Augusto Luis Ballardini, Domenico Giorgio Sorrenti
In this work we leverage Deep Neural Network (DNN) approaches to create a shared embedding space between images and LiDAR-maps, allowing for image to 3D-LiDAR place recognition.
2 code implementations • 24 Jun 2019 • Daniele Cattaneo, Matteo Vaghi, Augusto Luis Ballardini, Simone Fontana, Domenico Giorgio Sorrenti, Wolfram Burgard
In this paper we present CMRNet, a realtime approach based on a Convolutional Neural Network to localize an RGB image of a scene in a map built from LiDAR data.