Search Results for author: Thomas A. Ciarfuglia

Found 7 papers, 2 papers with code

AgriSORT: A Simple Online Real-time Tracking-by-Detection framework for robotics in precision agriculture

1 code implementation23 Sep 2023 Leonardo Saraceni, Ionut M. Motoi, Daniele Nardi, Thomas A. Ciarfuglia

The problem of multi-object tracking (MOT) consists in detecting and tracking all the objects in a video sequence while keeping a unique identifier for each object.

Multi-Object Tracking

Weakly and Semi-Supervised Detection, Segmentation and Tracking of Table Grapes with Limited and Noisy Data

no code implementations27 Aug 2022 Thomas A. Ciarfuglia, Ionut M. Motoi, Leonardo Saraceni, Mulham Fawakherji, Alberto Sanfeliu, Daniele Nardi

To improve detection and segmentation on the target data, we propose to train the segmentation algorithm with a weak bounding box label, while for tracking we leverage 3D Structure from Motion algorithms to generate new labels from already labelled samples.

Segmentation

The Role of the Input in Natural Language Video Description

no code implementations9 Feb 2021 Silvia Cascianelli, Gabriele Costante, Alessandro Devo, Thomas A. Ciarfuglia, Paolo Valigi, Mario L. Fravolini

Natural Language Video Description (NLVD) has recently received strong interest in the Computer Vision, Natural Language Processing (NLP), Multimedia, and Autonomous Robotics communities.

Data Augmentation Video Description

Towards Monocular Digital Elevation Model (DEM) Estimation by Convolutional Neural Networks - Application on Synthetic Aperture Radar Images

no code implementations14 Mar 2018 Gabriele Costante, Thomas A. Ciarfuglia, Filippo Biondi

In this work, the authors propose a novel experimental alternative to the InSAR method that uses single-pass acquisitions, using a data driven approach implemented by Deep Neural Networks.

J-MOD$^{2}$: Joint Monocular Obstacle Detection and Depth Estimation

no code implementations25 Sep 2017 Michele Mancini, Gabriele Costante, Paolo Valigi, Thomas A. Ciarfuglia

In this work, we propose an end-to-end deep architecture that jointly learns to detect obstacles and estimate their depth for MAV flight applications.

Depth Estimation Scene Understanding +1

LS-VO: Learning Dense Optical Subspace for Robust Visual Odometry Estimation

no code implementations18 Sep 2017 Gabriele Costante, Thomas A. Ciarfuglia

In addition, we propose to learn the latent space jointly with the estimation task, so that the learned OF features become a more robust description of the OF input.

Motion Estimation Optical Flow Estimation +1

Fast Robust Monocular Depth Estimation for Obstacle Detection with Fully Convolutional Networks

4 code implementations21 Jul 2016 Michele Mancini, Gabriele Costante, Paolo Valigi, Thomas A. Ciarfuglia

We propose a novel appearance-based Object Detection system that is able to detect obstacles at very long range and at a very high speed (~300Hz), without making assumptions on the type of motion.

Monocular Depth Estimation object-detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.