Search Results for author: Daniele De Martini

Found 25 papers, 4 papers with code

VDNA-PR: Using General Dataset Representations for Robust Sequential Visual Place Recognition

no code implementations14 Mar 2024 Benjamin Ramtoula, Daniele De Martini, Matthew Gadd, Paul Newman

Two parallel lines of work on VPR have shown, on one side, that general-purpose off-the-shelf feature representations can provide robustness to domain shifts, and, on the other, that fused information from sequences of images improves performance.

Visual Place Recognition

That's My Point: Compact Object-centric LiDAR Pose Estimation for Large-scale Outdoor Localisation

no code implementations7 Mar 2024 Georgi Pramatarov, Matthew Gadd, Paul Newman, Daniele De Martini

This paper is about 3D pose estimation on LiDAR scans with extremely minimal storage requirements to enable scalable mapping and localisation.

3D Pose Estimation

Masked Gamma-SSL: Learning Uncertainty Estimation via Masked Image Modeling

no code implementations27 Feb 2024 David S. W. Williams, Matthew Gadd, Paul Newman, Daniele De Martini

This work proposes a semantic segmentation network that produces high-quality uncertainty estimates in a single forward pass.

Segmentation Semantic Segmentation

What you see is what you get: Experience ranking with deep neural dataset-to-dataset similarity for topological localisation

1 code implementation20 Oct 2023 Matthew Gadd, Benjamin Ramtoula, Daniele De Martini, Paul Newman

In the case of localisation, important dataset differences impacting performance are modes of appearance change, including weather, lighting, and season.

Visual Navigation

Semantic Interpretation and Validation of Graph Attention-based Explanations for GNN Models

no code implementations8 Aug 2023 Efimia Panagiotaki, Daniele De Martini, Lars Kunze

In this work, we propose a methodology for investigating the use of semantic attention to enhance the explainability of Graph Neural Network (GNN)-based models.

Feature Importance Graph Attention

SEM-GAT: Explainable Semantic Pose Estimation using Learned Graph Attention

1 code implementation7 Aug 2023 Efimia Panagiotaki, Daniele De Martini, Georgi Pramatarov, Matthew Gadd, Lars Kunze

This paper proposes a Graph Neural Network(GNN)-based method for exploiting semantics and local geometry to guide the identification of reliable pointcloud registration candidates.

Graph Attention Inductive Bias +1

Roll-Drop: accounting for observation noise with a single parameter

no code implementations25 Apr 2023 Luigi Campanaro, Daniele De Martini, Siddhant Gangapurwala, Wolfgang Merkt, Ioannis Havoutis

This paper proposes a simple strategy for sim-to-real in Deep-Reinforcement Learning (DRL) -- called Roll-Drop -- that uses dropout during simulation to account for observation noise during deployment without explicitly modelling its distribution for each state.

Explainable Action Prediction through Self-Supervision on Scene Graphs

no code implementations7 Feb 2023 Pawit Kochakarn, Daniele De Martini, Daniel Omeiza, Lars Kunze

This work explores scene graphs as a distilled representation of high-level information for autonomous driving, applied to future driver-action prediction.

Autonomous Driving

Sampling, Communication, and Prediction Co-Design for Synchronizing the Real-World Device and Digital Model in Metaverse

no code implementations31 Jul 2022 Zhen Meng, Changyang She, Guodong Zhao, Daniele De Martini

This work proposes a sampling, communication and prediction co-design framework to minimize the communication load subject to a constraint on tracking the Mean Squared Error (MSE) between a real-world device and its digital model in the metaverse.

Mixed Reality

BoxGraph: Semantic Place Recognition and Pose Estimation from 3D LiDAR

no code implementations30 Jun 2022 Georgi Pramatarov, Daniele De Martini, Matthew Gadd, Paul Newman

This paper is about extremely robust and lightweight localisation using LiDAR point clouds based on instance segmentation and graph matching.

Graph Matching Instance Segmentation +2

Depth-SIMS: Semi-Parametric Image and Depth Synthesis

no code implementations7 Mar 2022 Valentina Musat, Daniele De Martini, Matthew Gadd, Paul Newman

In this paper we present a compositing image synthesis method that generates RGB canvases with well aligned segmentation maps and sparse depth maps, coupled with an in-painting network that transforms the RGB canvases into high quality RGB images and the sparse depth maps into pixel-wise dense depth maps.

Depth Completion Image Generation +2

Unsupervised Change Detection of Extreme Events Using ML On-Board

1 code implementation4 Nov 2021 Vít Růžička, Anna Vaughan, Daniele De Martini, James Fulton, Valentina Salvatelli, Chris Bridges, Gonzalo Mateo-Garcia, Valentina Zantedeschi

In this paper, we introduce RaVAEn, a lightweight, unsupervised approach for change detection in satellite data based on Variational Auto-Encoders (VAEs) with the specific purpose of on-board deployment.

Change Detection Management +2

Contrastive Learning for Unsupervised Radar Place Recognition

no code implementations6 Oct 2021 Matthew Gadd, Daniele De Martini, Paul Newman

We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving the place recognition problem with complex radar data.

Contrastive Learning Data Augmentation

The Oxford Road Boundaries Dataset

no code implementations16 Jun 2021 Tarlan Suleymanov, Matthew Gadd, Daniele De Martini, Paul Newman

In this paper we present the Oxford Road Boundaries Dataset, designed for training and testing machine-learning-based road-boundary detection and inference approaches.

Boundary Detection

Unsupervised Place Recognition with Deep Embedding Learning over Radar Videos

no code implementations12 Jun 2021 Matthew Gadd, Daniele De Martini, Paul Newman

We learn, in an unsupervised way, an embedding from sequences of radar images that is suitable for solving place recognition problem using complex radar data.

Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning

no code implementations1 Mar 2021 David Williams, Matthew Gadd, Daniele De Martini, Paul Newman

In this work, we train a network to simultaneously perform segmentation and pixel-wise Out-of-Distribution (OoD) detection, such that the segmentation of unknown regions of scenes can be rejected.

Contrastive Learning Data Augmentation +3

CPG-ACTOR: Reinforcement Learning for Central Pattern Generators

no code implementations25 Feb 2021 Luigi Campanaro, Siddhant Gangapurwala, Daniele De Martini, Wolfgang Merkt, Ioannis Havoutis

Our results on a locomotion task using a single-leg hopper demonstrate that explicitly using the CPG as the Actor rather than as part of the environment results in a significant increase in the reward gained over time (6x more) compared with previous approaches.

Robotics

Self-Supervised Localisation between Range Sensors and Overhead Imagery

no code implementations3 Jun 2020 Tim Y. Tang, Daniele De Martini, Shangzhe Wu, Paul Newman

Publicly available satellite imagery can be an ubiquitous, cheap, and powerful tool for vehicle localisation when a prior sensor map is unavailable.

Keep off the Grass: Permissible Driving Routes from Radar with Weak Audio Supervision

no code implementations11 May 2020 David Williams, Daniele De Martini, Matthew Gadd, Letizia Marchegiani, Paul Newman

Reliable outdoor deployment of mobile robots requires the robust identification of permissible driving routes in a given environment.

RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radar

no code implementations2 Apr 2020 Prannay Kaul, Daniele De Martini, Matthew Gadd, Paul Newman

This paper presents an efficient annotation procedure and an application thereof to end-to-end, rich semantic segmentation of the sensed environment using FMCW scanning radar.

Image Segmentation Segmentation +1

RSL-Net: Localising in Satellite Images From a Radar on the Ground

no code implementations9 Jan 2020 Tim Y. Tang, Daniele De Martini, Dan Barnes, Paul Newman

This paper is about localising a vehicle in an overhead image using FMCW radar mounted on a ground vehicle.

Online Fall Detection using Recurrent Neural Networks

1 code implementation13 Apr 2018 Mirto Musci, Daniele De Martini, Nicola Blago, Tullio Facchinetti, Marco Piastra

This information can be used to trigger the necessary assistance in case of injury.

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