60 citations · 234 across the 23 of their papers we have counts for
36 papers
Contrastive Learning for Unsupervised Radar Place Recognition
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. Our method is base…
The Oxford Road Boundaries Dataset
Tarlan Suleymanov, Matthew Gadd, Daniele De Martini +1
In this paper we present the Oxford Road Boundaries Dataset, designed for training and testing machine-learning-based road-boundary detection and inference approaches. We have hand…
Unsupervised Place Recognition with Deep Embedding Learning over Radar Videos
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. We experiment on 280…
Fool Me Once: Robust Selective Segmentation via Out-of-Distribution Detection with Contrastive Learning
David Williams, Matthew Gadd, Daniele De Martini +1
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…
Self-Supervised Localisation between Range Sensors and Overhead Imagery
Tim Y. Tang, Daniele De Martini, Shangzhe Wu +1
Publicly available satellite imagery can be an ubiquitous, cheap, and powerful tool for vehicle localisation when a prior sensor map is unavailable. However, satellite images are n…
Sense-Assess-eXplain (SAX): Building Trust in Autonomous Vehicles in Challenging Real-World Driving Scenarios
Matthew Gadd, Daniele De Martini, Letizia Marchegiani +2
This paper discusses ongoing work in demonstrating research in mobile autonomy in challenging driving scenarios. In our approach, we address fundamental technical issues to overcom…
Keep off the Grass: Permissible Driving Routes from Radar with Weak Audio Supervision
David Williams, Daniele De Martini, Matthew Gadd +2
Reliable outdoor deployment of mobile robots requires the robust identification of permissible driving routes in a given environment. The performance of LiDAR and vision-based perc…
RSS-Net: Weakly-Supervised Multi-Class Semantic Segmentation with FMCW Radar
Prannay Kaul, Daniele De Martini, Matthew Gadd +1
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. We a…
Rainy screens: Collecting rainy datasets, indoors
Horia Porav, Valentina-Nicoleta Musat, Tom Bruls +1
Acquisition of data with adverse conditions in robotics is a cumbersome task due to the difficulty in guaranteeing proper ground truth and synchronising with desired weather condit…
LiDAR Lateral Localisation Despite Challenging Occlusion from Traffic
Tarlan Suleymanov, Matthew Gadd, Lars Kunze +1
This paper presents a system for improving the robustness of LiDAR lateral localisation systems. This is made possible by including detections of road boundaries which are invisibl…
Look Around You: Sequence-based Radar Place Recognition with Learned Rotational Invariance
Matthew Gadd, Daniele De Martini, Paul Newman
This paper details an application which yields significant improvements to the adeptness of place recognition with Frequency-Modulated Continuous-Wave radar - a commercially promis…
Real-time Kinematic Ground Truth for the Oxford RobotCar Dataset
Will Maddern, Geoffrey Pascoe, Matthew Gadd +3
We describe the release of reference data towards a challenging long-term localisation and mapping benchmark based on the large-scale Oxford RobotCar Dataset. The release includes…
RSL-Net: Localising in Satellite Images From a Radar on the Ground
Tim Y. Tang, Daniele De Martini, Dan Barnes +1
This paper is about localising a vehicle in an overhead image using FMCW radar mounted on a ground vehicle. FMCW radar offers extraordinary promise and efficacy for vehicle localis…
Kidnapped Radar: Topological Radar Localisation using Rotationally-Invariant Metric Learning
Ştefan Săftescu, Matthew Gadd, Daniele De Martini +2
This paper presents a system for robust, large-scale topological localisation using Frequency-Modulated Continuous-Wave (FMCW) scanning radar. We learn a metric space for embedding…
Learning to Correct 3D Reconstructions from Multiple Views
Ştefan Săftescu, Paul Newman
This paper is about reducing the cost of building good large-scale 3D reconstructions post-hoc. We render 2D views of an existing reconstruction and train a convolutional neural ne…
Learning Geometrically Consistent Mesh Corrections
Ştefan Săftescu, Paul Newman
Building good 3D maps is a challenging and expensive task, which requires high-quality sensors and careful, time-consuming scanning. We seek to reduce the cost of building good rec…
The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Dataset
Dan Barnes, Matthew Gadd, Paul Murcutt +2
In this paper we present The Oxford Radar RobotCar Dataset, a new dataset for researching scene understanding using Millimetre-Wave FMCW scanning radar data. The target application…
Don't Worry About the Weather: Unsupervised Condition-Dependent Domain Adaptation
Horia Porav, Tom Bruls, Paul Newman
Modern models that perform system-critical tasks such as segmentation and localization exhibit good performance and robustness under ideal conditions (i.e. daytime, overcast) but p…
Online Inference and Detection of Curbs in Partially Occluded Scenes with Sparse LIDAR
Tarlan Suleymanov, Lars Kunze, Paul Newman
Road boundaries, or curbs, provide autonomous vehicles with essential information when interpreting road scenes and generating behaviour plans. Although curbs convey important info…
Generating All the Roads to Rome: Road Layout Randomization for Improved Road Marking Segmentation
Tom Bruls, Horia Porav, Lars Kunze +1
Road markings provide guidance to traffic participants and enforce safe driving behaviour, understanding their semantic meaning is therefore paramount in (automated) driving. Howev…
Training Object Detectors With Noisy Data
Simon Chadwick, Paul Newman
The availability of a large quantity of labelled training data is crucial for the training of modern object detectors. Hand labelling training data is time consuming and expensive…
Radar-only ego-motion estimation in difficult settings via graph matching
Sarah H. Cen, Paul Newman
Radar detects stable, long-range objects under variable weather and lighting conditions, making it a reliable and versatile sensor well suited for ego-motion estimation. In this wo…
Imminent Collision Mitigation with Reinforcement Learning and Vision
Horia Porav, Paul Newman
This work examines the role of reinforcement learning in reducing the severity of on-road collisions by controlling velocity and steering in situations in which contact is imminent…
I Can See Clearly Now : Image Restoration via De-Raining
Horia Porav, Tom Bruls, Paul Newman
We present a method for improving segmentation tasks on images affected by adherent rain drops and streaks. We introduce a novel stereo dataset recorded using a system that allows…