1 code implementation • 11 Aug 2023 • Darren Tsai, Julie Stephany Berrio, Mao Shan, Eduardo Nebot, Stewart Worrall
MS3D++ provides a straightforward approach to domain adaptation by generating high-quality pseudo-labels, enabling the adaptation of 3D detectors to a diverse range of lidar types, regardless of their density.
1 code implementation • 14 Jul 2023 • Zhenxing Ming, Julie Stephany Berrio, Mao Shan, Eduardo Nebot, Stewart Worrall
For smart vehicles driving through signalised intersections, it is crucial to determine whether the vehicle has right of way given the state of the traffic lights.
1 code implementation • 5 Apr 2023 • Darren Tsai, Julie Stephany Berrio, Mao Shan, Eduardo Nebot, Stewart Worrall
Our proposed Kernel-Density Estimation (KDE) Box Fusion method fuses box proposals from multiple domains to obtain pseudo-labels that surpass the performance of the best source domain detectors.
1 code implementation • 14 Sep 2022 • Darren Tsai, Julie Stephany Berrio, Mao Shan, Eduardo Nebot, Stewart Worrall
With SEE-VCN, we obtain a unified representation of objects across datasets, allowing the network to focus on learning geometry, rather than overfitting on scan patterns.
1 code implementation • 17 Nov 2021 • Darren Tsai, Julie Stephany Berrio, Mao Shan, Stewart Worrall, Eduardo Nebot
Sampling discrepancies between different manufacturers and models of lidar sensors result in inconsistent representations of objects.
1 code implementation • 23 Mar 2021 • Darren Tsai, Stewart Worrall, Mao Shan, Anton Lohr, Eduardo Nebot
We propose a robust calibration pipeline that optimises the selection of calibration samples for the estimation of calibration parameters that fit the entire scene.
no code implementations • 23 Nov 2020 • Kunming Li, Mao Shan, Karan Narula, Stewart Worrall, Eduardo Nebot
Seamlessly operating an autonomous vehicle in a crowded pedestrian environment is a very challenging task.
Robotics
no code implementations • 23 Nov 2020 • Kunming Li, Stuart Eiffert, Mao Shan, Francisco Gomez-Donoso, Stewart Worrall, Eduardo Nebot
Autonomous vehicle navigation in shared pedestrian environments requires the ability to predict future crowd motion both accurately and with minimal delay.
no code implementations • 16 Nov 2020 • Dhanoop Karunakaran, Stewart Worrall, Eduardo Nebot
The approach is based on a parameter optimisation problem to search for challenging scenarios.
no code implementations • 9 Jul 2020 • Julie Stephany Berrio, Mao Shan, Stewart Worrall, Eduardo Nebot
Our approach is capable of using a multi-sensor platform to build a three-dimensional semantic voxelized map that considers the uncertainty of all of the processes involved.
no code implementations • 23 Jun 2020 • Stuart Eiffert, Kunming Li, Mao Shan, Stewart Worrall, Salah Sukkarieh, Eduardo Nebot
Understanding and predicting the intention of pedestrians is essential to enable autonomous vehicles and mobile robots to navigate crowds.
no code implementations • 4 Mar 2020 • Dhanoop Karunakaran, Stewart Worrall, Eduardo Nebot
The widescale deployment of Autonomous Vehicles (AV) seems to be imminent despite many safety challenges that are yet to be resolved.
no code implementations • 4 Mar 2020 • Julie Stephany Berrio, Mao Shan, Stewart Worrall, James Ward, Eduardo Nebot
This paper presents an approach to fuse different sensory information, Light Detection and Ranging (lidar) scans and camera images.
2 code implementations • 29 Apr 2019 • Surabhi Verma, Julie Stephany Berrio, Stewart Worrall, Eduardo Nebot
This paper proposes an automated method to obtain the extrinsic calibration parameters between a camera and a 3D lidar with as low as 16 beams.
no code implementations • 24 Oct 2018 • Wei Zhou, Julie Stephany Berrio, Stewart Worrall, Eduardo Nebot
This paper presents a novel method for analysing the robustness of semantic segmentation models and provides a number of metrics to evaluate the classification performance over a variety of environmental conditions.
no code implementations • 13 Sep 2018 • Wei Zhou, Alex Zyner, Stewart Worrall, Eduardo Nebot
Semantic segmentation using deep neural networks has been widely explored to generate high-level contextual information for autonomous vehicles.
1 code implementation • 26 Jul 2018 • Alex Zyner, Stewart Worrall, Eduardo Nebot
Understanding the intentions of drivers at intersections is a critical component for autonomous vehicles.