Search

Your search keyword '"McCarroll, Niall"' showing total 20 results
Start Over Author "McCarroll, Niall"
20 results on '"McCarroll, Niall"'

4. BioFace : bio-inspired face detection

Author

McCarroll, Niall

Subjects
006.2
Abstract

The goal of face detection is to determine whether or not an image or video frame contains faces and, if present, return the number of instances of each face object and their location within an image space. Face detection is an important computer vision task as it is the building block for more sophisticated face processing algorithms such as face recognition and facial expression tracking. However, robust and reliable face detection in completely unconstrained settings remains a very challenging task. For example, while the human brain performs face detection and recognition robustly and with apparent ease, computer algorithms continue to find this a difficult task due to the huge variation of facial appearance in still images and video sequences. The existing literature documents extensive work on face detection utilising different classical machine learning and traditional algorithmic techniques. Given that challenges such as invariance to facial pose still remain with these traditional machine learning approaches, an exploration of biologically representative solutions that behave adaptively and autonomously through learning may help account for the well documented superior human and primate detection performance. In an effort to implement a more biologically plausible approach to invariant multi-view face detection, this thesis presents a novel hierarchical Spiking Neural Network (SNN) framework that adopts a hybrid approach to learning. This is achieved by combining a bottom-up unsupervised Spike-Timing Dependent Plasticity (STDP) feature extraction and filtering phase with a supervised feature selection process that provides feedback to the framework in an effort to select the most diagnostic neurons for accurate face detection. The detection accuracy of the hybrid system is further enhanced through two biologically plausible mechanisms of error control; namely threshold potential adaptation and spike latency thresholding. The broadly tuned behaviour of the neurons allows for a small but expressive set of multi­view neurons to achieve efficient and robust detection for multi-view face poses. The merged, multi-view face detection system is further adapted through a competitive lateral inhibition mechanism to achieve accurate in-plane and out-of-plane face pose estimation.

Published
2017

5. Bio-Inspired Hybrid Framework for Multi-view Face Detection

Author

McCarroll, Niall, Belatreche, Ammar, Harkin, Jim, Li, Yuhua, Hutchison, David, Series editor, Kanade, Takeo, Series editor, Kittler, Josef, Series editor, Kleinberg, Jon M., Series editor, Mattern, Friedemann, Series editor, Mitchell, John C., Series editor, Naor, Moni, Series editor, Pandu Rangan, C., Series editor, Steffen, Bernhard, Series editor, Terzopoulos, Demetri, Series editor, Tygar, Doug, Series editor, Weikum, Gerhard, Series editor, Arik, Sabri, editor, Huang, Tingwen, editor, Lai, Weng Kin, editor, and Liu, Qingshan, editor

Published
2015
Full Text
View/download PDF

7. Dynamic sea-level changes and potential implications for storm surges in the UK: a storylines perspective

Author

Bulgin, Claire E, Mecking, Jennifer V, Harvey, Ben J, Jevrejeva, Svetlana, McCarroll, Niall F, Merchant, Christopher J, Sinha, Bablu, Bulgin, Claire E, Mecking, Jennifer V, Harvey, Ben J, Jevrejeva, Svetlana, McCarroll, Niall F, Merchant, Christopher J, and Sinha, Bablu

Abstract

Global sea-level rise caused by a warming climate increases flood risk from storm surge events for those who live in coastal and low-lying areas. Estimates of global thermosteric sea-level rises are well constrained by model projections, but local variability in dynamic sea-level arising from seasonal and interannual changes is less well characterised. In this paper we use satellite altimetry observations coupled with CMIP6 model projections to understand drivers of change in dynamic sea-level over the UK shelf seas. We find a northward shift in the atmospheric jet stream and a weakening of the Atlantic meridional overturning circulation to be the key drivers of local dynamic sea-level variability. Using a storyline approach to constrain climate system responses to changes in atmospheric greenhouse gas concentrations, we find that dynamic sea-level is predicted to rise between 15–39 cm by 2080–2099 along the east coast of England (ECE). Under a worst-case scenario, assuming maximum variability as seen in the CMIP6 projections, ECE dynamic sea-level rise could reach 58 cm by 2100. We illustrate the impact of this dynamic sea-level rise in addition to non-dynamic components on the risks posed by storm surge events in ECE using an idealised example. If a storm surge event of the magnitude of the one experienced in ECE on the 5th of December 2013 was to occur in 2100, an additional 1414 km2 of land would potentially be affected in our worst-case idealised example, 22.4% of which can be attributed to dynamic sea-level rise.

Published
2023

8. Giving Voice to, and Empowering Stakeholders of UKRI DRI: A Net Zero Workshop Series (Go Zero)

Author

Manika, Danae, McCarroll, Niall, Buck, Justin, Lopez, Alvaro Lorenzo, Geatches, Dawn, Ahrens, Florian, Krumdieck, Susan, Keshtkar, Hossein, Fayyad, Nadine, and Hassanloo, Hamidreza

Subjects
Digital Research Infrastructure, Net Zero, DRI, UKRI
Abstract

Final Report of Go Zero, a sandpit project as part of theUKRI Net Zero Digital Research Infrastructure Scoping Project.The Go Zero project was created to engage with the diverse community of UKRI DRI policymakers, service providers and service users on the subject of the Net Zero transition. The project ran a series of workshops in the Autumn of 2022 which considered different aspects of the challenge, allowing participants to discuss and share their expertise and ideas and giving them a voice in shaping future policies. The report summarisesthe key findings and recommendations moving forward from Go Zero in working towards a roadmap for carbonneutrality in the UK's digital research infrastructures. &nbsp

Published
2023
Full Text
View/download PDF

10. Net Zero DRI Project Partners Webinars - slides for all talks

Author

Townsend, Poppy, Schien, Daniel, Hays, Jonathan, Bane, Michael, Turner, Andrew, Basden, Alastair, Stephens, Ag, Lambert, Simon, Smith, Lorna, Friday, Adrian, Boulton, Jack, McCarroll, Niall, Ahrens, Florian, McGuire, Laura, and Richardson, Harriett

Abstract

This document contains all presentation slides that were presented during the Project Partner webinars, hosted by the UKRI Net Zero DRI Scoping Project team in early 2023. Pages 1-85 show slides for webinar 1.Page 86 onwards are the slides that were presented during webinar 2. Recordings of the webinars can be found here: Webinar 1 -technical and operational challenges Webinar 2 - community and organisational challenges Further details about the webinars: The UKRI Net Zero Digital Research Infrastructure Scoping Project (https://net-zero-dri.ceda.ac.uk/) team hosted two webinars to share the outcomes of work undertaken by our project partners (https://net-zero-dri.ceda.ac.uk/project-activities/). These pieces of work have been undertaken by over 40 researchers from 20 different institutions over the last ~6 months. Both webinars provided an opportunity for the wider research community to engage with and discuss the project outcomes. Webinar 1 covered technical and operational challenges such as: hardware procurement, design and architecture of infrastructure, cloud platforms, consolidation, power management and efficiency, end-of-life, and carbon capture and offsetting. Speakers presented from the following project partners: - CarbonQuanDRI: developing a measurement trace capturing various sustainability aspects in the operation of a DRI service, including dependencies between different indicators (e.g. data flow, power consumption, and carbon intensity) (https://net-zero-dri.ceda.ac.uk/cquandri/) - IRISCAST: auditing energy usage of the IRIS DRI via snap-hot data capture (https://net-zero-dri.ceda.ac.uk/iriscast/) - Energetic: exploring energy-to-solution consumption in High Performance Computing (HPC) (https://net-zero-dri.ceda.ac.uk/energetic/) - HPC-Jeep: informing efficient, environmentally conscientious use of HPC resources – ARCHER2 and DiRAC (https://net-zero-dri.ceda.ac.uk/hpc-jeep/) - Mapping the DRI: collating a representative sample of the DRI using the UKRI InfraPortal (https://net-zero-dri.ceda.ac.uk/mapping/) - Case studies update – detailed analysis for the following infrastructures: JASMIN, Archer2, Jade, Scafell Pike Webinar 2 covered community and organisational challenges such as: user facing services, data management, behaviour change, training, proportionality of energy use, the risks of negative impacts, and monitoring and driving change. Speakers presented from the following project partners: - Arinzrit: mapping the DRI policy and practice landscape (https://net-zero-dri.ceda.ac.uk/arinzrit/) - Value: developing recommendations for evaluating carbon emissions vs output ‘value’ to support UKRI decision-making (https://net-zero-dri.ceda.ac.uk/value/) - Go Zero: empowering the research community to take ownership of Net Zero (https://net-zero-dri.ceda.ac.uk/go-zero/) - DRI User Behaviour Survey: identifying implicit attitudes to environmental sustainability and gathered information about existing sustainable usage of DRI (https://net-zero-dri.ceda.ac.uk/user-behaviour-survey/) - Art to inspire collective action on sustainable digital research infrastructure: the progress so far and how you can get involved (https://net-zero-dri.ceda.ac.uk/art-commission/) &nbsp

Published
2023
Full Text
View/download PDF

11. Go Zero- Giving Voice to, and Empowering Stakeholders of UKRI DRI: A Net Zero Workshop Series (Go Zero)

Author

Manika, Danae, McCarroll, Niall, Buck, Justin, Lopez, Alvaro Lorenzo, Geatches, Dawn, Ahrens, Florian, Krumdieck, Susan, Keshtkar, Hossein, Fayyad, Nadine, and Hassanloo, Hamidreza

Abstract

Different digital research infrastructure (DRI)stakeholders need help to understand and plan for meeting net zero challenges. Many of the skills and knowledge needed to solve net zero challenges are already in the community – but we lack the mechanisms for sharing them and enabling behaviour change.

Published
2022
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results