This blog is no longer active. I maintained this blog as part of my role of Research Development Officer with the Faculty of Engineering and Computing, DCU. I have taken up a new role, but you can continue to find information on research in the Faculty, through the main Faculty website [HERE], and through the DCU news pages [HERE].
Thanks for reading!
Raymond Kelly

Friday 23 November 2007

Congratulations to Philip Kelly

Congratulations to Philip Kelly who successfully defended his thesis and will be awarded the degree of PhD.

The title of Philip's thesis is "Pedestrian Detection and Tracking using Stereo Vision Techniques".

He completed his PhD in the Centre for Digital Video Processing (CDVP), Adaptive Information Cluster (AIC) and the School of Electronic Engineering, DCU under the supervision of Dr. Noel E. O’Connor.

Philip is currently working as a post-doctoral researcher with the CDVP.

Brief description of Project:
Accurate detection and tracking of pedestrians are two essential components required by a variety of applications that include, amongst others, Ambient Intelligence, automated surveillance, image compression and content-based multimedia storage and retrieval. Given this large number of potential applications, pedestrian detection and tracking has become an extremely active research area in computer vision. This has resulted in a significant amount of prior art proposing pedestrian segmentation techniques using a myriad of approaches. Many of the person detection techniques described so far in the literature work well in controlled environments, such as laboratory settings with a small number of people. This allows various assumptions to be made that simplify this complex problem. The performance of these techniques, however, tends to deteriorate when presented with unconstrained environments where pedestrian appearances, numbers, orientations, movements, occlusions and lighting conditions violate these convenient assumptions. Recently, 3D stereo information has been proposed as a technique to overcome some of these issues and to guide pedestrian detection.

This thesis presents such an approach, whereby after obtaining robust 3D information via a novel disparity estimation technique, pedestrian detection is performed via a 3D point clustering process within a region-growing framework. This clustering process avoids using hard thresholds by using bio-metrically inspired constraints and a number of plan view statistics. This pedestrian detection technique requires no external training and is able to robustly handle challenging real-world unconstrained environments from various camera positions and orientations. In addition, this thesis presents a continuous detect-and-track approach, with additional kinematic constraints and explicit occlusion analysis, to obtain robust temporal tracking of pedestrians over time.

This project was generously funded by Science Foundation Ireland (SFI).

Tuesday 13 November 2007

DCU to lead Multi-Million Euro Research in High-Tech Automatic Language Translation

Dublin City University is to lead a multi-million euro research partnership funded by Science Foundation Ireland (SFI) that will develop the next generation of high tech automatic language translation.

This five-year research programme will transform an important sector of Ireland’s global software business – localisation - as well as a key driver of the global content distribution industry.

DCU is collaborating in the project with academic partners, UCD, UL and TCD, and with renowned global technology leaders, IBM, Microsoft, Symantec, Dai Nippon Printing, and Idiom Technologies as well as key Irish SMEs, Alchemy, VistaTech, SpeechStorm and Traslan.

The Minister for Enterprise and Employment, Michael Martin, today announced the award of €16.8m to the project by SFI, and the industry partners are contributing €13.6m in materials, research services and additional funding.

Ireland already has a substantial global footprint in the localisation industry – the process of adapting digital content, download manuals, software and other materials, to different languages and cultures.

The President of DCU, Professor Ferdinand von Prondzynski, said: ”This welcome funding is a great endorsement of DCU’s international research capability. It means that DCU is now leading two SFI Centres for Science, Engineering and Technology (CSETs) – in biomedical diagnostics and localisation technology – that have won the largest-ever SFI funding in the state”

The Irish project will tackle three critical problems for the Localisation Industry:

  • Volume: The amount of content to be translated and localised to the destination culture and environment is growing rapidly and massively outstrips the supply of human translators.
  • Access: Powerful, small devices such as mobile phones and PDAs require novel technologies integrating speech and text to support “on the move” delivery of, and access to multilingual information.
  • Personalisation : A new demand has rapidly emerged for the adaptation of a huge amount of multilingual content now available on the web, for individual needs . It needs “instant” localisation and personalisation to meet the demands of the users.

Professor Josef van Genabith, Director of the new Centre said: "Localisation as an industrial process was developed in Ireland. We have a unique concentration of university- and industry-based research and development expertise in language technologies, machine translation, speech processing, digital content management and localisation. The research centre is going to pool that expertise and develop the next generation of language and content management technologies to support and develop the localisation industry.”

Thursday 8 November 2007

European Software Process Improvement Conference 2008

The School of Computing, DCU will host the 15th European Software Process Improvement Conference (EuroSPI 2008) from 3rd to 5th of September 2008.

EuroSPI conferences present and discuss results from software process improvement (SPI) projects in industry and research, focusing on the benefits gained and the criteria for success. Leading European universities, research canters, and industry are contributing to and participating in this event.

EuroSPI 2008 will be the 15th of a series of conferences to which international researchers contribute their lessons learned and share their knowledge as they work towards the next higher level of software management professionalism.


The conference will be jointly chaired by Dr. Rory O'Connor (School of Computing, DCU) and Dr Nathan Baddoo (University of Hertfordshire).

Wednesday 7 November 2007

International Conference on Business Innovation and Information Technology


DCU is proud to host the International Conference on Business Innovation and Information Technology

The new and unique International Conference on Business Innovation and Information Technology aims to provide a premier forum for the presentation and discussion of business innovations associated with Information Technology (IT). We invite contributions from industry and academia as well as encourage postgraduate researchers to submit their work.

Submissions may be any of the following:
- research paper
- short paper
- experience report

Contributions must be submitted here.

Held in Dublin, Ireland on 24th and 25th of January 2008, the conference focuses on real-world business applications and innovations associated with information technology. Therefore, contributions should highlight the benefits and invitations driven by information technology in organisations. The idea of the conference is to provide a forum and platform for both researchers and practitioners to exchange knowledge and ideas and learn from each other.

Practitioners and researchers present findings and experience. In addition to the official program, there is plenty of opportunity for informal discussions and networking.

Contributions are selected on the basis of abstracts. Abstracts will be evaluated for originality, significance and contribution. All authors of accepted contributions are expected to present at the conference. All accepted and presented contributions will be invited to submit a full paper, which will be published in the conference proceedings after the conference.

Topics may include, but are not limited to:
- Innovative Business Models and E-Commerce Solutions
- Regulatory and Privacy Issues
- E-Government
- Information Systems and Business Processes
- System Development and Software Engineering
- Advanced Information Technologies

It is planned to publish in the Springer Series “Lecture Notes in Business Information Systems (LNBIP)”. As accepted papers are published in the conference proceedings, contributions must not have been previously published or submitted for publication elsewhere.

Important Dates:
Abstract Submission Deadline: 30 November 2007
Notification of acceptance: 12 December 2007
Deadline Early Registration: 31 December 2007
Submission Online Version of Full Paper: 11 January 2008
Conference Date: 24-25 January 2008
Indicative Publication Date for Proceedings: May 2008

Conference Chairs
Dr. Markus Helfert, School of Computing, Dublin City University
Dr. Regina Connolly, Business School, Dublin City University

The conference is supported by Dublin City University and Science Foundation Ireland

Monday 5 November 2007

Research Student Graduation

Congratualtions to all of the DCU students who are graduating today and tomorrow. There are 13 students graduating from the Faculty of Engineering & Computing with Masters by research, and a further 20 students graduating with PhDs. Great credit is due to these students for their tireless work over the last number of years. Ireland's future as a knowledge based economy will be heavily influenced by innovative Engineers and Computer Scientists such as these.

In total, 13 research students graduated from the School of Computing, with a further 10 graduating from the School of Electronic Engineering, and a further 10 from the School of Mechanical and Manufacturing Engineering. You can get more information about the projects of some of these students here.

Thursday 25 October 2007

DCU Researchers Win Top International Paper Prize

DCU laser micromachining researchers have won the top application prize for their published paper on laser micromachining at the NI Days Worldwide Virtual Instrumentation Conference in London.

Over the last five years Dr. Dermot Brabazon, Dr. Ahmed Issa and Prof. Saleem Hashmi of the School of Mechanical and Manufacturing Engineering and the Materials Processing Research Centre (MPRC) have developed two laser micromachining processes which allow for the production of channels and voxels with highly repeatable micrometer level resolution. Devices fabricated with this developed technology can be used for applications such as microfluidic lab on a chip, strain measurement, sub-micrometer cooling systems and various photonic guiding systems.

The paper was entitled, Laser System Automation using LabVIEW and PCI E-Series Board for 3D Internal Micromachining. This work illustrated the sophisticated automated 3D Nd:YVO4 and CO2 laser micro fabrication facilities that were developed. In order to achieve the precise control, CAD processing, laser firing, 3D sample movement and thermal field modelling software were developed. In addition, in order to characterise the high efficiency achieved from these processes, an in house built automated channel and voxel profiler was used.

NI Days, which has been running for the past decade, gives engineers and scientists from across the UK & Ireland an opportunity to learn how the latest developments in computer-based measurement and automation increase productivity and lower cost through graphical system design and virtual instrumentation

The prize includes flight and accommodation to NI Week in Austin, TX, next year, a plaque and LEGO Mindstorms NXT.

Friday 19 October 2007

Congratulations to Puspita Deo

Congratulations to Puspita Deo who successfully defended her thesis and will be awarded the degree of PhD.

The title of Puspita's thesis is "Heterogeneous Motorised Traffic Flow Modelling using Cellular Automata".

She completed her PhD in the Modelling & Scientific Computing Group, School of Computing, DCU under the supervision of Professor Heather Ruskin.

Brief description of Project:
Traffic congestion is a major problem in most major cities around the world with few signs that this is diminishing, despite management efforts. In planning traffic management and control strategies at urban and inter urban level, understanding the factors involved in vehicular progression is vital. Most work to date has, however, been restricted to single vehicle-type traffic. Study of heterogeneous traffic movements for urban single and multi-lane roads has been limited, even for developed countries and motorised traffic mix, (with a broader spectrum of vehicle type applicable for cities in the developing world). The aim of the research, was thus to propose and develop a model for heterogeneous motorised traffic, applicable to situations, involving common urban and interurban road features in the western or developed world. A further aim of the work was to provide a basis for comparison with current models for homogeneous vehicle type.

A two-component cellular automata (2-CA) methodology is used to examine traffic patterns for single-lane, multi-lane controlled and uncontrolled intersections and roundabouts. In this heterogeneous model (binary mix), space mapping rules are used for each vehicle type, namely long (double-unit length) and short (single-unit length) vehicles. Vehicle type is randomly categorised as long (LV) or short (SV) with different fractions considered. Update rules are defined based on given and neighbouring cell states at each time step, on manoeuvre complexity and on acceptable space criteria for different vehicle types. Inclusion of heterogeneous traffic units increases the algorithm complexity as different criteria apply to different cellular elements, but mixed traffic is clearly more reflective of the real-world situation.

The impact of vehicle mix on the overall performance of an intersection and roundabout (one-lane one-way, one-lane two-way and two-lane two-way) has been examined. Investigation of performance metrics for heterogeneous traffic (short and long vehicles), can be shown to reproduce main aspects of real-world configuration performance. This has been validated, using local Dublin traffic data.

The developed model has potential to extend its use to linked transport network elements and can also incorporate further motorised and non-motorised vehicle diversity for various road configurations.

This project was funded by the School of Computing, DCU.