Projects

Current Projects

  • 3DSCAM

Enterprise Ireland Commercialisation Fund project for stereoscopic 3D conversion of animated movies. The idea is to develop post-production tools to help at the creation of stereoscopic content from standard monoscopic animation material.

  • CAMP [SFI]

CAMP (Content-Aware Media Processing) is an SFI Principal Investigator Award. There has been an exponential increase in the creation of digital media. Digital visual media e.g. pictures and movies have seen a particular explosion in the last five years. But as it has become easier to acquire images, it has become more difficult to organise them. Few people bother to create picture albums anymore for instance. The same problem is happening in science. Much more visual imagery is being recorded of important phenomenon, but it is difficult to locate the important features. While many researchers are concentrating on making media easier to search, there is less work on making media easier to use. This project explores the concept of Content Aware visual Media Processing (CAMP). The idea is to use salient visual features to control image processing tools, for example highlighting important features in a medical video, or making picture content clearer for viewing on a small screen.

  • Dynamic Visual Features for Automatic Speech Recognition

This project is funded by the SFI Research Frontiers Programme. Human speech is bimodal in nature. Incorporating visual features in Automatic Speech Recognition systems can improve performance in real environments. This work addresses core challenges in audio-visual speech recognition. It will develop new dynamic visual features that better capture the correlations in key mouth movements used by humans in lipreading. This is crucial in improving Hidden Markov Model performance. It will explore a new audio-fusion strategy motivated by the differing visibility of visemes allowing the influence of the audio and video stream to change over time.

Previous Projects

  • i3DPOST [EU Strep]

Led by the Foundry, the i3Dpost EU project is a collaboration between TCD, uni Surrey, Uni Thessonaliki and Buf (a post production house in France), QuanticDream (Paris based games developer). The idea is to exploit multiview film recording for new post-production techniques and more robust editing tools. This project started in Feb 2008.

  • Aids for anatomy students [RCSI]

Prof Clive Lee is the prof of Anatomy at the RCSI and has been working with Sigmedia to launch new teaching aids for anatomy students. Sigmedia has been developing editing tools that allow highlighting of important features of the human anatomy. See XXX for the site. not suitable for those of weak disposition.

  • Axiom [EU Marie-Curie]

Axiom stands for Automated Extraction of Image Metadata, an acronym coined by the Oscar Winning Ben Kent at the Foundry. Axiom combines the research skills of the Sigmedia Group and the practical knowledge of The Foundry in an ongoing collaboration to improve the workflow in the post-production house.

  • CellBio [RCSI]

In collaboration with Dr. Fergal O'Brien in the Bone Research Group this project is attempting to design new tools for quantifying porosity in scaffolds of organic material. The scaffolds are used to grow cells and the porosity determines the ability of the scaffold to support new growth.

  • 3DProfiling (for grinding wheels and tyres) [EI],

Motion estimation technology can find its way into the most amazing applications. In this project Sigmedia is using correspondence between two views of a surface to generate a fast 3d mesh of that surface. It is to be used for tyres and grinding wheels. The project was devised by Prof A Torrance of the Mechanical Eng. Dept, TCD.

  • Content Based Multiview Media Editing for eLearning Environments [SFI]

This project (2009-2010) is focused towards the development of useful tools for the automated post-production of multi-camera and multi-microphone lecture and seminar recordings. The aim is to develop useful plugins for commonly used audio/video editing suites such as Abode After Effects which will automate many aspects of the post-production cycle. An example of one such technology developed under this project can be found here. The development of these software tools is founded upon the out-comes of the "E-learning" [SFI] project (see below). The work is supported by Science Foundation Ireland through a Technology, Innovation and Development Award (TIDA).

  • E-Learning [SFI]

In this SFI Funded research frontiers project (2006-2009), work is underway to develop techniques that parse audio visual recordings of lecture presentations. In addition, in collaboration with the audio synthesis group of Dr Dermont Furlong, the project is creating new algorithms for sound field synthesis. There is also a collaboration with the University of the West Indies as part of this project as some of the work here will be used in a distance learning course in video processing to be launched at UWI in 2008.

This major EU project is a collaboration with over 30 industry and academic partners for the establishment of the concept of a distributed "restoration factory". Within this project Sigmedia has been porting some of its research ideas into usable plug-ins for the Diamant system.

  • UWI/UTT Teaching

Sigmedia launches its own Video processing course for the University of the West Indies next spring. Members of Sigmedia are expected to travel to the Caribbean twice a year to assist on this course.

  • Dumping Detective [EI]

The DumpingDetective project is applying ideas in motion tracking and video segmentation for the monitoring of illegal dumping activity at waste disposal sites and collection bins. The project is now ended, but our process is able to locate items left behind at a dumping site. This means that the thousands of hours of surveillance footage at these sites is now more useul.

  • Aurora [EU] / Brava [EU]

Over the last ten years this group has been involved in EU projects dealing with restoration. In particular we have been working on new concepts for parsing archived material according to degradation type and quality. This is similar to an "intelligent restoration agent" for post production houses and archivists.

Page last modified on May 23, 2012