Multimedia & Vision Research Group (MMV Group)

The Multimedia and Vision Research Group at QMUL was formed in September 2000 to conduct research in image, video processing and computer vision. The mission of the Group has been to complement traditional electronic areas well represented in the departments, such as antennas and telecommunications. When the group was founded in 2000, relatively new areas of multimedia signal processing were in a good position to strengthen the department and college portfolio in research and teaching. The vision was to discover new understanding in multimedia systems technology and to spread excellence through teaching and outreach. The approach taken is integrative since there are no clear boundaries with other groups. Specifically, synergies with the centre for digital music and the networks group are exploited. Since 2001 the group has: published over 100 journal papers, most of them in the highest ranked IEE and IEEE Transactions in the field, and over 400 refereed conference papers; graduated a MPhil and 28 PhD students; secured over £7 Millions grant funding. Objectives Fields of work Research output International cooperation Other esteem indicators

Objectives

Currently, the strategic objectives of the group are:

• to address critical technical challenges in emerging multimedia applications by strengthening existing research fields and building new research initiatives in a dynamic way according to technological trends;
• to enhance outreach activities by working closer with the industry and other research labs world-wide;
• to enrich QMUL’s overall research environment.

Being a main contributor and driver of standardisation in the context of JPEG2000 and MPEG the group will strengthen its research work on the areas of computer vision, surveillance, and tracking. This strategy will take advantage of existing collaborations with the Information Management Department of the MoD, Dstl. and with companies like Motorola, GE, Intel, and BT.

Building on the expertise from previous projects (e.g. EU BUSMAN, aceMedia, K-Space, MESH and RUSHES) the group continue growing its research portfolio with several new large grants.

The group's recent strategic research cooperation with United Technologies (one of the largest industrial corporations world-wide) and ST Microelectronics will further widen the industrial research portfolio, fully exploiting the available areas of expertise.

Contracts for three new EU grants with a combined value of over 1.6M Euros have been signed (PetaMedia, 3DLife, SARACEN and NextMedia) which will strengthen the group's position in scalable coding and visual information retrieval at international level.

Fields of work

The MMV Research Group has 37 members, including 4 members of academic staff, 7 Post-doctoral researchers and 20 PhD students. The group members are active in the following research areas of visual media engineering and computer vision:

• 3D Reconstruction and Graphics
• Video coding
• Analysis of (Human) Motion
• Semantic classification & clustering
• Human Sensing for Human-Media Interaction

Research output and funding

Since 2001 the group has published over 100 journal papers, most of them in the highest ranked IEE and IEEE Transactions in the field, and over 300 refereed conference papers, graduated a MPhil and 28 PhD students and secured over ?7 Millions grant funding.

Currently, the group has over ?3 Million of active research grants. Funding bodies include the EPSRC, the Royal Society, the British Council, Royal Academy of Engineering, industrial partners and the European Union.

The group has been a pioneer in visual information retrieval techniques for semantic inference from audiovisual content, and it is now recognized as a key-player in multimedia information retrieval, in the EU and beyond. This is evidenced by the important role it plays in the TrecVid NIST/USA benchmarking forum, its leading role in the largest cooperative EU projects in the area, and its leadership in the UK Knowledge Management, which embraces the 5 key UK groups in the area. The group coordinated the IST Network of Excellence K-Space and the European COST292 action. It was also one of the main contributors and steering member of several other projects, including FP7 NoE PetaMedia, FP7 Papyrus, FP7 APIDIS, FP6 IPs aceMedia, MESH and FP6 RUSHES. Currently, the group coordinates the NoE 3DLife.

The group is involved in the MPEG-4/7/21 activities and participated in EPSRC supported MMKM network. The coding schema proposed by the group, MMV-SVC, has been found to be one of the best two in terms of compression performance in a worldwide competition organized by MPEG in 2003 to demonstrate evidence on Advanced Scalable Video Coding technology. This kick-started the standardisation process on SVC, which is now near the final stages. The development of the complete framework for full granularity Scalable Video Coding (MMV-SVC), the only one of its kind worldwide, originated ?500k of industry and EU funding.

Finally, the MMV group has been involved in many other projects in the past few years including the FP5 NoE SCHEMA and the IST projects SAVANT, SAMBITS and BUSMAN.

International cooperation

Substantial participation in a number of national and international cooperative projects have enabled the group to initiate research collaborations with other world leading institutions including: the University of California, Los Angeles; Berkley University, California; the Northwestern University, Chicago; the University of Alberta, Edmonton; Intel, US. Several European institutions take part as well to projects in collaboration with the group, including: Motorola Research UK; British Telecom; Sony Research UK; the University of Glasgow; the Heinrich Hertz Institute for Communication Technology, Berlin; the Technical University of Berlin; the Technical University of Munich; Siemens Research Munich; the German Research Centre for Artificial Intelligence; INRIA Research, France; the Groupe des Ecoles des T?l?communications, Paris; the French Institut National de l'Audiovisuel; France Telecom; Thomson France; the Ecole Polytechnique F?d?rale de Lausanne, Switzerland; Telefonica, Spain; General Electric, Switzerland.

International connections are also related to the standardisation activities to which the group plays an active role, being involved in the MPEG standardization work.

Other esteem indicators

The group is highly active in the most relevant scientific societies, having an associated editor for an IEEE transactions journal, a member of the IEEE Signal Processing Society Multimedia Signal Processing Technical Committee and two members in the executive group of the IEE visual information engineering professional network, one of them acting as chairman of this important professional network.

A member of the group has been elected member of the Visual Signal Processing and Communications technical committee of the IEEE. One member is Associate Editor of the IEEE Transactions on Circuits and Systems for Video Technology. Group members have served as guest editor for 3 IEEE Transactions special issues, a IEE Proceeding special issue, a special issues of the EURASIP Journal of Applied Signal Processing, one special issue of the ELSEVIER Signal Processing: Image Communication Journal, a special issue of the Springer journal Signal, Image and Video Processing. A group member is associate editor of the Journal of Multimedia.

A number of really successful conferences has been organised by the group. Among them:

• the International Conference on Image processing for Interactive Services (WIAMIS 2003) attracted over 120 researchers in April 2003;
• the European Conference on the integration of semantics and digital media technology (EWIMT 2004), attracted over 100 researchers in November 2004;
• EWIMT 2005, in November 2005, was as successful as the previous version;
• The IEEE International Conference on Advanced Video and Signal based Surveillance (AVSS 2007) counted 160 attendees in September 2007.
• The International Conference on Content Based Multimedia Indexing, CBMI 2008, held in June 2008;
• The IET International Conference on Visual Information Engineering, VIE 2008, held in July 2008.