ELIS – Multimedia Lab Multimedia Lab Rik Van de Walle Department of Electronics and Information Systems Ghent University - IBBT Gaston Crommenlaan 201 bus 8 B-9050 Ledeberg-Ghent, Belgium t: +32 9 33 14914 f: +32 9 33 14896 m: +32 478 39 62 31 t secr: +32 9 33 14911 e: rik.vandewalle@ugent.be URL: multimedialab.elis.ugent.be ELIS – Multimedia Lab Multimedia Lab - UGent • History – background in image and signal processing – 1999: Multimedia Systems and Applications new research area within Ghent University – 2001: Multimedia Lab formally founded new research group within ELIS department – 2003: link/co-operation with IMEC – 2004: partner of the IBBT www.ibbt.be, Flemish Government MMLab Overview F2F MMSEM, Athens – December 2006 2/28 ELIS – Multimedia Lab Multimedia Lab - UGent • People – 5 staff members • • • • • Rik Van de Walle, full professor Peter De Neve, 10% lecturer Erik Mannens, project management Peter Lambert, senior researcher Ellen Lammens, administrative management – currently 25 researchers • PhD students • “others” (projects) – about 15 master students per year MMLab Overview F2F MMSEM, Athens – December 2006 3/28 ELIS – Multimedia Lab Multimedia Lab - UGent • Teaching – programs • ba/ma Computer Science (Faculty of Engineering) • ba/ma Electronics (Faculty of Engineering) • ba/ma Informatics (Faculty of Sciences) – – – – – Multimedia Techniques (baC3 - baE3) Development of MM Applications (maC1 - maE1) Advanced MM Applications - project (maC2 - maE2) Multimedia (baINFO2) Internet Technology (baINFO3) MMLab Overview F2F MMSEM, Athens – December 2006 4/28 ELIS – Multimedia Lab Research topics: data + metadata opera: il barbiere di Siviglia composer: Gioachino Rossini director: Claudio Abbado type: audio format: MP3 opera: il barbiere di Siviglia composer: Gioachino Rossini libretto: Cesare Sterbini type: web page format: html place: Sydney building: opera house architect: Jørn Utzon type: still image format: JPEG2000 MMLab Overview F2F MMSEM, Athens – December 2006 5/28 ELIS – Multimedia Lab Research topics: adaptation - optimization multimedia terminals INTERACTION DEPENDING ON mono/stereo audio, color depth, resolution, bandwidth, ... network MMLab Overview F2F MMSEM, Athens – December 2006 6/28 ELIS – Multimedia Lab Research topics (1) • Advanced video applications – development and exploitation of scalable video compression techniques – motion estimation and compensation – ROI-based video compression (Region of Interest) – adaptation of multimedia data with respect to varying usage environments – development of iDTV applications (a/o based on MHP, the Multimedia Home Platform) MMLab Overview F2F MMSEM, Athens – December 2006 7/28 ELIS – Multimedia Lab Research topics (2) • Mobile multimedia applications – reduction impact of network losses on quality of multimedia presentations (a/o adaptive coding/decoding wrt varying network characteristics) – rendering multimedia data on mobile terminals with limited resources – transparent handover of multimedia sessions between different devices (session mobility) – hardware/software co-design of embedded multimedia systems MMLab Overview F2F MMSEM, Athens – December 2006 8/28 ELIS – Multimedia Lab Research topics (3) • Standardization – MPEG-21 • • • • – – – – – Digital Item Declaration Digital Item Adaptation Digital Item Processing Development of Reference Software for various tools MPEG-4 Scalable Video Coding (SVC) MPEG-4 Advanced Video Coding (H.264/AVC) JVT - Joint Video Team VQEG - Video Quality Experts Group IFTA - International Federation of Television Archives MMLab Overview F2F MMSEM, Athens – December 2006 9/28 ELIS – Multimedia Lab Ex. 1: exploitation of scalability MMLab Overview F2F MMSEM, Athens – December 2006 10/28 ELIS – Multimedia Lab Ex. 2: session mobility for mobile applications student watching a lesson on a settop box tv/set-top box Media stream student continuing the session on a PDA Media stream Servers containing online classes Session Transfer Pocket PC Session Transfer Media stream finishing the elearning session on a tablet PC Tablet PC MMLab Overview F2F MMSEM, Athens – December 2006 11/28 ELIS – Multimedia Lab Ex. 3: video adaptation for mobile applications MMLab Overview F2F MMSEM, Athens – December 2006 12/28 ELIS – Multimedia Lab In short: transparent content adaptation MMLab Overview F2F MMSEM, Athens – December 2006 13/28 ELIS – Multimedia Lab New Research Paths related to MMSEM MMLab Overview F2F MMSEM, Athens – December 2006 14/28 ELIS – Multimedia Lab Feature Extraction (Video) • Use cases: – Video surveillance • Detection of moving foreground objects – Video adaptation • Change bitrate, framerate, resolution, coding format, … – goal: reduction of network load, processing load, adjustment to client capacities or user preferences • Extraction of relevant features: ROI, semantics, shot detection MMLab Overview F2F MMSEM, Athens – December 2006 15/28 ELIS – Multimedia Lab Feature Extraction tool • Low level extraction: MMLab Overview F2F MMSEM, Athens – December 2006 16/28 ELIS – Multimedia Lab Integrated Video Surveillance System • Combining expertise: Raw Pixel Data MPEG-21 Digital Item H.264 /AVC Digital Item Item Descriptor Descriptor Item Descriptor Descriptor Item Component Component Component features features MMLab Overview F2F MMSEM, Athens – December 2006 17/28 ELIS – Multimedia Lab Interoperable Integrated Video Surveillance System • Issues – Which features (high level <-> low level, automatic <-> manual) – How to describe them – When to describe them (camera, video processing module, network node, client) – How to link them to video resource (storage, distribution, presentation, …) New Use Case? MMLab Overview F2F MMSEM, Athens – December 2006 18/28 ELIS – Multimedia Lab New IBBT Projects related to MMSEM MMLab Overview F2F MMSEM, Athens – December 2006 19/28 ELIS – Multimedia Lab PeCMan • The goal of the PeCMan project is to research the major technological challenges of a user-centric solution enabling uniform storage and manipulation of data as well as universal access to this personal data. A successful solution will have premium capabilities in the areas of security, performance, usability and description of the personal data MMLab Overview F2F MMSEM, Athens – December 2006 20/28 ELIS – Multimedia Lab Personal Digital Photo Archives --> need for effective, uniform annotation strategy Manual annotation Automatic annotation + detailed fast - time consuming, mostly not uniform error prone, semantic gap Overcome semantic gap? • • • • semantic gap is still very wide! Extract the ”good” features -> which algorithm?, domain specific? Combine which primitive features for scene understanding? Machine learning -> many methods, training on different datasets, ... Ontologies -> need to model the whole world? Content vs. Context ELIS – Multimedia Lab Feature extraction - human vision system best tuned to color and texture perception - imitate cells of the visual cortex - texture features can provide semantic information - texture helpful in object segmentation MMLab Overview F2F MMSEM, Athens – December 2006 22/28 ELIS – Multimedia Lab Machine Learning - supervised <-> unsupervised - self-organizing map: processing principles of human (visual & auditory) cortex - incremental learning: knowledge must be continuously updated to manage non-static archives, relevance feedback Feature extraction Machine learning Classification Ontologies Scene understanding --> use both manual and automatic annotation with minimal user overhead MMLab Overview F2F MMSEM, Athens – December 2006 23/28 ELIS – Multimedia Lab Lindo MMLab Overview F2F MMSEM, Athens – December 2006 24/28 ELIS – Multimedia Lab FIPA / AVEQ • investigate the processes related to engineering and analysis of audiovisual material, based on the notion of a virtual model of the product • explore some aspects of reverse engineering, including audiovisual-quantization, analysis and classification • Stretching the idea of the virtual model, we may develop a much more powerful analysis and classification system when we succeed in reconstructing the model – the background, the characters, the objects that constitute the scene of the image – quantifying the subjects per scene by a finite list of normalized and relevant vectors and being able to express semantics, history and behaviour in a single geospatial and temporal reference MMLab Overview F2F MMSEM, Athens – December 2006 25/28 ELIS – Multimedia Lab Industrial partners • Main partners (projects & MPEG) – Alcatel, France-Belgium – Artec/Televic, Belgium – Barco, Belgium – Belgacom, Belgium – CISCO/Scientific Atlanta, USA – Concentra, Belgium – Deutsche Telecom, Germany – eTampere, Finland – France Telecom, France – IBM, USA – Intel, USA – LG Electronics, Korea MMLab Overview F2F MMSEM, Athens – December 2006 26/28 ELIS – Multimedia Lab Industrial partners • Main partners (projects & MPEG) – Microsoft Research, USA – Museon, Netherlands – Philips, Netherlands – Porthus, Belgium – ScreenPeaks, Israel – Siemens, Germany – Sun Microsystems, USA – Telindus, Belgium – Thomson Multimedia, France – T-Systems Nova GmbH, Germany – VMMa, Belgium – VRT, Belgium MMLab Overview F2F MMSEM, Athens – December 2006 27/28 ELIS – Multimedia Lab Contact Erik Mannens Department of Electronics and Information Systems Ghent University - IBBT Gaston Crommenlaan 201 bus 8 B-9050 Ledeberg-Ghent, Belgium t: +32 9 33 14992 f: +32 9 33 14896 m: +32 478 39 62 31 t secr: +32 9 33 14911 e: erik.mannens@ugent.be URL: multimedialab.elis.ugent.be MMLab Overview F2F MMSEM, Athens – December 2006 28/28