Welcome to the EMC2 Research Showcase, comprising sketches of ground-breaking research currently being undertaken in some of Europe’s top research institutions. The Showcase is designed to inform industry of new developments in media computing and communication, to facilitate the formation of productive partnerships and to promote the commercialisation of research products. If your company is interested in any of the work exhibited here, please contact EMC2 for further details.
Innovative coding technique for delivering scalable video on overlay networks.
Improved video compression via enhanced inter-prediction in the HEVC video codec, using shift transformation to reduce complexity.
Vision based 3D reconstruction and discrepancy analysis tool supports precise positioning and alignment of safety critical installations.
A method for highly accurate hippocampus and amygdala segmentation in MR images.
YAAFE is an efficient toolbox that computes audio features out of audio signals.
A low-cost system for real-time 3D capture and reconstruction of moving objects and humans using multiple Kinect sensors and a single host PC.
Smartphone application for searching online product catalogues by sketch, image or text query.
Multimodal search technology enabling combinations of query types, including text, images, 3D models or sounds, for more reliable retrieval of desired content.
High performance prediction tool for possible complexes that can be produced by the interaction between two proteins.
Capture of users' responses to images enables automatic tagging of media content.
High accuracy classification of proteins based on the geometric similarity of their molecules.
An improved shape/ structure descriptor for more reliable 3D object recognition.
Augmented reality mirror system enables customers to try on garments or footwear quickly and interactively.
A tool for semi-automatically measuring the distance between the arterial walls in ultrasound images of the brachial artery.
A method for computing positional and intent behaviours in team sports based on novel analyses of player positions and movements on the sports field.
Computer vision based recognition of team activities in sports using Poisson equation.
A machine-learning framework for sentiment analysis of online content including reviews, blogs and social media.
Plugin architecture for development and automated evaluation of interactive image segmentation algorithms.
Hybrid depth/ inertial sensor technology providing robust, low-cost capture for all environments.
Open source software based on cognitive science principles for navigating large volumes of image data from life-logging devices.
Multimedia library search and navigation tools for professional, educational (both for educators and researchers) and home users.
Activity recognition technology for sports and other activities, using machine learning in conjunction with smartphones.
Virtual museum/ gallery using off-the-shelf tools to enable interaction with cultural/ historical artifacts in a realistic 3D museum environment.
Faster, more efficient techniques for converting H.264/AVC video bitstreams to high-quality HEVC bitstreams.