Big data analytics face the challenge of carrying out data analytics, improving the quality of available data, performing accurate prediction and visualization tasks dealing with extremely large and unstructured or semi-structured datasets.
The expertise of our research group goes beyond traditional approaches of human recognition, which are often characterized by increased obtrusiveness and raise strong disapproval by the public and their potential users.
We research and develop technologies that focus on supporting the healthcare practice, through advanced multisensorial networks signal processing, computer vision algorithms and inference engines for user monitoring and behavioural modeling, as well as through VR-based intervention and reinforcement tools.
Our research group is developing new algorithms and novel technologies that combine computer vision, 2D/3D image and video processing and pattern recognition for robust Occupancy Extraction (human presence and movements). Novel algorithms have been developed that cope with multiple-space occupancy extraction in indoor/outdoor environments using privacy-preserving sensors (depth and thermal cameras), whereas the extracted occupancy models can be used for Building Energy Performance Analysis and Simulation and/or for land surveillance.
CERTH/ITI is one of the largest European independent research institutes in the Human Computer Interaction (HCI) domain while its research focuses on the accessibility and usability of ICT applications and the design of ubiquitous, adaptive and accessible user interfaces. Moreover the Institute has been active in the design and development of multimodal interfaces for various application areas including ambient intelligence, assistive technologies and natural interaction in virtual reality environments.
The analysis of remote sensing data for Earth surface monitoring is one of the research priorities of the working team. The team designs and develops advanced methodologies for the analysis and processing of satellite, airborne and field acquired data to support and initiate services for the environment and human well-being.
The group is developing new algorithms, technologies and architectures for applications in the areas of Security. Emerging technologies have been designed and developed by the Research Team of the Lab not only for indoor and outdoor security and surveillance but also for cyber-security.
Semantic annotation of existing web services comprises a fundamental requirement for enabling more efficient and accurate search and discovery of services on the semantic web ecosystem. In order to efficiently deal with the growing presence of web services, more automated mechanisms are required, because manual semantic annotation is a long, tedious and error-prone process, based on subjective and monolithic knowledge.
Nowadays, the interest for developing intelligent transportation systems constantly increases. Transport optimization, either for individuals or fleets, has significant social, economical and environmental impact. Forecasting vehicle traffic within multiple steps ahead of present time is certainly a challenging task whose successful outcome could improve current urban mobility services.
The group exhibits substantial research activity, both academic and industry-oriented, as well as technology transfer actions, in the area of virtual, augmented and mixed reality. This area includes modeling and simulation of complex virtual environments, haptic force feedback applied research, 3D modeling and compression, deformable objects and cloth modeling, collaborative virtual environments, new sensor development for head/hands/body tracking, multimedia analysis/synthesis, gesture recognition, head motion modelling and tracking, advanced applications of virtual/augmented/mixed reality in education and training, e-health, assistive technologies, culture, industry and e-business.
A core research area of the group is the visualization of multimodal data of multimedia datasets, with applications in multimodal search engines. The research includes graph-based visualization methods, combination of modalities using weighted-sum techniques and multi-objective optimization.