Below you’ll find selected projects in which I participate or participated.
Intelligent system of effective analysis of diagnostic and repair work of industrial devices with the help of mobile units and advanced image analysis. 2018-…. (POIR)
Links-on-the-fly Technology for Robust, Efficient and Smart Communication in Unpredictable Environments. 2013-2016 (FP 7)
The project goal is to develop an intelligent information system to detect safety risks caused by traffic for persons with a vision impairment. It is focused on many different way of supporting visual impairment people. It include but are not limited to: sensor and vision based detection of potential obstacles and threats, navigation help based on GPS and reading street and bus names.
My responsibility in this project is to develop vision based navigation assistance for visually impaired individuals using general purpose mobile devices.
Visual analysis is based on a pair of digital cameras which acquire images from the user’s surroundings. This data is synchronized and used to produce a depth map a visual representation of the distance between the user and other objects, which constitute potential obstacles and threats. The aim of the system is to detect these objects by means of depth map processing (segmentation and classification) into selected threat categories. Scenarios under research here include, but are not limited to: movement around plane areas, in inclined regions, negotiating curbed pavements, going up or down stairways, or finding a way through doorways. Finally, the extracted information about distance to the closest obstacle, the nature of the threat to the user, and overall situation assessment, will be combined in order to output direction tips.
Examples of depth map reconstruction for indoor and outdoor scenarios are presented below:
The system was created and makes use of standard hardware components such as web cameras, a single-board Raspberry Pi computer, Android-based mobile phone (HTCOne), and a software toolkit based on OpenCV. The technological demo was created and tested. It shows the potential of contemporary mobile platforms which are able to perform depth reconstruction from stereovision sequence in real-time (~5 fps).
Since I’m convinced that mobile phones, in the near future, will be even faster and cheaper, and thus will allow for the creation of a navigation aid as a mobile application and an inexpensive stereo camera as a form of a smartphone accessory.
Further work includes: developing better algorithms for obstacle recognition (especially stairways up/down and single stair) and creation a prototype. 2011-2014 (NCBiR)
Socially Aware, collaboRative, scAlable Coding mEdia distributioN was a research initiative funded partially by the Information Society and Media Directorate General of the European Commission under the Seventh Framework programme. The SARACEN initiative will research on distribution of multimedia streams supported through innovative techniques, both as regards media encoding and media distribution including p2p schemes, where the peer nodes will participate in an end to end media distribution system making use of social networking related information.
I was involved in integration 3D delivery path in SARACEN infrastructure. 2010-2012 (FP 7)
The project covers the development and testing of infrastructure and services for the future generation Internet, i.e. IPv6 Internet and Future Internet. It is expected that new generations of Internet (one of the research priorities in the scope of European Union Framework Programmes) will contribute substantially to civilizational development in Europe by using their capabilities in all or almost all areas of human activity.
It was very large project: from the physical layer to the application. I was responsible for 3D content presentation. My work includes: QoE tests of 3D content presentation and analysis of artifacts in 3D displays made in various technologies. 2010 – 2013 (OP IE Operational Programme ‘Innovative economy’)
Integrated system supporting bronchoscopy laboratory integrating: the archiving, management and semantic ordering the procedures recordings, automatic image-based diagnostic data detection and retrieval, and interactive visualisation using computed tomography data
It is CAD/CAI, a system for supporting bronchoscopy laboratory. Bronchovid consists of data acquisition, comprehensive data repository, real-time analyser, off-line editor and viewer as well as treatment planning. It deal with video sequences and CT data (3D visualization).
My responsibility in this project was to design computer system, develop and implement efficient way of data processing. The system was implemented by means of MPI interface (MPICH implementation). It makes use of multiprocess NUMA type computer. 2007-2010 (MNiSW)
The objective of the VECTOR project is to develop intelligent endoscopic capsules using innovations in micro- and nanotechnology. The VECTOR project aims at investigating and developing a miniaturised robotic pill for advanced diagnostics and therapy in the human digestive tract. The project mission is to make a significant contribution to the diagnosis and treatment of digestive cancers and their precursors and to strengthen the competitiveness of the European biomedical industry through innovative technologies.
For more information see: vector-project.com
Projects before 2005: DSM, xDSL and wavelet.