The software provides fully automatic decomposition of surface electromyograms, recorded in isometric muscle contractions, into contributions of individual motor units, thus, noninvasive investigation of muscle control strategies, also in children and needleintolerant patients. In the last four years, it has been tested in more than 1000 healthy subjects and patients with neurodegenerative diseases. It is currently being used in investigations of children with cerebral palsy, in computer-aided diagnosis of Parkinsonian and essential tremor, in studies of diabetes, in planning of cleftlip surgeries, in design and evaluation of rehabilitation techniques after stroke and in studies of muscle atrophy and hypertrophy. The areas of other potential applications include ergonomics, training of athletes, studies of impact of microgravity on human motor system and myocontrol of prosthetic devices. DEMUSE tool is available at http://demuse.unimb.si/. The tool is used by researchers who are analyzing neuromuscular system. We presented it to the end users in journal manuscripts, at scientific conferences, international workshops and fair presentations.
F.06 Development of a new product
COBISS.SI-ID: 18426390This invention relates to the compression of 3D geometric meshes and point cloud data. The method’s embodiment consists of a binary voxelizator, slice decompositor, chain code encoder, and entropy encoder. The binary voxelizator is responsible for voxelization of 3D points from 3D mesh vertices or point cloud data, where the resulting voxels within the 3D grid contain a binary scalar value (i.e. empty or occupied). The compression is near-lossless because of the quantization induced by the voxelization. Further, only the compression of geometry is considered. The voxel 3D grid is then divided into 2D slices having thicknesses of one voxel. The slices represent 2D raster grids, and are perpendicular to the coordinate axis of the shortest bounding box side of the considered 3D mesh or point cloud. Each slice contains one or more 2D segments consisting of occupied pixels. The segments are preprocessed before they are encoded by the chain codes. Optionally, thinning is applied on each segment in order to generate contours with widths of one pixel. The contours are then encoded by a chain code algorithm. The starting positions (x and y coordinates) of each contour are coded as a nearest offset to either the grid’s centre of the 2D slice, or one of the previously coded segments, or from one of the grid’s four corners. The starting position is then coded using the variable length coding (VLC) scheme. The resulting chain codes from different segments are then further compressed by using entropy coding. The embodiment of the decompression is done by entropy-based decoding, chain code decoding into 2D segments, constructing a 3D grid out of decoded slices, and extraction of points from voxels. 3D points denoting extracted voxels’ centre positions are smoothed by average smoothing over each point’s local neighbourhood. Optionally a reconstruction algorithm is applied in order to construct the 3D mesh. The presented method is especially important for computer multimedia researchers, as well as end users of 3D multimedia content (e.g. 3D models and point clouds), since it allows faster 3D data exchange, as well as adaptive 3D data processing on different platforms.
F.32 International patent
COBISS.SI-ID: 20741398The invention provides a method for compressing three dimensional point data. The method includes receiving a dataset including a plurality of data points in a sequence, each including at least four types of attribute values i.e. an X-coordinate value type, a Y-coordinate value type, a Z-coordinate value type, and at least one associated scalar value type. The method performs predictive coding of a sequence of attribute values of the same type from the dataset to generate a sequence of prediction errors for a given attribute value type. the variable length coding of the sequence of prediction errors is applied then to generate byte-streams of variable length codes. These are finally compressed using entropy coding. The invention significantly improves the efficiency of geometry representation of big point sets and is, thus, a valuable tool for data archiving and data sharing. Data producers can distribute the results of their acquisitions over the internet, which was not possible for such big point sets before. The invention was presented on international conferences, international workshops, fair presentations and, more importantly, at professional meetings with interested industry. As such, the invention was integrated in several our tools, developed either as our own products or in collaboration with industrial partners.
F.32 International patent
COBISS.SI-ID: 19503126The infrastructure consists of Slovenian universities’ repositories (repository of University of Ljubljana, digital library of University of Maribor, repository of University of Primorska and repository of University of Nova Gorica), a repository for research organisations, repository for faculties which are not part of four universities and a national portal that aggregates content from the repositories and other Slovenian archives (Digitalna knjižnica Slovenije (dLib.si), VideoLectures.NET, digital library of Ministry of Defence (DKMORS), Slovenian academy of science journals repository, open access journals from Slovenian Academy of science and Social Science data archive (SDA). The national portal ‘openscience.si’ provides a common search engine, recommendations for similar publications, and similar text detection. We have developed the repository software which is integrated with the universities' information and authentication systems and with the COBISS.SI. During the project the necessary legal background was defined and processes for mandatory submission of electronic theses and dissertations as well as of research publications were designed. The processes for data exchange between the institutional repositories and the national portal, and the processes for similar text detection and recommendation system were established. Bilingual web and mobile applications, a recommendation system and the interface suitable for persons with disabilities are provided to the users from around the world. Establishment of Slovenian open access infrastructure is important for all Slovenian educational and research institutions. Open accessibility of publications will enable Slovenian researchers to gain more visibility of their research. Consequently the visibility of research activities on the state level will also increase. With the help of the national open access infrastructure companies will be able to use the results of publicly funded research and the results of the final works of the study that were difficult to access before this infrastructure has been established. We also expect that the open accessibility of research results and the potential for their further use will improve the efficiency of public funding of research activities from national or foreign sources. The achievement was presented at several professional and scientific meetings in Slovenia and abroad (COBISS-SI IDs: 20634902, 18348566, 18441238, 18441494, 86937857), in web and print media, on radio stations, on television (COBISS ID 601128) and in webinar on Council of Europe Advocacy week (http://www.academicintegrity.eu/wp/materials/tools-supporting-academic-integrity/).
F.06 Development of a new product
COBISS.SI-ID: 18052630ROSUS – Computer image processing and its application in Slovenia is a professional conference that, since 2006, has been organized every year by the Institute of Computer Science. The conference connects researchers in the fields of Image Processing and Machine Vision with users of this knowledge, whereby users are coming from diverse industrial environments, biomedicine, sport, entertainment, and related fields. The conference is advertised in public media and via the World Wide Web. Peer-reviewed conference contributions are published in the publicly accessible conference proceedings.
B.01 Organiser of a scientific meeting
COBISS.SI-ID: 94131201