Filters
cris logo
-
New search Filters
Select from list
Displayed from Show more
You have reached the maximum number of displayed search results.
All results displayed
No results are available for the search performed
Displayed from
You have reached the maximum number of displayed search results.
All results displayed
Loading results
Obtaining statistical data

Projects / Programmes source: ARIS

Computer Vision

Edit
Periods
January 1, 2015 - December 31, 2018
Research activity

Code Science Field Subfield
2.07.00  Engineering sciences and technologies  Computer science and informatics   

Code Science Field
P176  Natural sciences and mathematics  Artificial intelligence 

Code Science Field
1.02  Natural Sciences  Computer and information sciences 
Keywords
computer vision, visual learning, incremental learning, cognitive systems, visual concepts, object recognition, visual tracking, vision-based user interfaces, human faces, digital heritage, 3D point clouds
Evaluation (rules)
source: COBISS
Evaluation of bibliographic research performance indicators according to ARIS methodology
Citations Citations for bibliographic records in COBIB.SI that are linked to records in citation databases
source: WoS source: Scopus source: COBISS
Researchers (16)
no. Code Name and surname Research area Role Period No. of publications
1.  22472  PhD Borut Batagelj  Computer science and informatics  Researcher  2015 - 2018  192 
2.  31252  PhD Narvika Bovcon  Computer science and informatics  Researcher  2015 - 2018  308 
3.  29381  PhD Luka Čehovin Zajc  Computer science and informatics  Researcher  2015 - 2018  124 
4.  11161  PhD Aleš Jaklič  Computer science and informatics  Researcher  2015 - 2018  119 
5.  30155  PhD Matej Kristan  Computer science and informatics  Researcher  2015 - 2018  323 
6.  05896  PhD Aleš Leonardis  Computer science and informatics  Researcher  2015 - 2018  455 
7.  39227  PhD Alan Lukežič  Computer science and informatics  Junior researcher  2016 - 2018  51 
8.  06618  PhD Jasna Maver  Computer science and informatics  Researcher  2015 - 2018  99 
9.  19226  PhD Peter Peer  Computer science and informatics  Researcher  2015 - 2018  408 
10.  32043  PhD Robert Ravnik  Computer science and informatics  Researcher  2015  23 
11.  50002  Anže Rezelj  Computer science and informatics  Technical associate  2017 - 2018  0 
12.  18198  PhD Danijel Skočaj  Computer science and informatics  Researcher  2015 - 2018  309 
13.  09581  PhD Franc Solina  Computer science and informatics  Head  2015 - 2018  640 
14.  23401  PhD Luka Šajn  Computer science and informatics  Researcher  2015 - 2018  108 
15.  38300  MSc Peter Uršič  Computer science and informatics  Technical associate  2016  17 
16.  52095  Matej Vitek  Computer science and informatics  Junior researcher  2018  20 
Organisations (2)
no. Code Research organisation City Registration number No. of publications
1.  0581  University of Ljubljana, Faculty of Arts  Ljubljana  1627058  97,992 
2.  1539  University of Ljubljana, Faculty of Computer and Information Science  Ljubljana  1627023  16,242 
Abstract
The research program is involved in basic and applied research in artificial cognition or more specifically in computer and cognitive vision. This segment represents one of the most important components of intelligent systems, information systems or robotic systems, and is a crucial part of numerous applications ranging from automatic query of large image and video data bases, face recognition, analysis of human behavior, visual surveillance and tracking, autonomous vehicles (cars, helicopters, submarines) and control of various types of robots, ranging from industrial robots to humanoid and special purpose robots. Although computer and cognitive vision made large advances in the past years, numerous challenges remain unsolved. Among these problems are challenges how to make artificial  perception more robust in the sense of recognition and categorization under more general and changing environmental conditions and considering huge variability of visual entities. In fact, these problems are interconnected since modeling of a huge number of visual categories can assure regularization for inference of visual perception under consideration of contextual and a priori information. A similar large challenge represents efficient, robust and adaptive tracking of visual entities.   The goals of the research program are to contribute to the world  knowledge in these areas by proposing new methods for modeling, learning and inferring a large number of visual categories, new methods of incremental learning and original contributions to visual tracking and analysis of human behavior. The research program will continue its previous research and in enhance some of its methods, that are already among the most advanced in this area. The program will do theoretical work on generalized representations of hierarchical compositionally, on probability models of incremental learning and adaptive multilevel models of visual tracking.   The research program will, as in the past, a considerate part of its activities devote to verifying theoretical results on real platforms such as mobile robots, active sensory systems and intelligent mobile devices. The team will also contribute to sharing of knowledge in the form of publicly accessible annotated databases of image and video collections, organizing challenges in the framework of international conferences and proposing of evaluation protocols and metrics. Finally, the research program will take care for transfer of theoretical knowledge to practical applications in cooperation with end users, building on their experience (use of computer vision in web commerce, documentation in digital heritage, new media fine art, ...) and will look for opportunities to start spin-off and spin-out companies.
Significance for science
Computer vision is one of the key elements of autonomous intelligent systems which are at the center of interest of European research policy. Computer vision is one of the most important ways of non-contact perception of the environment. Any automatization of this perception requires automatic interpretation of images. Because of continuously increasing size of digitalized image databases in various scientific fields, these information sources can not be handled anymore in a conventional way but call for search and analysis of data using computer vision methods. On the other hand, from various sensors flows a growing life image flow that needs to be analyzed in real-time. Computer vision is therefore important for scientific development in several scientific fields to handle visual information, for example in recent emergence of Digital Heritage. However, we should not limit ourselves just to solving partial problems in various application domains but to study computer vision methods also from the more basic standpoint of cognitive science and artificial intelligence, to answer the old question of whether such problems are solvable bottom-up just by providing ever better processing of input signals or if top-down interventions are needed by providing knowledge of a wider cognitive context. Lately, in that sense one can observe the tendency for interdisciplinary research in artificial intelligence, computer vision and robotics on one side and psychology, neurophysiology, cognitive science and similar disciplines on the other side. The latter disciplines could benefit from efficient computational models of artificial cognitive systems which could facilitate the understanding of natural and human cognitive systems.
Significance for the country
Knowledge of computer vision is important for technological development in Slovenia. Use of robots in industry is often possible only in combination with computer vision. Quality assurance in modern industrial production is very important. A very important dimension in quality is the visual appearance of individual parts or of the final product. Visual quality inspection is important in packaging typical industrial products, pharmaceutical products or even agricultural products. Computer vision is gaining importance also in culture. Since more and more visual data is digitized or produced in digital form, it can be efficiently handled only with the help of computer vision methods. Therefore we already cooperate with the Institute for the protection of cultural heritage of Slovenia, museums and galleries on 3D documentation, analysis and search in visual data bases. This trend in digital heritage is evident also in EU research programs. The importance of computer vision is growing also in post-industrial society. One of the most important problems that we try to solve using image capture and analysis is safety (in transpiration, in public spaces, against terrorism, caring for elderly). The safety issue is often interwoven with other social issues, in particular with privacy. Biometry (faces or other features), analysis of behaviours that are captured by security cameras, control of traffic or people so that help can be provided on time; all of these are tasks for computer vision. Members of our research program are one of the few Slovenian experts who can produce expert opinions on image and video information for Slovenian courts of law. Computer vision is even gaining importance in modern fine arts since using images in user interfaces offers the simplest way of introducing interaction to contemporary art installations. In this area we cooperate with the Department of new media at the Academy of fine arts and design for almost 20 years. New media art represents for our research program an exciting area for experimentation since the development cycles are very short and the feedback from the end users is readily available. Computer vision is also the key technology for cognitive systems. The importance and benefits of cognitive systems can be clearly deducted from the large investments to this area of research, both in private and public sectors. Due to the robustness and generality of artificial cognitive systems, their user friendliness and adaptability, one can expect that this technology will be used in many different application areas ranging from industry to our homes. Due to a high level of knowledge in computer vision, Slovenia has been made visible and recognisable in the international community of vision researchers. With top notch research we contribute to the discipline and are also able to transfer the latest knowledge back to Slovenia. With the international exchange of researchers, in particular doctoral and postdoctoral researchers, we contribute to better education and recognition of Slovenia.
Most important scientific results Annual report 2015, 2016, 2017, final report
Most important socioeconomically and culturally relevant results Annual report 2015, 2016, 2017, final report
Confirmation required
Views history
Favourite