Danijel Skočaj, PhD

Danijels.jpg
Associate Professor
Head of the laboratory
danijel.skocaj@fri.uni-lj.si
+386 1 479 8225

Visual Cognitive Systems Laboratory
Faculty of Computer and Information Science
University of Ljubljana
Večna pot 113
SI-1000 Ljubljana
Slovenia



Research

The main research interests: computer vision, pattern recognition, deep learning, cognitive vision, cognitive systems, visual learning and recognition, incremental learning, interactive learning

Defect-detection.png
We explore deep learning models for industrial quality control. Our focus is on surface-defect detection for which we have developed a novel two-stage architecture that uses segmentation network in the first stage and decision network in the second stage. We also present a novel dataset with real-case scenario for surface defect detection. This research is done in collaboration with the industry partner Kolektor Group d.o.o.
Traffic-signs.png
We explore automation of traffic-sign inventory management using deep-learning models. Models such as Faster R-CNN and Mask R-CNN are improved and applied to traffic sign detection. Instead of specializing in automated detection for only several traffic sign categories we explore possibility of automating the detection of over 200 different traffic signs that are needed to automate the traffic-sign inventory management.
GeorgeSmall.png
In the EU FP7 project CogX we have developed a corious robot George; a complex heterogenuous distributed system for interactive learning of visual concepts in a dialogue with a tutor. Our objective was to demonstrate that a cognitive system can efficiently acquire conceptual models in an interactive learning process that is not overly taxing with respect to tutor supervision and is performed in an intuitive, user-friendly way.
IntLearnSmall.png
In our research work we address the problem of interactive learning of categorical knowledge. We describe, implement, and analyse several teacher and learner-driven approaches that require different levels of teacher competencies and consider different types of knowledge for selection of training samples. We also introduce a formal model for describing the learning strategies, and evaluate them using the proposed evaluation measures.
RoomCategorization.png
We have designed approaches for 2D laser-range-data-based room categorization that are grounded on a compositional hierarchical representation of space. We have also developed a part-based image representation that is suitable for robust vision-based room categorization.
SsMethodsSmall.png
One of the main research topics of our group in the past were subspace methods. We have proposed several methods for robust estimation of subspace coefficients and for learning subspace representations. By combining the properties of the reconstructive and the discriminative subspace methods we were able to extend the standard approaches into incremental and robust ones, and to show the efficiency of the proposed methods in many computer vision tasks.
AffordancesWorkspace.jpg
The main task of the affordance learning algorithm as defined in our framework, is to identify significant clusters in the result space and associate these clusters with data in the object property space. This allow for the affordances of novel objects to be broadly classified in terms of result space clusters, by observing their respective object property features and using them as input to a classifier trained by the affordance learning algorithm.

Main Projects

Current projects

DIVIDlogo1.png
The objective of the proposed project is to develop novel deep learning methods for modelling complex consistency and detecting inconsistencies in visual data using training images annotated with different levels of accuracy.
ARRS Basic research project.
Project duration: 2018 - 2021
ARRSLogo.png
The research group is involved in basic research in computer vision, with emphasis on visually enabled cognitive systems involving visual learning and recognition. Topics include recognition and tracking of objects, scenes, and activities in visual cognitive tasks such as smart vision-based detection and positioning using wearable computing as well as for mobile robots and cognitive assistants.
Project duration: 2009-2014.

Past projects

TraPriLogo1.jpg
The project addresses the use of computer vision algorithms for object recognition and augmented reality on smart mobile devices. PKP project, 2018 (pages in Slovenian).
Villard logo.png
The main goal of the project is to develop a framework for semi-supervised interactive incremental learning as well as specific methods for visual learning and recognition that will increase the quality and efficiency of large visual information databases maintenance.
Applied ARRS project.
Project duration: 2014 - 2017
3d carve blue.png
The project addresses the use of computer vision algorithms for contactless foot measuring techniques that facilitate a reliable online recommendation system for footwear purchasing.
PKP project, 2014 (pages in slovenian).
CogXLogo.png
The high level aim of this project was to develop a unified theory of self-understanding and self-extension with a convincing instantiation and implementation of this theory in a robot. By self-understanding we mean that the robot has representations of gaps in its knowledge or uncertainty in its beliefs. By self-extension we mean the ability of the robot to extend its own abilities or knowledge by planning learning activities and carrying them out. The project involved six universities and about 30 researchers.
CoSyLogo.jpg
The main goal of the project was to advance the science of cognitive systems through a multi-disciplinary investigation of requirements, design options and trade-offs for human-like, autonomous, integrated, physical (eg., robot) systems, including requirements for architectures, for forms of representation, for perceptual mechanisms, for learning, planning, reasoning and motivation, for action and communication.
CogVislLogo.png
The main objective of the EU FP5 project CogVis was to provide the methods and techniques that enable construction of vision systems that can perform task oriented categorization and recognition of objects and events in the context of an embodied agent.


Selected Publications


Full list of publications



Teaching

Teaching in 2018/19

Old courses

  • Scientific skills 2 (Veščine v znanstvenem delu 2, 3.st.)
  • Production of multimedia content (Produkcija multimedijskih gradiv)
  • Artificial intelligence (Umetna inteligenca, 3.st.)
  • Algorithms and data structures 1 (Algoritmi in podatkovne strukture 1(Sežana))
  • Distributed intelligent software technologies (Porazdeljene inteligentne programske tehnologije)
  • Data structures and algorithms (Podatkovne strukture in algoritmi (PeF))
  • Computer science (Računalništvo (FPP))

All information about the courses is provided on the internal pages of FRI.



Membership



Links

Research partners

Events