computer vision, artificial intelligence, embedded systems, robot vision, human motion analysis
I am employed as Assistant Professor at Faculty of Electrical Engineering, University of Ljubljana, Slovenia. I teach undergraduate and graduate courses on computer vision, machine/industrial vision, embedded systems and network technologies.
During my study and employment at the University of Ljubljana, I was member of Laboratory for Artificial Perception, Laboratory for Imaging Technologies, Machine Vision Laboratory, and finally, the Laboratory for Machine Intelligence, which is my current affiliation inside the Faculty of Electrical engineering.
My research history is as follows.
My PhD in 2004 dealt with analysis of human motion using computer vision algorithms, with special attention to the influence of scale on human motion observation. During my PhD and several years thereafter I had close collaboration with scientists from the field of sports, which enabled me to acquire massive amounts of hard-to-get annotated human motion data, and this research collaboration with human motion specialists is still ongoing. In years 2004-2005 I participated in project for US based startup company to develop system for offline tracking of sport players. System remains in use at Faculty of Sports at University of Ljubljana.
With new technologies appearing, my research expanded into visual sensor networks, especially in relation to analysis of human motion and reidentification of humans in distributed camera systems.
I worked, and I am still working on methods to adapt modern methods of artificial intelligence, especially deep networks, to produce results that are close to human understanding.
Finally our laboratory has collaborated on multiple successive projects on developing computer vision algorithms for autonomous vehicles, especially water-borne vehicles (unmanned surface vehicles, USV), and this represents major part of my research work for the past few years.
In the lecture, I will present some of the common sensor modalities that are used in autonomous and semi-autonomous vehicles. After brief introduction to RGB cameras and extension to stereo matching, we will examine LIDAR, automotive radar, thermographic cameras, polarization cameras, inertial sensors, and high-precision GPS. The focus of the lecture will be on the nature and properties of data provided by these sensors with only brief explanation of each sensor’s physics. I will focus on possible use cases for each modality in the fields of image processing and artificial intelligence, as they relate to self-driving vehicles. As a benefit to students, a short dataset, containing the data from the above listed sensors will be provided for download, so that the students can examine the data and develop their own algorithms during or after the summer school. The multimodal dataset was captured by our own multimodal sensor system for water-borne autonomous vehicles.
Keywords: artificial intelligence, autonomous driving, cameras, LIDAR, RADAR