Home Search AA
 
VISTA - COMPUTER VISION INNOVATIONS FOR SAFE TRAFFIC

VISTA is a project whose overall objectives are strengthening of technology transfer and commercialization capacities of partner HEIs, transfer of existing computer vision applications from HEIs to SMEs, and developing new traffic- and transportation-related computer vision applications with commercial potential in collaboration with SMEs in the automotive industry sector.

The project is funded from the Regional Competitiveness Operational Programme 2007 - 2011 for Community Assistance under the IPA Regional Development Component in Croatia.


Published: 2014-05-14 at 16:09
Edited: 2014-05-14 at 16:09
Research seminar "A Novel...

We invite you to a VISTA research seminar:

 

"A Novel Approach for On-road Night-time Vehicle Headlight Detection and Tracking"

 

held by Darko Jurić, mag. ing.

 

The seminar will be held on friday 16.5.2014. at 14:15 in TCR.

 

More information about the seminar and about the speaker can be found in the detailed news content.

Abstract

One of the main issues during night-time driving is a good visibility of the road ahead. Although the traffic volume is much lower during the night-time, percentage of traffic accidents is much higher. High beams are used too rarely or in non-appropriate situations thus dazzling other drivers, which can be lethal. In urban areas there is an increased need for attention which can lead to an accident when mixed with driver fatigue and unpredictable preceding vehicle movements. Therefore advanced driver assistance systems (ADAS) can lead to more safety driving by automatically controlling headlights or estimating a distance between vehicles. Headlight control system demands an early vehicle detection where only camera based approaches are suitable. In this seminar, recent methods are described that rely on single camera input along with its drawbacks. New method for vehicle detection and tracking is introduced which is capable to correctly detect and track vehicle headlights in rural areas, where detection at longer distances is required, as well as in urban areas, where an extensive clutter is present. Detection procedure does not require image binarization and thresholding or any other preprocessing technique, which is commonly used in other methods, thus increasing robustness and performance. Tracking method efficiently associates object detections with existing tracks and provides track management system which deals with object appearance and temporary occlusion and can deal with false detections which are inevitable introduced by frame-based detector. 

 

CV

Darko Jurić received his BSc and MSc degree from the Faculty of Electrical Engineering and Computing in Zagreb. He finished his undergraduate study program in Computing in 2010 and in 2012 his master study program in Computer Science with a specialization in Image processing and analysis. Currently, he is employed at the Faculty of Electrical Engineering and Computing, University of Zagreb, as a research engineer at the Department of Electronic Systems and Information Processing within Image Processing Group, where he is pursuing his PhD degree. His research interests are in the areas of image processing and machine learning which is used for solving problems in computer vision.

Iva Harbaš
News list
SEARCH
 
PARTNERS
 

 


FUNDING
 

This project is cofinanced by the European Union from the European Regional Development Fund.

 

 
Disclaimer
 
The contents of this website are the sole responsibility of the University of Zagreb Faculty of Electrical Engineering and Computing and do not necessary reflect the views of the European Union.