Thesis Details

Detekce kolizí vozidel

Bachelor's Thesis Student: Kruták Martin Academic Year: 2015/2016 Supervisor: Špaňhel Jakub, Ing.
English title
Vehicle Collision Detection
Language
Czech
Abstract
This bachelor thesis decribes a system for detection and tracking of multiple vehicles from a surveillance camera with a collision detection. The focus is on detection and prediction of collisions of vehicles in one direction - towards the camera. System is not fully automatic, meaning that some initial settings are needed (e.g. lines on the road) to quarantee a good functionality of the system. Accurate vehicles' contour is obtained in the detection phase, and object centroids are calculated. Each detected vehicle is assigned to the specific lane and tracked separately. This thesis then describes the method of prediction and detection of a collision. A rectangle is created around the ground part of every vehicle. This rectangle of
each of the vehicles is enlarged and checked for the overlaps. Those rectangles that overlaps are then subject to further analysis for the collision detection. Experimental results show a success rate of 72 % for the accurate rectangle construction being a crucial part for the
collision detection. The advantage of the proposed system is its possible usage in surveillance cameras monitoring the traffic flow on highways.
Keywords

Multiple vehicle tracking, collision prediction, collision detection, vehicle detection

Department
Degree Programme
Information Technology
Files
Status
defended, grade C
Date
16 June 2016
Reviewer
Committee
Herout Adam, prof. Ing., Ph.D. (DCGM FIT BUT), předseda
Drahanský Martin, prof. Ing., Dipl.-Ing., Ph.D. (DITS FIT BUT), člen
Chudý Peter, doc. Ing., Ph.D. MBA (DCGM FIT BUT), člen
Očenášek Pavel, Mgr. Ing., Ph.D. (DIFS FIT BUT), člen
Strnadel Josef, Ing., Ph.D. (DCSY FIT BUT), člen
Citation
KRUTÁK, Martin. Detekce kolizí vozidel. Brno, 2016. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2016-06-16. Supervised by Špaňhel Jakub. Available from: https://www.fit.vut.cz/study/thesis/18708/
BibTeX
@bachelorsthesis{FITBT18708,
    author = "Martin Krut\'{a}k",
    type = "Bachelor's thesis",
    title = "Detekce koliz\'{i} vozidel",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2016,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/18708/"
}
Back to top