Thesis Details
Mapování dopravního značení za pomoci metod zpracování obrazu
The following Bachelor's Thesis deals with traffic sign recognition in video clips, obtaining GPS records and inserting traffic sings with accurate GPS co-ordinates into OSM central database. In each of Thesis' chapters are in sequence introduced methods of image detection and classification, consecutive familiarization with OSM project and its JOSM plug-in. Afterwards there will be presented an application and an applicative plug-in design and implementation process. The final chapter is represented as the results of testing the application in 10 video clips. The conclusion contains an evaluation of the Thesis with possible extensions.
Computer vision, Traffic sign recognition, Color segmentation, Object detection and object classification, HOG, SVM, OpenCV, JOSM, OpenStreetMap
Fučík Otto, doc. Dr. Ing. (DCSY FIT BUT), člen
Ryšavý Ondřej, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Smrčka Aleš, Ing., Ph.D. (DITS FIT BUT), člen
Španěl Michal, Ing., Ph.D. (DCGM FIT BUT), člen
@bachelorsthesis{FITBT17265, author = "Vladim\'{i}r Le\v{s}ko", type = "Bachelor's thesis", title = "Mapov\'{a}n\'{i} dopravn\'{i}ho zna\v{c}en\'{i} za pomoci metod zpracov\'{a}n\'{i} obrazu", school = "Brno University of Technology, Faculty of Information Technology", year = 2015, location = "Brno, CZ", language = "czech", url = "https://www.fit.vut.cz/study/thesis/17265/" }