dc.contributor.author | Matovic, Mark Phillip | |
dc.date.accessioned | 2021-05-07T07:41:05Z | |
dc.date.available | 2021-05-07T07:41:05Z | |
dc.date.issued | 2020-12-22 | |
dc.identifier.citation | Matovic, M.P. (2020). Uganda Traffic Sign Recognition System Using Deep Learning. (Unpublished undergraduate dissertation) Makerere University. Kampala, Uganda | en_US |
dc.identifier.uri | http://hdl.handle.net/20.500.12281/10594 | |
dc.description | A Report submitted in partial fulfillment of the requirements for the
Degree of Bachelor of Science in Electrical Engineering
of Makerere University. | en_US |
dc.description.abstract | Increase in the number of vehicles on road necessitates the use of automated systems for driver
assistance. These systems form important components of self-driving vehicles also. Traffic
Sign Recognition system is such an automated system which provides contextual awareness for
the self-driving vehicle. CNN based methods like Faster R-CNN for object detection provide
human level accuracy and real time performance and are proven successful in Traffic Sign
Recognition systems. Single stage detection systems such as YOLO and SSD offer state-ofthe-art realtime detection speed. In this report we design a traffic sign recognition system by
applying deep learning techniques in particular using the Sinlge-Shot Detector algorithm. The
network training and evaluation are done using a Ugandan traffic sign detection dataset that
we collected ourselves as part of the project. We detect only a subset of the Ugandan traffic
signs considering the shortage of data for some traffic signs. | en_US |
dc.language.iso | en | en_US |
dc.publisher | Makerere University | en_US |
dc.subject | Traffic Sign | en_US |
dc.subject | Deep Learning. | en_US |
dc.title | Uganda Traffic Sign Recognition System Using Deep Learning. | en_US |
dc.type | Thesis | en_US |