Traffic Sign Detection and Recognition
Session
Computer Science and Communication Engineering
Description
Traffic sign detection and recognition (TSD, TSR) has become part of new technologies in order to support the development of automatic vehicles. This application is a great help for drivers taking into consideration that driving requires great care and constant attention on their part. The algorithm of traffic sign detection and recognition system (TSDR) is divided into two parts, including: detection and recognition. Deep Learning methods are the main ones to be considered for implementing TSDR. This paper presents an approach that enables the detection and recognition of traffic signs in real time regardless of driving conditions, including rainy weather, fog or other atmospheric conditions. The proposed system performs with 92% accuracy rate.
Keywords:
TSD, TSR, Recognition, Detection
Proceedings Editor
Edmond Hajrizi
ISBN
978-9951-550-47-5
Location
UBT Kampus, Lipjan
Start Date
30-10-2021 12:00 AM
End Date
30-10-2021 12:00 AM
DOI
10.33107/ubt-ic.2021.386
Recommended Citation
Jajaga, Edmond; Pylla, Rreza; Dinarama, Saura; and Shabani, Valentina, "Traffic Sign Detection and Recognition" (2021). UBT International Conference. 403.
https://knowledgecenter.ubt-uni.net/conference/2021UBTIC/all-events/403
Traffic Sign Detection and Recognition
UBT Kampus, Lipjan
Traffic sign detection and recognition (TSD, TSR) has become part of new technologies in order to support the development of automatic vehicles. This application is a great help for drivers taking into consideration that driving requires great care and constant attention on their part. The algorithm of traffic sign detection and recognition system (TSDR) is divided into two parts, including: detection and recognition. Deep Learning methods are the main ones to be considered for implementing TSDR. This paper presents an approach that enables the detection and recognition of traffic signs in real time regardless of driving conditions, including rainy weather, fog or other atmospheric conditions. The proposed system performs with 92% accuracy rate.