Detection of Traffic Light Violations from Fish Eye Driver Cameras of Public Transport Buses
Küçük Resim Yok
Tarih
2023
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Ieee
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Nowadays, automatic detection of traffic rule violations become an important part of smart transportation networks. Among these, automatic detection of traffic light violations is one of the most needed due to their serious effects on life and property safety. In this study, we propose a method based on computer vision and deep learning techniques for the automatic detection of traffic light violations of public transport buses. Our method is designed to work with images taken from fish eye driver cameras, which are currently used for security purposes in buses, in order not to create the need for additional equipment. With our experiments, it has been shown that the object detection models in the literature and in addition, a simple method using optical flow are insufficient for this problem, whereas our proposed method produces successful results.
Açıklama
31st IEEE Conference on Signal Processing and Communications Applications (SIU) -- JUL 05-08, 2023 -- Istanbul Tech Univ, Ayazaga Campus, Istanbul, TURKEY
Anahtar Kelimeler
Automatic detection of traffic violations, smart cities
Kaynak
2023 31st Signal Processing and Communications Applications Conference, Siu
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
