In many places across the world, traffic congestion is a serious issue. And this traffic congestion may cause many issues in day- to- day lives like delays that could lead to being late for work, meetings, or school and cause lost revenue or other personal losses. Due to increased idling, acceleration, and braking, fuel is wasted, which raises air pollution and carbon dioxide emissions. Passage of emergency vehicles may get delayed which may put the lives of people at risk where vehicles are urgently needed. Managing this traffic congestion has become one of the great issues for governing bodies of every country. So, the traditional methods of handling traffic are not as effective as it used to be, as the population is increasing day by day especially in countries like India and China. In this paper, a MobileNet-SSD algorithm is used to get the density of traffic on each lane and switch the signal according to the density in real time, instead of doing static or manual signal switching. The proposed work is compared with YOLO V3. The novelty of the work is introducing curfew detection and emergency vehicle monitoring.
Urban Traffic Management using Machine Learning
20.11.2022
589138 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Intelligent Traffic Management using Machine Learning
IEEE | 2025
|Poster: Urban Traffic Monitoring via Machine Learning
IEEE | 2019
|Real Time Traffic Management Using Machine Learning
IEEE | 2020
|