Intelligent road traffic monitoring necessitates the development of efficient systems capable of handling the substantial data volumes continuously generated by traffic surveillance cameras. Automated solutions are essential since manual data analysis is both labour-intensive and impractical. The goal of our deep learning-based method is to build a traffic detection system that is both quick and accurate, with no human involvement required. The study focuses on two critical aspects of intelligent traffic monitoring: accident detection and traffic flow analysis. The goal of this project is to improve future intelligent transportation systems by using TrafficNet technology. The TrafficNet system performs multiple activities, including data splitting, data analysis, deep learning convolutional neural network (DLCNN) model training, traffic forecasting, and performance evaluation. Following that, DLCNN model for diverse traffic scenarios was developed. The TrafficNet system eventually anticipates numerous categories, such as heavy traffic, light traffic, accidents, and fires. The proposed TrafficNet demonstrates its accuracy and versatility by effectively identifying regions in a wide range of applications.
Enhanced Deep Learning Model for Road Transportation Safety with Accident Detection and Traffic Flow Analysis
AI Front. & Ethics
Recent Trends in Artificial Intelligence Towards a Smart World ; Chapter : 11 ; 295-320
2024-09-10
26 pages
Article/Chapter (Book)
Electronic Resource
English
Road traffic accident risk prediction deep learning algorithm
European Patent Office | 2022
|Deep learning based condition monitoring of road traffic for enhanced transportation routing
Springer Verlag | 2024
|