Real-time vehicle classification is one of the most important services of traffic management, road safety, and security in the age of intelligent transportation systems and smart and developed cities. In this research, the study proposes an experimental and accurate real-time vehicle classification technique based on deep learning. Our proposed method reliably and accurately recognizes vehicles from photos, videos, and live video streams collected by security cameras that broadcast in real-time. In recent years, there has been an increase in autonomous vehicles and technologies such as ADAS (Adaptive Cruise Control), which typically assists the driver in reducing road accidents and makes it more straightforward to drive the vehicles on complicated roadways. Real-time vehicle classifier is also beneficial to road safety and traffic management. It aids with the detection of emergency vehicles, making it easier for law enforcement to clear traffic according to emergency vehicles roots. To maintain optimal efficiency, we handle obstacles, changing light conditions, and small and distant vehicles. The outcomes of our studies indicate that the suggested strategy is a useful complement to intelligent transportation and surveillance systems.
Real-Time Vehicle Classification Using Deep Neural Networks Based Model
2024-06-29
734337 byte
Conference paper
Electronic Resource
English
Towards Real-Time Image Reconstruction Using Deep Neural Networks
British Library Conference Proceedings | 2020
|Towards Real-Time Drone Detection Using Deep Neural Networks
Springer Verlag | 2021
|