Emergency vehicles such as ambulances and fire engines get stuck in a heavy traffic may lead to the loss of valuable lives. To overcome this problem, a framework is proposed to detect emergency vehicle in heavy traffic, using Region-Based Convolutional Neural Network (RCNN) to take quick decisions. When an ambulance comes in a particular direction in a traffic signal, the controller detects and checks for the density of traffic and speed of the vehicle in a particular direction and also calculates the time taken by the emergency vehicle to cross the road. Based on the information received, the controller alerts the alternate roads, by displaying a red signal for a particular time in its path. Once the emergency vehicle passes away from the signal, the master control has to be reset for maintaining the normal traffic flow.
Emergency Vehicle Detection in Traffic Surveillance Using Region-Based Convolutional Neural Networks
Lect. Notes Electrical Eng.
International Conference on Automation, Signal Processing, Instrumentation and Control ; 2020 February 27, 2020 - February 28, 2020
Advances in Automation, Signal Processing, Instrumentation, and Control ; Chapter : 49 ; 561-567
2021-03-05
7 pages
Article/Chapter (Book)
Electronic Resource
English
Regional-based convolutional neural networks , Emergency vehicle , Ambulance , Fire engines , Controller Engineering , Circuits and Systems , Robotics and Automation , Signal, Image and Speech Processing , Communications Engineering, Networks , Wireless and Mobile Communication , Mobile and Network Security
Emergency Vehicle Detection in Traffic Surveillance Using Region-Based Convolutional Neural Networks
British Library Conference Proceedings | 2021
|Emergency Vehicle Detection Using Deep Convolutional Neural Network
Springer Verlag | 2022
|