A New Vehicle Tracking System with R-CNN and Random Forest Classifier for Disaster Management Platform to Improve Performance

Smart devices connected to the Internet of Things (IoT) play a big role in the growth of smart cities, which are becoming more technologically advanced over time. Find out how many monitoring systems that are based on artificial intelligence could save people's lives in different situations. Disaster management needs to be better organized in order to save more lives and keep an accurate count of property damage. People who are in trouble can get help quickly, like fire extinguishers, ambulances, and other emergency vehicles. Today, you can also use visual equipment to look at a situation and find actions that can be done again. In the past, this was not the case. With the systems that are out there now, it is possible to find out where an ambulance is. GPS and surveillance cameras can be used to find the location with great accuracy. In the proposed work, a new intervention method is used to pull out features that can be used to find objects and track vehicles. This process uses image object detection and a field of view that takes in the whole NH road (AoV). Region-based convolutional neural network, or R-CNN, is an algorithm that can be useful when doing research. In an emergency, it gives you the right mix of different visual clues to help you find your way. When looking at traffic during times of heavy congestion, the position of the camera and how drivers and passengers interact on the road are both taken into account. Cars can be targeted based on the area where they run and the time differences that come with that. Both the Random Forest algorithm and the Adam optimizer are based on neural networks. They are analysed to see how well classifiers do their jobs. These changes were made to make the system work better as a whole while keeping the same level of effectiveness, even though the monitoring services rotate through 360 degrees.