Due to the increasing number of cars on the road and the exponential growth of traffic throughout the globe, regulating traffic has become crucial in the most industrialized countries. The development of technology has led to the current state of traffic management systems that comes with the ability to count, monitor, and predict the speed of vehicles in order to improve the transportation planning. This has also reduced the number of accidents that occur due to worsen traffic conditions. Road traffic surveys have been carried out manually for a long time since automated measures were not often employed due to the difficulty of installation. Machine learning in image processing is widely recognized as a significant approach for real-world applications such as traffic monitoring. The primary benefit of automated vehicle counting is that it allows for the management and evaluation of traffic in the urban transportation system. There are many methods employing distributed acoustic systems on intelligent transportation systems, including YOLO v4 and the Normalized Cross-correlation algorithm, which uses ultrasonic sensors and the algorithms ALPR, YOLO, GDPR, and CNN. The simplest method for identifying a vehicle is to gather information from sensors such as cameras, vibration detectors, ultrasound detectors, or acoustic detectors. These sensors are combined with the proper microcontrollers to determine the amount of traffic using the most recent data and theory. This review article is a quick reference for researchers working on safety-related traffic management systems.

Traffic Management System Signal Processing Safety Communication Data Processing Neural networks