Paper Title
Vehicle Counting and Monitoring of The Intelligent Transportation System in Nukus City

Abstract
The growing number of vehicles on the road necessitates accurate and efficient detection methods to obtain valuable data for detecting traffic congestion, contributing to effective traffic management. The major goal of this research was to create a real-time system for counting automobiles that is both accurate and dependable in order to reduce congestion in traffic in a given location. This research proposes a system that can properly count automobiles inside a given area by recognizing and tracking them as they move around the area. To improve the system's precision, we employed the highperformance and computationally efficient YOLO version 5 system for vehicle recognition, while vehicle tracking and counting were achieved through the DeepSort approach, along with the proposed simulated loop technique. Following the implementation of the proposed system, the testing of YOLOv5 yielded a detection precision rate with a mean average precision (mAP) of 98.0%. The integration of YOLOv5 with the Deep Sort and simulated loop algorithms enabled the system to successfully detect, track, and count various types of vehicles. Keywords - Intelligent transportation system, Object detection, CNN, YOLOv5.