Today, one of the most pressing challenges in every region of the world is transportation. Every nation approaches its transportation issues differently by its demands and within its capacity. Volume is crucial for transportation system planning, design, and operation. The procedure involves identifying the predominant volume of traffic on roadways at a certain place during a specified time period. It is quantified by the quantity of cars per minute, hour, and day. Translating the flow of different vehicle classes into a single unit called the passenger car unit is crucial for representing traffic flow on a route over a certain time period. The volume of traffic is dynamic and changes throughout the day. The amount of daily traffic fluctuates on different days of the week, different months, and seasons of the year. Intelligent transport system (ITS) traffic management is a vital component. Intelligent Transportation Systems (ITS) is a system that incorporates sophisticated communications, information, and electronic technologies into transportation infrastructure and vehicles. ITS is designed to reduce traffic congestion, enhance safety, and decrease transit times and fuel use. The advancement of Intelligent Transportation Systems (ITS) has led to a rising need for real-time traffic data. In the past, manual estimates were the most prevalent method. Several observers employ technology, such as mechanical and electronic counting boards, to count the number of passing cars, their sorts, and even the number of people. Currently, there are various standard surveillance technologies to capture real-time traffic data, such as image processing and inductive loop detection. Using these approaches, traffic statistics, vehicle speeds, and classifications may be collected. However, they have certain drawbacks, such as their restricted scope and high cost of installation and maintenance. The study, therefore, presented diminutive research on using an algorithm for detecting vehicles and analyzing traffic volume using real-time video graphic techniques to combat some of these challenges. This research was conducted using the image detection model YOLO. The algorithm counts traffic volume and was compared with the manual count traffic volume to check the reliability of the proposed model. In this research, we outlined a five-tasked methodology viz, recording of traffic video (data collection), developing an algorithm for detection and counting of vehicles, testing of the algorithm with recorded video, exporting data for analysis, and comparing algorithm count with manual count traffic volume to check the trustworthiness of the model. The research relived a high accuracy level of detected vehicles as well as, yield minimal percentage errors when subjected to mean absolute percentage error computations. Also, the results of the research fell into the accepted zone of the GEH (Goffrey E. Havers) statistics.