Vehicle detection and tracking of moving vehicles for the surveillance videos.

In recent years, multi-element detection and tracking is an essential application of computer vision, including civilian or military surveillance systems. However, the precision and system's capacity to track cars is the key challenges these systems experience in their work. the speed of system interaction, and the reduction of noise associated with the video sequences captured by the system. Therefore, vehicle detection is an important stage in vehicle tracking. The approach to finding moving cars in a video is known as tracking. Vehicle tracking has many applications, including robot vision, traffic control, video surveillance, and simulation. Over the years, many scientists have sought to design useful and efficient algorithms. In this paper, a Kalman filter (KF) was developed to identify and track moving vehicles. The topic of vehicle monitoring and tracking with a fixed camera is addressed in this work. This includes a three-stage work in the first stage, the acquired video is converted to frames and the video is converted from RGB to gray in the first step of preprocessing, then the salt and pepper noise is eliminated using an average filter technology. Background subtraction is performed in the next phase of moving vehicle detection and extraction due to its ability to handle complex backgrounds and appearance changes due to lighting and size, and vehicle detection. The exposed front part is cleaned by applying the shaping process. The detected object is marked as a vehicle with a bounding box. The vehicles are then tracked using a Kalman filter in the next stage. This paper aims to identify and track vehicles in video frames sequence. An average filter was used to remove 70-80 percent of the noise during the noise reduction step. Since the noise, presumably salt and pepper, is less complex than that of the Wiener filter, an intermediate filter was used in place of the Wiener filter. KF was used as a discretionary filter during the tracing step. We conclude that the accuracy of the composite detection achieved using the Kalman filter approach is about 94 percent. It is a great technology for tracking the movement of moving vehicles and has a lot of potential in a traffic control system. The complete system was developed and tested using MATLAB. [ABSTRACT FROM AUTHOR]