This thesis aims to study the use of deep learning, specifically the YOLOv5 (You Only Look Once version 5) model for object detection, in conjunction with seven OpenCV (Open Source Computer Vision Library) object tracking algorithms, and to compare their effectiveness using MOTP and MOTA performance evaluation metrics. A vehicle tracking program was developed as the testing ground for the evaluation of the different tracking algorithms. The thesis includes a step-by-step guide on how to create the development environment and explains the most important parts of the program. The results obtained from the execution of the program are then shown and discussed to determine how well the algorithms performed and which ones were the most effective in this scenario.