With the economic growth, people began buying more vehicles. However, the number of parking spaces didn’t keep up with this increase. The search for vacant spots in parking lots has become increasingly time-consuming, resulting in longer parking searches and a rise in carbon dioxide emission into the atmosphere. Nowadays, with the help of computer vision, it has become viable to train models that can detect empty park spaces and facilitate the search for available gaps.The goal of this project is to implement an algorithm that can detect vacant and occupied parking spaces in a parking lot using computer vision.This algorithm was trained using the You Only Look Once (YOLO) v8 model, which is currently widely used in real-time object detection and has proven to be efficient. It was tested using OpenCV, a library that processes images and enables the visualization of results by drawing bounding boxes that identify the objects from the referenced classes.The project was developed using Python language, using Docker to ensure portability across environments, and was implemented on a Jetson Orin. The proposed model demonstrated robust performance in detecting most parking spaces under standard imaging conditions.