RESUMOThe constant increase in the number of vehicles around the world hasdrawn attention to the need to implement effective traffic monitoringand control technologies. In this work, a methodology is presentedthat uses two algorithms, one that applies the YOLOv8 detector andthe other that applies Deep SORT tracking, to detect, track and countvehicles. Validation results during training of the vehicle detectionmodel revealed an overall accuracy of 89, 2% and mAP50 of 93, 7%on the AIC HCMC 2020 database. Additionally, when applying themodel to a test video, an overall accuracy of 81, 2% and mAP50 of87, 5% was achieved. These results highlight the effectiveness of thedetection algorithm for use in applications involving vehicle trackingand counting, with significant potential for traffic management.