Tipo di tesi
Tesi di laurea magistrale
Titolo
Comparative study of YOLO-based object detection for automated damage assessment in vehicles
Dipartimento
INGEGNERIA DELL'INFORMAZIONE
Corso di studi
ARTIFICIAL INTELLIGENCE AND DATA ENGINEERING
Riassunto (Italiano)
Vehicle damage assessment is an important task in different industries, as it helps determine the repair cost and maintenance requirements; it also assists in preventing fraud during the acquisition and management of second-hand vehicles. In this context automated damage assessment can save time and reduce subjectivity in manual inspection. YOLO(You Only Look Once) is currently one of the state-of-art object detection model in the field of Computer Vision, showing remarkable results in both speed and accuracy. In this study, we specifically compared the performance of two YOLO versions: YoloV5 and YoloV7. These two models were evaluated in terms of accuracy and speed, and results were analyzed to determine the best model for distinct business cases.
