Tesi etd-02022023-134057 |
Link copiato negli appunti
Tipo di tesi
Tesi di laurea magistrale
Autore
PETRELLI, GIANMARCO
Indirizzo email
g.petrelli@studenti.unipi.it, giammipetrelli96@gmail.com
URN
etd-02022023-134057
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
Relatori
relatore Prof. Cimino, Mario Giovanni Cosimo Antonio
relatore Prof. Vaglini, Gigliola
tutor Ing. Xhani, Orges
relatore Prof. Vaglini, Gigliola
tutor Ing. Xhani, Orges
Parole chiave
- Vehicle damage assessment
- Damage Detection
- YOLO
- Deep Learning
- Artificial Intelligence
Data inizio appello
17/02/2023
Consultabilità
Non consultabile
Data di rilascio
17/02/2093
Riassunto
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.
File
| Nome file | Dimensione |
|---|---|
La tesi non è consultabile. |
|