Abstract

An application that uses the power of deep learning and computer vision to detect and annotate vehicles within images.

You can access the app at: https://find-the-vehicles.vercel.app.

You can also view the GitHub repository for this project at: https://github.com/gustavo-ribeiro-santiago/find-the-vehicles-app.

Methodology

The application uses YOLOv5, trained through transfer learning, for object detection and annotation.

The backend is built with FastAPI and served on an AWS EC2 instance.

The frontend is built with Next.js and deployed on Vercel.

Results

The fine-tuned YOLOv5 model achieved 85% accuracy for cars detection.

Here’s the link to my GitHub profile: https://github.com/gustavo-ribeiro-santiago.

Feel free to reach out if you have any questions or feedback!