Skip to content

A Faster R-CNN based model for detection and tracking of F1 racing cars through transfer learning and histograms distance

License

Notifications You must be signed in to change notification settings

andrea-gasparini/f1-racing-cars-tracking

Repository files navigation

F1 racing cars tracking through transfer learning

Transfer learning

In this project we make use of transfer learning (Pan and Yang, 2009), by fine-tuning a pre-trained faster R-CNN model with a ResNet-50-FPN backbone (Ren et al., 2015), to develop a pipeline for detection and tracking of F1 racing cars, enhanced with histograms distance.

For further information, you can read the presentation slides.

This project has been developed during the A.Y. 2021-2022 for the Computer Vision course @ Sapienza University of Rome.

Dependencies

Install all the python dependencies:

pip install -r requirements.txt

Authors