Overview
Learn how to create a horse race detection model using deep learning without an existing dataset. Extract frames from a horse race video, automate annotations using GroundingDINO and Autodistill, train a YOLOv8 model, and apply it to detect objects in new videos. Follow along as the tutorial covers frame extraction, image visualization, annotation automation, model training, and real-time object detection on video footage. Gain hands-on experience with computer vision tools like OpenCV, Supervision, and YOLOv8 while building a complete object detection pipeline from scratch.
Syllabus
Introduction & Demo
Installation
Generate the dataset
Automatic dataset annotation
Train a model
Test the mode
Taught by
Eran Feit