Learn to build an application for tracking and counting objects using Computer Vision in this comprehensive tutorial. Explore the implementation of YOLOv8 for detection, ByteTrack for tracking, and Roboflow's Supervision library for object counting. Set up a Python environment for vehicle tracking, create custom inference pipelines for images and videos, and train a YOLOv8 Object Detection model on a custom dataset. Apply these techniques to real-world scenarios, such as detecting, tracking, and counting candies on a conveyor belt. Gain hands-on experience with cutting-edge computer vision tools and techniques to enhance your object tracking and counting skills.
Track & Count Objects Using YOLOv8, ByteTrack & Supervision
Overview
Syllabus
Introduction
Setting up the Python environment for vehicle tracking
Using YOLOv8 for vehicle detection
Building custom inference pipeline with Supervision for a single image
Building custom inference pipeline with Supervision for a whole video
Tracking detections with ByteTrack
Counting objects crossing the line with Supervision
Training YOLOv8 Object Detection model on custom dataset
Detect, track, and count candies on the conveyor
Conclusion
Taught by
Roboflow
Related Courses
-
Traffic Analysis with YOLOv8 and ByteTrack - Vehicle Detection and Tracking
-
Computer Vision: YOLO Custom Object Detection with Colab GPU
-
Object Tracking and Motion Detection with Computer Vision
-
Computer Vision and Perception for Self-Driving Cars (Deep Learning Course)
-
Modern Computer Vision GPT, PyTorch, Keras, OpenCV4 in 2024!
-
YOLOv11 for Real-Time Class-Wise Vehicle Counting and Tracking
