A Centroid-Based Object Tracking Implementation

Centroid based Object Tracking with YOLOv4

An Introduction to Object Tracking

Object Tracking is a technique to identify objects of interest in a video, track the identified objects by assigning a unique Id as they move between frames

Typically, Object Tracking is composed of

• Object Detection and Recognition: A technique to identify and localize the objects of interest by drawing bounding boxes around them in each frame.
• Object Tracking: Generating a unique ID for each detected object, tracking the objects as they move around in a video while maintaining the ID assignment.

Object Tracking implementation for this implementation will use Yolo V4 for object detection, and tracking will be done using Centroid-based Object Tracking on an existing video.

The implementation in this article will perform object detection on persons and assign a unique ID to each person as they move between the frames.

Object Detection using Yolo V4

Download the following files from here for the Yolo v4 object detection.