Skip to content

nourfen/YOLOv9-ObjectDetection-Unity

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

17 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

About

This project implements the YOLO (You Only Look Once) detection model made by Ultralytics in Unity 6. It uses the YOLO IX model—with plans to incorporate newer versions—and leverages the Unity Sentis package for ONNX model manipulation. Through GPU acceleration via ComputeShaders, the application enables real-time object detection from images, videos, or camera feeds with a configurable confidence and IoU (Intersection over Unon) thresholds. The recognized objects are limited to those included in the COCO (Common Objects in Context) dataset.

Motivation

My motivation for creating this application stems from a previous job where we considered integrating real-time object detection from a HoloLens 2 camera stream. Unfortunately, short deadlines prevented that feature from becoming a reality. However, my fascination with the concept led me to develop this project on my own.

About

This project implements the YOLO (You Only Look Once) detection model made by Ultralytics in Unity 6.

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published