YOLOv8 With OpenCVForUnity Example

• An example of using OpenCV dnn module with YOLOv8. https://docs.ultralytics.com/models/yolov8/
• This example can also work for YOLOv5u, YOLOv9, YOLOv10, YOLOv11, YOLOv12 models, which has the same input/output shapes as the YOLOv8 model.

Environment

• Windows / Mac / Linux / WebGL / Android / iOS
• Unity >= 2021.3.35f1+
• Scripting backend MONO / IL2CPP
• OpenCV for Unity 3.0.0+

Setup

1. Download the latest release unitypackage. YOLOv8WithOpenCVForUnityExample.unitypackage
2. Create a new project. (YOLOv8WithOpenCVForUnityExample)
3. Import OpenCVForUnity.
4. Import the YOLOv8WithOpenCVForUnityExample.unitypackage.
5. Add the "Assets/YOLOv8WithOpenCVForUnityExample/*.unity" files to the "Scenes In Build" list in the "Build Settings" window.
6. Build and Deploy.

Training from custom data and export to ONNX

1. YOLOv8_export_to_OpenCVDNN_ONNX
2. YOLOv5u_export_to_OpenCVDNN_ONNX
3. YOLOv9_export_to_OpenCVDNN_ONNX
4. YOLOv10_export_to_OpenCVDNN_ONNX
5. YOLOv11_export_to_OpenCVDNN_ONNX
6. YOLOv12_export_to_OpenCVDNN_ONNX

Tutorials

1. How to Train Ultralytics YOLOv8 models on Your Custom Dataset in Google Colab

Works with Multi-Object Tracking (MOT)

1. MultiObjectTrackingExample

ScreenShot