https://github.com/enoxsoftware/yolov5withopencvforunityexample

An example of using OpenCV dnn module with YOLOv5. (ObjectDetection, Segmentation, Classification)
https://github.com/enoxsoftware/yolov5withopencvforunityexample

dnn object-detection opencv unity unity3d-plugin yolo yolov5

Last synced: about 1 year ago
JSON representation

An example of using OpenCV dnn module with YOLOv5. (ObjectDetection, Segmentation, Classification)

• Host: GitHub
• URL: https://github.com/enoxsoftware/yolov5withopencvforunityexample
• Owner: EnoxSoftware
• License: agpl-3.0
• Created: 2023-01-31T13:11:15.000Z (over 3 years ago)
• Default Branch: master
• Last Pushed: 2024-03-09T19:50:14.000Z (over 2 years ago)
• Last Synced: 2024-03-15T04:51:57.517Z (over 2 years ago)
• Topics: dnn, object-detection, opencv, unity, unity3d-plugin, yolo, yolov5
• Language: Jupyter Notebook
• Homepage:
• Size: 258 MB
• Stars: 12
• Watchers: 2
• Forks: 2
• Open Issues: 2
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# YOLOv5 With OpenCVForUnity Example

- An example of using OpenCV dnn module with YOLOv5. [https://github.com/ultralytics/yolov5](https://github.com/ultralytics/yolov5)

- This example can also work for [YOLOv6](https://github.com/meituan/YOLOv6), [YOLOv7](https://github.com/WongKinYiu/yolov7) models, which has the same input/output shapes as the YOLOv5 model.

![YOLOv5_output_shapes.png](YOLOv5_output_shapes.png) 

## Environment

- Windows / Mac / Linux / WebGL / Android / iOS

- Unity >= 2021.3.35f1+

- Scripting backend MONO / IL2CPP

- [OpenCV for Unity](https://assetstore.unity.com/packages/tools/integration/opencv-for-unity-21088?aid=1011l4ehR) 2.6.5+

## Setup

1. Download the latest release unitypackage. [YOLOv5WithOpenCVForUnityExample.unitypackage](https://github.com/EnoxSoftware/YOLOv5WithOpenCVForUnityExample/releases)

1. Create a new project. (YOLOv5WithOpenCVForUnityExample)

1. Import OpenCVForUnity.

1. Import the YOLOv5WithOpenCVForUnityExample.unitypackage.

1. Add the "Assets/YOLOv5WithOpenCVForUnityExample/*.unity" files to the "Scenes In Build" list in the "Build Settings" window.

1. Build and Deploy.

## Export YOLOv5 model to ONNX

1. [YOLOv5_export_to_OpenCVDNN_ONNX.ipynb](https://github.com/EnoxSoftware/YOLOv5WithOpenCVForUnityExample/tree/master/models/YOLOv5/YOLOv5_export_to_OpenCVDNN_ONNX.ipynb)

1. [YOLOv5_segment_export_to_OpenCVDNN_ONNX.ipynb](https://github.com/EnoxSoftware/YOLOv5WithOpenCVForUnityExample/tree/master/models/YOLOv5_segment/YOLOv5_segment_export_to_OpenCVDNN_ONNX.ipynb)

1. [YOLOv5_classify_export_to_OpenCVDNN_ONNX.ipynb](https://github.com/EnoxSoftware/YOLOv5WithOpenCVForUnityExample/tree/master/models/YOLOv5_classify/YOLOv5_classify_export_to_OpenCVDNN_ONNX.ipynb)

## Works with Multi-Object Tracking (MOT)

1. [MultiObjectTrackingExample](https://github.com/EnoxSoftware/OpenCVForUnity/tree/master/Assets/OpenCVForUnity/Examples/Advanced/MultiObjectTrackingExample)

## ScreenShot

![screenshot01.jpg](screenshot01.jpg) 

![screenshot02.jpg](screenshot02.jpg) 

![screenshot03.jpg](screenshot03.jpg) 

## Tutorials

1. [How to Train YOLO v5 on a Custom Dataset](https://www.youtube.com/watch?v=MdF6x6ZmLAY)

2. [Example of custom training for dice roll detection](https://qiita.com/DiNOV-Tokyo/items/1333ff4a6d9b4b5b79c0)