LaboroTomato for Unity Sentis (Version 1.4.0-pre.3*)

LaboroTomato is is an image dataset of growing tomatoes at different stages of their ripening.

This model was trained on the LaboroTomato image dataset using the Ultralytics YOLOv8n object detection framework. The sentis example implementation was copied from sentis-YOLOv8n.

How to Use

First get the package com.unity.sentis from the package manager. You will also need the Unity UI package.

Create a new scene in Unity 6.
Install com.unity.sentis version 1.4.0-pre.3 from the package manager, and enable the 'Video' built-in module.
Add the c# script to the Main Camera.
Create a Raw Image in the scene and link it as the displayImage
Drag the laboro_tomato_yolov8.sentis file into the model asset field
Drag the classes.txt on to the labelAssets field
Put a video file in the Assets/StreamingAssets folder and set the name of videoName to the filename in the script ("tomatoes.mp4")
Set the fields for the bounding box texture sprite (you can create your own one using a transparent texture or use an inbuilt one) and the font

Preview

If working correctly you should see something like this:

Information

The onnx model was designed with the same inputs as sentis-YOLOv8n. If you are using that implementation, you can simply swap out the model and labels with the ones in this project and it should work.

References

For information on how the model was trained and exported to onnx, see the project github page.

Unity Sentis

Unity Sentis is the inference engine that runs in Unity 3D. More information can be found at here

License

Ultralytics YOLOv8 uses the GPLv3 license. Details here.

The LaboroTomato dataset uses the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License. Details here.