Creating and training a specific model for counting hazelnuts from video

[JohBB]

Search before asking

• [X] I have searched the HUB issues and discussions and found no similar questions.

Question

Estimated, Good morning

I´m looking for some help to develop a system which based on live video counts objects (hazelnuts) to calculate in real time the capacity of the process (amount of kg/hour that passes through our machine.

I have a couple of customers who could use a service like this and I found the existing options (Count things for example) are rather expensive so I´m looking to develop a new system.

I found information on this software online and I was hoping if anyone could help me to develop a system like this?

Kind Regards Johannes Biesbrouck

Additional

No response

[github-actions[bot]]

👋 Hello @JohBB, thank you for raising an issue about Ultralytics HUB 🚀! Please visit our HUB Docs to learn more:

• Quickstart. Start training and deploying YOLO models with HUB in seconds.
• Datasets: Preparing and Uploading. Learn how to prepare and upload your datasets to HUB in YOLO format.
• Projects: Creating and Managing. Group your models into projects for improved organization.
• Models: Training and Exporting. Train YOLOv5 and YOLOv8 models on your custom datasets and export them to various formats for deployment.
• Integrations. Explore different integration options for your trained models, such as TensorFlow, ONNX, OpenVINO, CoreML, and PaddlePaddle.
• Ultralytics HUB App. Learn about the Ultralytics App for iOS and Android, which allows you to run models directly on your mobile device.
  • iOS. Learn about YOLO CoreML models accelerated on Apple's Neural Engine on iPhones and iPads.
  • Android. Explore TFLite acceleration on mobile devices.
• Inference API. Understand how to use the Inference API for running your trained models in the cloud to generate predictions.

If this is a 🐛 Bug Report, please provide screenshots and steps to reproduce your problem to help us get started working on a fix.

If this is a ❓ Question, please provide as much information as possible, including dataset, model, environment details etc. so that we might provide the most helpful response.

We try to respond to all issues as promptly as possible. Thank you for your patience!

[pderrenger]

@JohBB hello Johannes,

Good morning! 🌞 We're glad you're interested in developing a hazelnut counting system using live video processing. While I can't provide a code example directly here, I'm happy to guide you through the steps you'll need to take to get started with your project.

1. Data Collection: First, you'll need a dataset of hazelnut images. This dataset should be as varied as possible, including different lighting conditions, hazelnut sizes, and angles.

2. Annotation: Once you have your dataset, the next step is to annotate your images. This involves marking the hazelnuts in each image, which helps the model learn to identify them.

3. Model Selection: For real-time object counting, the YOLO (You Only Look Once) models provided by Ultralytics are highly efficient. You can start with a pre-trained model and fine-tune it for your specific needs.

4. Training: With your annotated dataset, you can now train your model. This will involve adjusting parameters and possibly reiterating on your dataset and annotations for optimal performance.

5. Deployment: After training, the model can be deployed to work with live video feeds. You'll process each frame of the video through the model to detect and count the hazelnuts in real-time.

6. Integration: For calculating the capacity (kg/hour), you'll need to integrate your counting system with a scale or have an average weight per hazelnut. This will allow you to convert the count into weight.

Please check our documentation at https://docs.ultralytics.com/hub for more detailed guidance on each step of the process.

If you have specific questions or hit a snag along the way, feel free to reach out. The YOLO community and the Ultralytics team are always here to help. Good luck with your project!