Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

camera ai sheep #1033

Open
1 task done
koplomen69 opened this issue Feb 28, 2025 · 2 comments
Open
1 task done

camera ai sheep #1033

koplomen69 opened this issue Feb 28, 2025 · 2 comments
Labels
enhancement New feature or request

Comments

@koplomen69
Copy link

Search before asking

  • I have searched the HUB issues and found no similar feature requests.

Description

scan domba di segala kondisi

Use case

No response

Additional

No response

@koplomen69 koplomen69 added the enhancement New feature or request label Feb 28, 2025
@UltralyticsAssistant
Copy link
Member

👋 Hello @koplomen69, 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 regarding a camera AI for detecting sheep under all conditions ("scan domba di segala kondisi"), we kindly ask you to provide screenshots and steps to reproduce the issue. A minimum reproducible example (MRE) would help us investigate this better. Additionally, information about your environment (e.g., operating system, camera details) would be very helpful.

If this is a ❓ Question or feature request, please describe your use case more fully, including specific details about your dataset, the AI pipeline you're envisioning, or other relevant information so that we can better guide you.

This is an automated response, but don't worry 😊—an Ultralytics engineer will also assist you soon. We appreciate your patience and look forward to helping resolve your issue!

@pderrenger
Copy link
Member

@koplomen69 thank you for your interest in using AI for sheep detection! 🐑 Ultralytics HUB provides excellent tools for this exact use case. Here's how to implement a robust sheep scanning system:

  1. Dataset Preparation
    Collect diverse sheep images in various conditions (lighting, angles, weather). Our Datasets Guide explains how to create and upload high-quality datasets with proper labeling.

  2. Model Selection
    Start with YOLOv8 or YOLO11, both proven effective for animal detection. Pre-trained models are available in the HUB Model Library. For challenging conditions, consider our Cloud Training options.

  3. Real-Time Deployment
    Export trained models to:

    • TFLite for Android cameras
    • CoreML for iOS devices
    • ONNX for embedded systems

Example inference code for sheep detection:

from ultralytics import YOLO

model = YOLO('yolov8n.pt')  # or your custom sheep model
results = model.predict('sheep_video.mp4', stream=True)

For livestock monitoring examples, see our Animal Behavior Monitoring Guide using similar techniques.

Would you like guidance on any specific aspect of implementation?

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
enhancement New feature or request
Projects
None yet
Development

No branches or pull requests

3 participants