The accuracy of using Yolov5 for dust detection in ports is not high, and there will be a large number of false detections, especially at night

[hdjhasd]

Search before asking

• [x] I have searched the YOLOv5 issues and discussions and found no similar questions.

Question

The accuracy of using Yolov5 for dust detection in ports is not high, and there will be a large number of false detections, especially at night

Additional

No response

[UltralyticsAssistant]

👋 Hello @hdjhasd, thank you for your interest in YOLOv5 🚀! Please visit our ⭐️ Tutorials to get started, where you can find quickstart guides for common tasks like Custom Data Training all the way to advanced optimization techniques like Hyperparameter Evolution.

If this is a 🐛 Bug Report, please provide a minimum reproducible example (MRE) to help us investigate this further. This should include details such as custom dataset samples, relevant training or inference code snippets, and complete logs for better debugging.

If this is a ❓ Question related to your dust detection task, please make sure to share:

• Information about your custom dataset (e.g., size, quality, class balance)
• Examples of false detections, particularly at night, to better understand the issue
• Details of the model configuration or modifications you may have made
• Your training logs and hyperparameters used (learning rate, batch size, etc.)
• Steps you've already taken using our Tips for Best Training Results

Requirements

Python>=3.8.0 with all requirements.txt installed, including PyTorch>=1.8. To set up an environment:

git clone https://github.com/ultralytics/yolov5  # clone
cd yolov5
pip install -r requirements.txt  # install

Environments

YOLOv5 can be run in the following verified environments, all preconfigured with essential dependencies like CUDA, Python, and PyTorch:

• Notebooks with free GPUs:
• Google Cloud Deep Learning VM. See GCP Quickstart Guide
• Amazon Deep Learning AMI. See AWS Quickstart Guide
• Docker Image. See Docker Quickstart Guide

Status

If this badge is green, all YOLOv5 GitHub Actions Continuous Integration (CI) tests are passing. These tests confirm YOLOv5's functionality for training, validation, inference, export, and benchmarks across various environments.

This is an automated response to assist you faster 😊. An Ultralytics engineer will take a look at your issue and provide additional support soon.

[pderrenger]

@hdjhasd thank you for your question. For improving accuracy and reducing false detections, especially in challenging scenarios like night-time dust detection, ensure your training dataset includes diverse and representative images of the deployment environment (e.g., day and night conditions). Verify that annotations are accurate and consistent, and consider adding background images to reduce false positives. You can also experiment with hyperparameter tuning or use Test-Time Augmentation (TTA) for better results. For more guidance, refer to the Tips for Best Training Results documentation. Let us know if you need further clarification!

[github-actions[bot]]

👋 Hello there! We wanted to give you a friendly reminder that this issue has not had any recent activity and may be closed soon, but don't worry - you can always reopen it if needed. If you still have any questions or concerns, please feel free to let us know how we can help.

For additional resources and information, please see the links below:

• Docs: https://docs.ultralytics.com
• HUB: https://hub.ultralytics.com
• Community: https://community.ultralytics.com

Feel free to inform us of any other issues you discover or feature requests that come to mind in the future. Pull Requests (PRs) are also always welcomed!

Thank you for your contributions to YOLO 🚀 and Vision AI ⭐