🌊 Underwater Trash Plastic Detection 🛢️

Table of Contents

1. About The Project
   • Built With
2. Getting Started
   • Prerequisites
   • Installation
3. Usage
4. Output
5. License
6. Acknowledgments

🌟 About The Project

We have developed an underwater trash plastic detection project using YOLOv5 and YOLOv8 by training custom datasets. This project includes two models: one based on YOLOv5 for object detection and another using YOLOv8 for instance segmentation.

Built With

• YOLOv5
• YOLOv8

🚀 Getting Started

We utilized Google Colab with GPU support to run our YOLOv5 model.

Prerequisites

• Python

Installation for YOLOv5 object detection

1. Clone the repository

   !git clone https://github.com/ultralytics/yolov5.git

2. Install required dependencies

   !pip install -r requirements.txt

3. Run the YOLOv5 object detection model

   !python detect.py --weights bestpla.pt --source path/to/folder/orImage

Installation for YOLOv8 instance segmentation

1. Install ultralytics

   !pip install ultralytics

2. Install required dependencies

   !pip install -r requirements.txt

3. Run the YOLOv5 object detection model

   !yolo predict model='runs/segment/yolov8n-seg/weights/best.pt' source='detection source file' name='folder_name'

🎯 Usage

This project serves to detect underwater garbage, including items like plastic bags. It can contribute to ocean cleanup efforts and environmental monitoring. To run the project, consider Google Colab.

📊 Output

The images above depict the output of our underwater trash plastic detection models. The model successfully identifies and outlines plastic waste items, such as plastic bags, cups, metal_can and cups, contributing to efforts to clean up our oceans.

📜 License

Distributed under the MIT License. See LICENSE for more information.

🙏 Acknowledgments

Thanks to Ultralytics for their awesome framework!