A deep learning model for aerial object detection using YOLOv11.
🛰️ Detect objects from aerial images with our YOLOv11 model! 🚁 Powered by PyTorch 🔥, this tool analyzes aerial footage to identify various objects. 🚀 Upload an image and get instant predictions with confidence scores! ✨
This project provides a Jupyter Notebook that demonstrates how to train a YOLOv11 model for aerial object detection on the VisDrone dataset. The notebook covers the entire process, from setting up the environment to training the model and evaluating its performance.
- Automatic detection of objects in aerial images
- Support for multiple object classes
- User-friendly Jupyter Notebook for easy experimentation
- High-accuracy object detection using YOLOv11
- Python 3.7+
- pip (Python package installer)
- Jupyter Notebook or JupyterLab
-
Clone the repository:
git clone https://github.com/your-username/your-repo-name.git cd your-repo-name -
Install required dependencies:
pip install -r requirements.txt
-
Download the dataset: The notebook uses the VisDrone dataset, which is downloaded from Kaggle.
-
Open the Jupyter Notebook:
jupyter notebook aerial_object_detection.ipynb
-
Run the cells: Execute the cells in the notebook to train the model and see the results.
This project uses the YOLOv11 object detection model. The model architecture consists of:
- A backbone for feature extraction
- A neck for feature fusion
- A head for object detection
The pre-trained model is fine-tuned on the VisDrone dataset for aerial object detection.
The model was trained on the VisDrone dataset, which contains images and annotations for various object categories. https://www.kaggle.com/code/haydenbanz/aerial-object-detection-git?kernelSessionId=252036752
This project is licensed under the Creative Commons Attribution-NonCommercial 4.0 International (CC BY-NC 4.0) License. See the LICENSE file for more details.
Unauthorized commercial use is strictly prohibited.
- Your Name
- Suman Bera (Original notebook author)