This repository contains the code and resources for a computer vision project that focuses on detecting military aircraft using YOLOv5. The project utilizes a custom dataset of military planes, which can be found at Kaggle: Military Aircraft Detection Dataset.
The goal of this project is to develop a proof-of-concept object detection model capable of identifying military aircraft in images. YOLOv5, a state-of-the-art object detection algorithm, has been employed to train the model on the provided dataset. The specific aircraft models included in the training and detection process are:
- F15
- F16
- F18
- F35
- C130
Due to resource limitations, only these aircraft models have been considered. The project utilizes the Google Colab platform for both training and detection.
This project is based on the work of a Kaggle notebook created by changchi0914. I express my gratitude to the author for providing a valuable template that served as the foundation for our project.
The dataset used for training and evaluation can be found at the following location: Kaggle: Military Aircraft Detection Dataset. It consists of a diverse collection of images containing various military aircraft models, including the ones listed above.
Plain Yolov5 detection of an F16:
Detection using the custom trained dataset:
|
|
|
|
|
|
This project is licensed under the MIT License. Please refer to the LICENSE file for more information.