# Airplanes_Detection_Satellite_Images

**Repository Path**: hf-datasets/Airplanes_Detection_Satellite_Images

## Basic Information

- **Project Name**: Airplanes_Detection_Satellite_Images
- **Description**: Mirror of https://huggingface.co/datasets/mrcsgh/Airplanes_Detection_Satellite_Images
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-08-30
- **Last Updated**: 2025-08-30

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

---
license: cc-by-4.0
---

## Dataset Summary
More than 250 satellite images taken from Google Maps for airplanes detection.
  

## Uses
The data was collected for educational purposes. I learned how to label images with labelImg, and it can also be used to test pre-trained models like YOLO.

## Dataset Structure
The dataset contains 272 labeled images divided into training and validation sets. It also includes the configuration file `dataset.yaml`.

## Dataset Creation

### 1. Image Capture
Images were taken from Google Maps in different places around the world to create a dataset as diverse as possible. This includes:
> +100 images with airplanes (civilian and military)

> +100 images without airplanes

### 2. Preprocessing
Images were resized (960x960) and renamed using a python script

### 3. Labeling
Images containing airplanes were manually labeled using [labelImg](https://github.com/HumanSignal/labelImg). And I obtained empty `.txt`files using a python script.

### 4. Labels and images are organized
I split the images and lables `.txt` in training and validation sets 
> 222 labeled images for training (82% aprox)
> 50 labeled images for validation (18% aprox)

### 5. `dataset.yaml` file
The dataset´s configuration file is written. It includes the path to the different folders and the names that receive the classes. In this case, only one class **0: airplane**

## Source Data
Google Maps