Data

Tools

Indexes

Applications

Experiments

Open Source Science

aircraft_classification

MSc Thesis: Impact of Metadata on Aircraft Classification in Satellite Imagery

https://github.com/tb-tan/aircraft_classification

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (4.9%) to scientific vocabulary
Last synced: 6 months ago · JSON representation ·

Repository

MSc Thesis: Impact of Metadata on Aircraft Classification in Satellite Imagery

Basic Info
  • Host: GitHub
  • Owner: tb-tan
  • Language: Jupyter Notebook
  • Default Branch: main
  • Homepage:
  • Size: 11.1 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 0
  • Releases: 0
Created 10 months ago · Last pushed 9 months ago
Metadata Files
Readme Citation

README.md

Aircraft_Classification

This repository contains the source code and documentation for the thesis project "Impact of Metadata on Civil and Military Aircraft Classification in Satellite Imagery: A Multi-Modal Framework with YOLO and XGBoost", submitted to Tilburg University.

This thesis explores improving aircraft classification in satellite imagery by combining deep learning with structured metadata. A two-phase pipeline integrates YOLO-based object detection and feature extraction with an XGBoost classifier. Using the RarePlanes dataset, the study compares YOLO11 and YOLO12 models across scenarios with and without geometric metadata. Results show that fusing visual features with metadata boosts classification accuracy, especially for underrepresented military aircraft. The research demonstrates the value of multi-modal approaches for more interpretable and effective satellite-based aircraft recognition.

Owner

  • Name: Tuba
  • Login: tb-tan
  • Kind: user

Studying for a MSc in Data Science

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this, please cite it as below."
authors:
- family-names: "Tandogan"
  given-names: "Tugba"
title: "Aircraft_Classification"
version: 1.0.0
date-released: 2025-05-19
url: "https://github.com/tb-tan/Aircraft_Classification"

GitHub Events

Total
  • Push event: 4
  • Create event: 2
Last Year
  • Push event: 4
  • Create event: 2