Conference paper Embargoed Access

Training Deep Learning Models via Synthetic Data: Application in Unmanned Aerial Vehicles

Kamilaris Andreas; van den Brink Corjan; Karatsiolis Savvas


JSON-LD (schema.org) Export

{
  "description": "<p>This paper describes preliminary work in the recent promising approach of generating synthetic training data for facilitating the<br>\nlearning procedure of deep learning (DL) models, with a focus on aerial photos produced by unmanned aerial vehicles (UAV). The general concept and methodology are described, and preliminary results are presented, based on a classication problem of re identication in forests as well as a counting problem of estimating number of houses in urban areas. The proposed technique constitutes a new possibility for the DL community, especially related to UAV-based imagery analysis, with much potential, promising results, and unexplored ground for further research.</p>", 
  "license": "http://creativecommons.org/licenses/by-nc-nd/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Pervasive Systems Group, Department of Computer Science University of Twente, The Netherlands,Research Centre on Interactive Media, Smart Systems and Emerging Technologies (RISE), Nicosia, Cyprus", 
      "@id": "https://orcid.org/0000-0002-8484-4256", 
      "@type": "Person", 
      "name": "Kamilaris Andreas"
    }, 
    {
      "affiliation": "Pervasive Systems Group, Department of Computer Science University of Twente, The Netherlands", 
      "@type": "Person", 
      "name": "van den Brink Corjan"
    }, 
    {
      "affiliation": "Department of Computer Science, University of Cyprus, Nicosia, Cyprus", 
      "@type": "Person", 
      "name": "Karatsiolis Savvas"
    }
  ], 
  "headline": "Training Deep Learning Models via Synthetic Data: Application in Unmanned Aerial Vehicles", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2019-10-30", 
  "url": "https://zenodo.org/record/3523006", 
  "keywords": [
    "UAV  Deep Learning", 
    "Generative Data", 
    "Aerial Imagery"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.5281/zenodo.3523006", 
  "@id": "https://doi.org/10.5281/zenodo.3523006", 
  "@type": "ScholarlyArticle", 
  "name": "Training Deep Learning Models via Synthetic Data: Application in Unmanned Aerial Vehicles"
}
25
8
views
downloads
All versions This version
Views 2525
Downloads 88
Data volume 10.4 MB10.4 MB
Unique views 2323
Unique downloads 66

Share

Cite as