• English
  • Deutsch
  • Log In
    Password Login
    Research Outputs
    Fundings & Projects
    Researchers
    Institutes
    Statistics
Repository logo
Fraunhofer-Gesellschaft
  1. Home
  2. Fraunhofer-Gesellschaft
  3. Scopus
  4. Efficient training data generation by clustering-based classification
 
  • Details
  • Full
Options
2022
Conference Paper
Title

Efficient training data generation by clustering-based classification

Abstract
Insufficient amount or complete absence of reference data for the training of classifiers is a general topic. Especially the state-of-The-Art deep learning approaches have to deal with the availability or adaption of this reference data to produce the reliable results they are designed for. This paper will pursue different approaches according to the absence of training data for land cover classification from aerial images. First, we will analyze the performance of traditional classification in the absence of reference data using clustering techniques and salient features for the assignment of semantic labels. Second, we will transfer the results as training data to a DeepLabv3+ CNN with pre-Trained weights to demonstrate the usability of the generated training data. Third, we expand the clustering approaches and combine them with a Random Forest classifier. Finally, if user interaction and manual annotation of training data are still necessary, we also introduce our labeling GUI that enables a simple, fast, and comfortable training data generation with only a few clicks. To evaluate our procedure, we used two datasets, including the Vaihingen benchmark, for which ground truth is available. Without any interactive steps except setting a few algorithm paremeters, we achieved an overall accuracy of 75% using the Deeplab method with image data only.
Author(s)
Böge, Melanie  
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB  
Bulatov, Dimitri  
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB  
Debroize, Denis
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB  
Häufel, Gisela  
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB  
Lucks, L.
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB  
Mainwork
XXIV ISPRS Congress "Imaging today, foreseeing tomorrow", Commission III  
Conference
International Society for Photogrammetry and Remote Sensing (ISPRS Congress) 2022  
Open Access
DOI
10.5194/isprs-Annals-V-3-2022-179-2022
Additional full text version
Landing Page
Language
English
Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung IOSB  
Keyword(s)
  • Classification

  • CNN

  • GUI

  • Hierarchical Clustering

  • Labeling

  • Training Data

  • Cookie settings
  • Imprint
  • Privacy policy
  • Api
  • Contact
© 2024