---
_id: '12904'
abstract:
- lang: eng
  text: 'It is crucial to identify defective machine components in production to ensure
    quality. Some components generate heat when defective, so automating the inspection
    process with a thermal imaging camera can provide qualitative measurements. This
    work aims to use computer vision methods to locate these components in thermal
    images. Since there is currently  no comparison of object detection and semantic
    segmentation algorithms for this use case, this study compares different architectures
    with the goal of localising these components for  further defect inspection. Moreover,
    as there are currently no datasets for this use case, this study contributes a
    novel annotated dataset of thermal images of combine harvester  components. The
    different algorithms are evaluated based on the quality of their predictions and
    their suitability for further defect inspection. As semantic segmentation and
    object  detection cannot be directly compared with each other, custom weighted
    metrics are used. The architectures evaluated include RetinaNet, YOLOV8 Detector,
    DeepLabV3+, and  SegFormer. Based on the experimental results, semantic segmentation
    outperforms object detection regarding the use case, and the SegFormer architecture
    achieves the best results  with a weighted MeanIOU of 0.853.  '
author:
- first_name: Hanna
  full_name: Senke, Hanna
  id: '79810'
  last_name: Senke
- first_name: Dennis
  full_name: Sprute, Dennis
  last_name: Sprute
- first_name: Ulrich
  full_name: Büker, Ulrich
  id: '81453'
  last_name: Büker
  orcid: 0000-0002-4403-3889
- first_name: Holger
  full_name: Flatt, Holger
  id: '58494'
  last_name: Flatt
citation:
  ama: Senke H, Sprute D, Büker U, Flatt H. <i>Deep Learning-Based Localisation of
    Combine Harvester Components in Thermal Images</i>. (Längle T, Heizmann M, Karlsruher
    Institut für Technologie. Institut für Industrielle Informationstechnik , Fraunhofer-Institut
    für Optronik, Systemtechnik und Bildauswertung , eds.). KIT Scientific Publishing;
    2024:71-82. doi:<a href="https://doi.org/10.58895/ksp/1000174496-7">10.58895/ksp/1000174496-7</a>
  apa: Senke, H., Sprute, D., Büker, U., &#38; Flatt, H. (2024). Deep learning-based
    localisation of combine harvester components in thermal images. In T. Längle,
    M. Heizmann, Karlsruher Institut für Technologie. Institut für Industrielle Informationstechnik
    , &#38; Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung  (Eds.),
    <i>Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024</i> (pp. 71–82). KIT
    Scientific Publishing. <a href="https://doi.org/10.58895/ksp/1000174496-7">https://doi.org/10.58895/ksp/1000174496-7</a>
  bjps: '<b>Senke H <i>et al.</i></b> (2024) <i>Deep Learning-Based Localisation of
    Combine Harvester Components in Thermal Images</i>, Längle T et al. (eds). Karlsruhe:
    KIT Scientific Publishing.'
  chicago: 'Senke, Hanna, Dennis Sprute, Ulrich Büker, and Holger Flatt. <i>Deep Learning-Based
    Localisation of Combine Harvester Components in Thermal Images</i>. Edited by
    Thomas Längle, Michael Heizmann, Karlsruher Institut für Technologie. Institut
    für Industrielle Informationstechnik , and Fraunhofer-Institut für Optronik, Systemtechnik
    und Bildauswertung . <i>Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024</i>.
    Karlsruhe: KIT Scientific Publishing, 2024. <a href="https://doi.org/10.58895/ksp/1000174496-7">https://doi.org/10.58895/ksp/1000174496-7</a>.'
  chicago-de: 'Senke, Hanna, Dennis Sprute, Ulrich Büker und Holger Flatt. 2024. <i>Deep
    learning-based localisation of combine harvester components in thermal images</i>.
    Hg. von Thomas Längle, Michael Heizmann, Karlsruher Institut für Technologie.
    Institut für Industrielle Informationstechnik , und Fraunhofer-Institut für Optronik,
    Systemtechnik und Bildauswertung . <i>Forum Bildverarbeitung 2024 = Image Pocessing
    Forum 2024</i>. Karlsruhe: KIT Scientific Publishing. doi:<a href="https://doi.org/10.58895/ksp/1000174496-7">10.58895/ksp/1000174496-7</a>,
    .'
  din1505-2-1: '<span style="font-variant:small-caps;">Senke, Hanna</span> ; <span
    style="font-variant:small-caps;">Sprute, Dennis</span> ; <span style="font-variant:small-caps;">Büker,
    Ulrich</span> ; <span style="font-variant:small-caps;">Flatt, Holger</span> ;
    <span style="font-variant:small-caps;">Längle, T.</span> ; <span style="font-variant:small-caps;">Heizmann,
    M.</span> ; <span style="font-variant:small-caps;">Karlsruher Institut für Technologie.
    Institut für Industrielle Informationstechnik </span> ; <span style="font-variant:small-caps;">Fraunhofer-Institut
    für Optronik, Systemtechnik und Bildauswertung </span> (Hrsg.): <i>Deep learning-based
    localisation of combine harvester components in thermal images</i>. Karlsruhe :
    KIT Scientific Publishing, 2024'
  havard: H. Senke, D. Sprute, U. Büker, H. Flatt, Deep learning-based localisation
    of combine harvester components in thermal images, KIT Scientific Publishing,
    Karlsruhe, 2024.
  ieee: 'H. Senke, D. Sprute, U. Büker, and H. Flatt, <i>Deep learning-based localisation
    of combine harvester components in thermal images</i>. Karlsruhe: KIT Scientific
    Publishing, 2024, pp. 71–82. doi: <a href="https://doi.org/10.58895/ksp/1000174496-7">10.58895/ksp/1000174496-7</a>.'
  mla: Senke, Hanna, et al. “Deep Learning-Based Localisation of Combine Harvester
    Components in Thermal Images.” <i>Forum Bildverarbeitung 2024 = Image Pocessing
    Forum 2024</i>, edited by Thomas Längle et al., KIT Scientific Publishing, 2024,
    pp. 71–82, <a href="https://doi.org/10.58895/ksp/1000174496-7">https://doi.org/10.58895/ksp/1000174496-7</a>.
  short: H. Senke, D. Sprute, U. Büker, H. Flatt, Deep Learning-Based Localisation
    of Combine Harvester Components in Thermal Images, KIT Scientific Publishing,
    Karlsruhe, 2024.
  ufg: '<b>Senke, Hanna u. a.</b>: Deep learning-based localisation of combine harvester
    components in thermal images, hg. von Längle, Thomas u. a., Karlsruhe 2024.'
  van: 'Senke H, Sprute D, Büker U, Flatt H. Deep learning-based localisation of combine
    harvester components in thermal images. Längle T, Heizmann M, Karlsruher Institut
    für Technologie. Institut für Industrielle Informationstechnik , Fraunhofer-Institut
    für Optronik, Systemtechnik und Bildauswertung , editors. Forum Bildverarbeitung
    2024 = Image Pocessing Forum 2024. Karlsruhe: KIT Scientific Publishing; 2024.'
conference:
  end_date: 2024-11-22
  location: Karlsruhe
  name: Forum Bildverarbeitung 2024
  start_date: 2024-11-21
corporate_editor:
- 'Karlsruher Institut für Technologie. Institut für Industrielle Informationstechnik '
- 'Fraunhofer-Institut für Optronik, Systemtechnik und Bildauswertung '
date_created: 2025-05-08T14:01:20Z
date_updated: 2025-05-12T07:33:48Z
department:
- _id: DEP5023
doi: 10.58895/ksp/1000174496-7
editor:
- first_name: Thomas
  full_name: Längle, Thomas
  last_name: Längle
- first_name: Michael
  full_name: Heizmann, Michael
  last_name: Heizmann
keyword:
- industrial quality assurance
- deep learning architectures
- object localisation
- Thermal images
language:
- iso: eng
page: 71-82
place: Karlsruhe
publication: Forum Bildverarbeitung 2024 = Image Pocessing Forum 2024
publication_identifier:
  isbn:
  - 978-3-7315-1386-5
publication_status: published
publisher: KIT Scientific Publishing
quality_controlled: '1'
status: public
title: Deep learning-based localisation of combine harvester components in thermal
  images
type: conference_editor_article
user_id: '83781'
year: '2024'
...