---
_id: '13721'
abstract:
- lang: eng
  text: In this study, we examined the possibility of detecting different types of
    materials that contaminate carcasses during industrial pig slaughter using video
    image analysis and artificial intelligence (AI). A camera system was installed
    between evisceration and postmortem meat inspection on an industrial pig slaughter
    line with a capacity of 12,000 pigs per day. The pigs were photographed using
    five 2D cameras, and the images were analysed for contamination using an AI-based
    algorithm. The setup, which was developed and installed by CLK GmbH, performed
    under industrial conditions. In order to train the system, specifications were
    created for the most frequently occurring types of contamination, namely, intestinal
    contents, bile, stomach contents, and tubular rail fat. Afterward, the system
    was trained using annotated images. In principle, the system was able to recognize
    all types of contamination on the camera images; even pinhead-sized contaminations
    were visible. The agreement between the algorithm and the results of an expert
    assessor who assessed the images online agreed in 60% of the judgements. The agreement
    between experts using onsite assessment and those using online assessment by images
    was 73%. Thus, the kappa measure of agreement was κ = 0.1215 (p = 0.0199). Significantly
    higher recognition rates appear to be possible by adjusting the algorithm and
    increasing the number of training images. Thus, the system is a useful tool to
    preselect contaminated carcasses and to support postmortem inspection.
article_number: '1698416'
author:
- first_name: Janna
  full_name: Tholen, Janna
  id: '80924'
  last_name: Tholen
- first_name: Alina
  full_name: Kirse, Alina
  last_name: Kirse
- first_name: Alexander
  full_name: Voß, Alexander
  last_name: Voß
- first_name: Gereon
  full_name: Schulze Althoff, Gereon
  last_name: Schulze Althoff
- first_name: Lea
  full_name: Strotkötter, Lea
  last_name: Strotkötter
- first_name: Lothar
  full_name: Kreienbrock, Lothar
  last_name: Kreienbrock
- first_name: Matthias
  full_name: Upmann, Matthias
  id: '12666'
  last_name: Upmann
citation:
  ama: Tholen J, Kirse A, Voß A, et al. Detection of carcass contamination using video
    image analysis during industrial pig slaughter. <i>Frontiers in Food Science and
    Technology</i>. 2026;6. doi:<a href="https://doi.org/10.3389/frfst.2026.1698416">10.3389/frfst.2026.1698416</a>
  apa: Tholen, J., Kirse, A., Voß, A., Schulze Althoff, G., Strotkötter, L., Kreienbrock,
    L., &#38; Upmann, M. (2026). Detection of carcass contamination using video image
    analysis during industrial pig slaughter. <i>Frontiers in Food Science and Technology</i>,
    <i>6</i>, Article 1698416. <a href="https://doi.org/10.3389/frfst.2026.1698416">https://doi.org/10.3389/frfst.2026.1698416</a>
  bjps: <b>Tholen J <i>et al.</i></b> (2026) Detection of Carcass Contamination Using
    Video Image Analysis during Industrial Pig Slaughter. <i>Frontiers in Food Science
    and Technology</i> <b>6</b>.
  chicago: Tholen, Janna, Alina Kirse, Alexander Voß, Gereon Schulze Althoff, Lea
    Strotkötter, Lothar Kreienbrock, and Matthias Upmann. “Detection of Carcass Contamination
    Using Video Image Analysis during Industrial Pig Slaughter.” <i>Frontiers in Food
    Science and Technology</i> 6 (2026). <a href="https://doi.org/10.3389/frfst.2026.1698416">https://doi.org/10.3389/frfst.2026.1698416</a>.
  chicago-de: Tholen, Janna, Alina Kirse, Alexander Voß, Gereon Schulze Althoff, Lea
    Strotkötter, Lothar Kreienbrock und Matthias Upmann. 2026. Detection of carcass
    contamination using video image analysis during industrial pig slaughter. <i>Frontiers
    in Food Science and Technology</i> 6. doi:<a href="https://doi.org/10.3389/frfst.2026.1698416">10.3389/frfst.2026.1698416</a>,
    .
  din1505-2-1: '<span style="font-variant:small-caps;">Tholen, Janna</span> ; <span
    style="font-variant:small-caps;">Kirse, Alina</span> ; <span style="font-variant:small-caps;">Voß,
    Alexander</span> ; <span style="font-variant:small-caps;">Schulze Althoff, Gereon</span>
    ; <span style="font-variant:small-caps;">Strotkötter, Lea</span> ; <span style="font-variant:small-caps;">Kreienbrock,
    Lothar</span> ; <span style="font-variant:small-caps;">Upmann, Matthias</span>:
    Detection of carcass contamination using video image analysis during industrial
    pig slaughter. In: <i>Frontiers in Food Science and Technology</i> Bd. 6. Lausanne,
    Frontiers Media SA (2026)'
  havard: J. Tholen, A. Kirse, A. Voß, G. Schulze Althoff, L. Strotkötter, L. Kreienbrock,
    M. Upmann, Detection of carcass contamination using video image analysis during
    industrial pig slaughter, Frontiers in Food Science and Technology. 6 (2026).
  ieee: 'J. Tholen <i>et al.</i>, “Detection of carcass contamination using video
    image analysis during industrial pig slaughter,” <i>Frontiers in Food Science
    and Technology</i>, vol. 6, Art. no. 1698416, 2026, doi: <a href="https://doi.org/10.3389/frfst.2026.1698416">10.3389/frfst.2026.1698416</a>.'
  mla: Tholen, Janna, et al. “Detection of Carcass Contamination Using Video Image
    Analysis during Industrial Pig Slaughter.” <i>Frontiers in Food Science and Technology</i>,
    vol. 6, 1698416, 2026, <a href="https://doi.org/10.3389/frfst.2026.1698416">https://doi.org/10.3389/frfst.2026.1698416</a>.
  short: J. Tholen, A. Kirse, A. Voß, G. Schulze Althoff, L. Strotkötter, L. Kreienbrock,
    M. Upmann, Frontiers in Food Science and Technology 6 (2026).
  ufg: '<b>Tholen, Janna u. a.</b>: Detection of carcass contamination using video
    image analysis during industrial pig slaughter, in: <i>Frontiers in Food Science
    and Technology</i> 6 (2026).'
  van: Tholen J, Kirse A, Voß A, Schulze Althoff G, Strotkötter L, Kreienbrock L,
    et al. Detection of carcass contamination using video image analysis during industrial
    pig slaughter. Frontiers in Food Science and Technology. 2026;6.
date_created: 2026-04-30T13:02:33Z
date_updated: 2026-05-04T09:41:58Z
department:
- _id: DEP4028
- _id: DEP4029
doi: 10.3389/frfst.2026.1698416
intvolume: '         6'
keyword:
- artificial intelligence (AI)
- bile contamination
- contamination detection
- faecal contamination
- slaughter hygiene
- tubular rail fat
language:
- iso: eng
place: Lausanne
publication: Frontiers in Food Science and Technology
publication_identifier:
  issn:
  - 2674-1121
publication_status: published
publisher: Frontiers Media SA
status: public
title: Detection of carcass contamination using video image analysis during industrial
  pig slaughter
type: scientific_journal_article
user_id: '83781'
volume: 6
year: '2026'
...
---
_id: '14070'
abstract:
- lang: eng
  text: "Deploying digital twins across the broader building stock is constrained
    by a key bottleneck: high-quality 3D content from LiDAR or photogrammetry remains
    labor-intensive and difficult to scale. We introduce Generative Twins (GT), a
    workflow that shifts digital twin creation from explicit geometric reconstruction
    toward probabilistic 3D synthesis. The pipeline takes a\r\nsingle street-level
    façade photograph, corrects perspective distortion and removes occlusions, uses
    an instruction-conditioned multimodal image model to synthesise an isometric view
    of the building, and passes that view to an image-to-3D reconstruction model that
    leverages learned shape priors to produce a textured mesh without manual modelling.
    Three image to-3D platforms (Hitem3D, Hyper3D and Hunyuan3D 3.1) are compared
    on identical isometric inputs and assessed on architectural boundary clarity.
    We demonstrate GT through two applied cases: (i) reconstruction of ordinary residential
    streets in Detmold as stimuli for a virtual-reality study of multi sensory urban
    perception, and (ii) Green Editor, a design-exploration tool in which façade greenery
    is added or removed at the image layer before mesh generation.\r\nTogether these
    cases position Generative Twins as a scalable pathway for the digitization of
    ordinary building stock, with emphasis on controllability, editability, and iterative
    design workflows."
author:
- first_name: Mohamed Khaled
  full_name: Ashmawy, Mohamed Khaled
  id: '81286'
  last_name: Ashmawy
- first_name: Buse
  full_name: Akay, Buse
  id: '88405'
  last_name: Akay
- first_name: Alvaro
  full_name: Balderrama, Alvaro
  id: '74171'
  last_name: Balderrama
  orcid: 0000-0002-4118-2838
citation:
  ama: 'Ashmawy MK, Akay B, Balderrama A. <i>Towards Generative Twins: An AI Based
    Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis</i>. Vol 1.
    eCAADe; 2026. doi:<a href="https://doi.org/10.52842/conf.ecaade.2026.1.619">10.52842/conf.ecaade.2026.1.619</a>'
  apa: 'Ashmawy, M. K., Akay, B., &#38; Balderrama, A. (2026). Towards Generative
    Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis.
    In <i>eCAADe proceedings</i> (Vol. 1). eCAADe. <a href="https://doi.org/10.52842/conf.ecaade.2026.1.619">https://doi.org/10.52842/conf.ecaade.2026.1.619</a>'
  bjps: '<b>Ashmawy MK, Akay B and Balderrama A</b> (2026) <i>Towards Generative Twins:
    An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis</i>.
    eCAADe.'
  chicago: 'Ashmawy, Mohamed Khaled, Buse Akay, and Alvaro Balderrama. <i>Towards
    Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic
    Synthesis</i>. <i>ECAADe Proceedings</i>. Vol. 1. eCAADe, 2026. <a href="https://doi.org/10.52842/conf.ecaade.2026.1.619">https://doi.org/10.52842/conf.ecaade.2026.1.619</a>.'
  chicago-de: 'Ashmawy, Mohamed Khaled, Buse Akay und Alvaro Balderrama. 2026. <i>Towards
    Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic
    Synthesis</i>. <i>eCAADe proceedings</i>. Bd. 1. eCAADe. doi:<a href="https://doi.org/10.52842/conf.ecaade.2026.1.619">10.52842/conf.ecaade.2026.1.619</a>,
    .'
  din1505-2-1: '<span style="font-variant:small-caps;">Ashmawy, Mohamed Khaled</span>
    ; <span style="font-variant:small-caps;">Akay, Buse</span> ; <span style="font-variant:small-caps;">Balderrama,
    Alvaro</span>: <i>Towards Generative Twins: An AI Based Pipeline from Explicit
    3D Reconstruction to Probabilistic Synthesis</i>. Bd. 1 : eCAADe, 2026'
  havard: 'M.K. Ashmawy, B. Akay, A. Balderrama, Towards Generative Twins: An AI Based
    Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis, eCAADe, 2026.'
  ieee: 'M. K. Ashmawy, B. Akay, and A. Balderrama, <i>Towards Generative Twins: An
    AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis</i>,
    vol. 1. eCAADe, 2026. doi: <a href="https://doi.org/10.52842/conf.ecaade.2026.1.619">10.52842/conf.ecaade.2026.1.619</a>.'
  mla: 'Ashmawy, Mohamed Khaled, et al. “Towards Generative Twins: An AI Based Pipeline
    from Explicit 3D Reconstruction to Probabilistic Synthesis.” <i>ECAADe Proceedings</i>,
    vol. 1, eCAADe, 2026, <a href="https://doi.org/10.52842/conf.ecaade.2026.1.619">https://doi.org/10.52842/conf.ecaade.2026.1.619</a>.'
  short: 'M.K. Ashmawy, B. Akay, A. Balderrama, Towards Generative Twins: An AI Based
    Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis, eCAADe, 2026.'
  ufg: '<b>Ashmawy, Mohamed Khaled/Akay, Buse/Balderrama, Alvaro</b>: Towards Generative
    Twins: An AI Based Pipeline from Explicit 3D Reconstruction to Probabilistic Synthesis,
    Bd. 1, o. O. 2026.'
  van: 'Ashmawy MK, Akay B, Balderrama A. Towards Generative Twins: An AI Based Pipeline
    from Explicit 3D Reconstruction to Probabilistic Synthesis. Vol. 1, eCAADe proceedings.
    eCAADe; 2026.'
conference:
  end_date: 2026-09-11
  location: Lübeck
  name: 44. eCAADe-Konferenz
  start_date: 2026-09-07
date_created: 2026-09-30T10:14:15Z
date_updated: 2026-10-01T14:28:23Z
department:
- _id: DEP1634
doi: 10.52842/conf.ecaade.2026.1.619
intvolume: '         1'
keyword:
- Digital Twins
- Virtual Reality (VR
- Artificial Intelligence (AI)
- Image-to-3D
- Generative Design.
language:
- iso: eng
publication: eCAADe proceedings
publication_identifier:
  issn:
  - 2684-1843
publication_status: published
publisher: eCAADe
status: public
title: 'Towards Generative Twins: An AI Based Pipeline from Explicit 3D Reconstruction
  to Probabilistic Synthesis'
type: conference_editor_article
user_id: '83781'
volume: 1
year: '2026'
...