CoChat
Sign Up
Cited by 51Neuroscience and Neural EngineeringTactile and Sensory InteractionsEEG and Brain-Computer Interfaces

Real-world indoor mobility with simulated prosthetic vision: The benefits and feasibility of contour-based scene simplification at different phosphene resolutions

Open access
de Ruyter van Steveninck, Jaap, van Gestel, Tom, Koenders, Paula, van der Ham, Guus, Vereecken, Floris, Güçlü, Umut, van Gerven, Marcel, Güçlütürk, Yağmur +1 more·2022·Journal of Vision
DOI 10.1167/jov.22.2.1PMC PMC8819280
Open this paper in CoChat — free accountOpen PDF

Abstract

Neuroprosthetic implants are a promising technology for restoring some form of vision in people with visual impairments via electrical neurostimulation in the visual pathway. Although an artificially generated prosthetic percept is relatively limited compared with normal vision, it may provide some elementary perception of the surroundings, re-enabling daily living functionality. For mobility in particular, various studies have investigated the benefits of visual neuroprosthetics in a simulated prosthetic vision paradigm with varying outcomes. The previous literature suggests that scene simplification via image processing, and particularly contour extraction, may potentially improve the mobility performance in a virtual environment. In the current simulation study with sighted participants, we explore both the theoretically attainable benefits of strict scene simplification in an indoor environment by controlling the environmental complexity, as well as the practically achieved improvement with a deep learning-based surface boundary detection implementation compared with traditional edge detection. A simulated electrode resolution of 26 × 26 was found to provide sufficient information for mobility in a simple environment. Our results suggest that, for a lower number of implanted electrodes, the removal of background textures and within-surface gradients may be beneficial in theory. However, the deep learning-based implementation for surface boundary detection did not improve mobility performance in the current study. Furthermore, our findings indicate that, for a greater number of electrodes, the removal of within-surface gradients and background textures may deteriorate, rather than improve, mobility. Therefore, finding a balanced amount of scene simplification requires a careful tradeoff between informativity and interpretability that may depend on the number of implanted electrodes.

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1167/jov.22.2.1

Cites

57 of 57 references verified0 citation errors · 0 not checkable

Statistics

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The use of pre-trained convolutional neural networks was proposed in three studies as a pre-processing step for saliency extraction.

    “The use of pre-trained convolutional neural networks was proposed in three studies82–84 as a pre-processing step for saliency extraction.”

    From Visual Prostheses in the Era of Artificial Intelligence Technology (2025) · cites this paper as [84]

    The Introduction describes testing a pretrained deep neural network for real-time surface-boundary detection, and Materials and methods (Image processing) identifies the pretrained SharpNet model. That supports the use of a pretrained network in image preprocessing, but the paper describes contour and surface-boundary extraction, not saliency extraction. This source alone also cannot establish what the other two cited studies proposed. (LLM, conf=0.83)

    Experimental — accuracy not yet measured

  • These three studies proposed to combine outputs of two deep learning models to build their saliency maps.

    “These three studies have proposed to combine outputs of two deep learning models to build their saliency maps (saliency with depth,83 contours with surface normals,84 contours with semantic masks).82”

    From Visual Prostheses in the Era of Artificial Intelligence Technology (2025) · cites this paper as [84]

    The Materials and methods > Image processing section says the authors combined contours from a surface-normal estimation map with a thresholded boundary prediction. But it identifies both predictions as outputs of the single SharpNet model, not two deep-learning models; it also describes the result as a surface-boundary mask rather than a saliency map. No page number is available in our copy. (LLM, conf=0.91)

    Experimental — accuracy not yet measured

  • The models had been pre-trained on natural image datasets.

    “The models had been pre-trained on natural image datasets.”

    From Visual Prostheses in the Era of Artificial Intelligence Technology (2025) · cites this paper as [84]

    The Image processing section says the SharpNet model was pretrained on the NYUv2 dataset, and the Discussion describes its training data as naturalistic indoor images. The source establishes this for one model and one dataset, not for multiple models and datasets. (LLM, conf=0.87)

    Experimental — accuracy not yet measured

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Cites

Flagged first, then by citations

Research works printed but not linked: 6

  1. Bollen, C. J. M., Guclu, U., van Wezel, R. J. A., van Gerven, M. A. J., & Gucluturk, Y. (2019). Simulating neuroprosthetic vision for emotion recognition. 2019 8th International Conference on Affective Computing and Intelligence Interaction Workshops and Demos (pp. 85– 87). Cambridge, UK.
  2. Bradski, G. (2000). The OpenCV library. Dr Dobb's Journal of Software Tools, 25, 120– 125.
  3. Dowling, J. A., Maeder, A., & Boles, W. (2004). Mobility enhancement and assessment for a visual prosthesis. In: Amini AA, Manduca A (Eds.), Seventh Australian and New Zealand Intelligence Intelligent Information Systems Conference, 2001 (p. 780). Perth, WA: IEEE.
  4. Dowling, J., Boles, W. W., Maeder, A J. (2006). Simulated artificial human vision: The effects of spatial resolution and frame rate on mobility (pp. 138–143). Amsterdam, the Netherlands: IOS Press.
  5. Han, N., Srivastava, S., Xu, A., Klein, D., & Beyeler, M. (2021). Deep learning–based scene simplification for bionic vision. In: Augmented Humans International Conference 2021, Rovaniemi, Finland, February 22 - 24, 2021 (pp. 45– 54). New York: ACM.
  6. Silberman, N., Hoiem, D., Kohli, P., & Fergus, R.. (2012). Indoor segmentation and support inference from RGBD images (pp. 746–760). European Conference on Computer Vision ’12. Berlin: Springer.

Cited by

Sorted by citations

Related

Authors
de Ruyter van Steveninck, J., van Gestel, T., Koenders, P., van der Ham, G., Vereecken, F., Güçlü, U., van Gerven, M., Güçlütürk, Y., & van Wezel, R.
Affiliations
  • Department of Artificial Intelligence, Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, the Netherlands
  • Department of Biophysics, Donders Institute for Brain, Cognition and Behaviour, Radboud University, Nijmegen, the Netherlands
  • Radboud University Nijmegen (NL)
Corresponding author
  • Koenders, Paula
  • Vereecken, Floris
  • Güçlü, Umut
  • Güçlütürk, Yağmur
ORCID
Venue
Journal of Vision
Publisher
Association for Research in Vision and Ophthalmology (ARVO)
Published
2022-02-01
Volume
22
Issue
2
Pages
1
ISSN
1534-7362 (ISSN-L)
DOI
10.1167/jov.22.2.1
PMC
PMC8819280
OpenAlex
W4210425967
Cited by
51
References
57
Citations by year
2026: 7 · 2025: 16 · 2024: 11 · 2023: 12 · 2022: 5
FWCI
4.86
Type
journal article
Language
en
Open access
Licence
Locations
  • Journal of Vision (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • University of Twente Research Information (publishedVersion, cc-by)
  • Radboud Repository (Radboud University) (submittedVersion)
  • Radboud Repository (Radboud University) (submittedVersion, other-oa)
  • University of Twente Research Information (submittedVersion, cc-by)
Funders
Nederlandse Organisatie voor Wetenschappelijk Onderzoek
Topics
  • Life Sciences › Neuroscience › Cellular and Molecular Neuroscience › Neuroscience and Neural Engineering
  • Life Sciences › Neuroscience › Cognitive Neuroscience › Tactile and Sensory Interactions
  • Life Sciences › Neuroscience › Cognitive Neuroscience › EEG and Brain-Computer Interfaces
Keywords
visual prosthesis, simulated prosthetic vision, electrical neurostimulation, indoor mobility, contour detection, deep learning, edge detection, visual impairment, environmental complexity
MeSH terms
Feasibility Studies, Form Perception, Humans, Phosphenes, Vision, Ocular, Vision Disorders

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review