TU Darmstadt / ULB / TUprints

Deep learning-based pupil model predicts time and spectral dependent light responses

Zandi, Babak ; Khanh, Tran Quoc (2022)
Deep learning-based pupil model predicts time and spectral dependent light responses.
In: Scientific Reports, 2022, 11
doi: 10.26083/tuprints-00021202
Article, Secondary publication, Publisher's Version

[img] Text
s41598-020-79908-5(1).pdf
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (8MB)
[img] Text
Supplement21240.pdf
Copyright Information: CC BY 4.0 International - Creative Commons, Attribution.

Download (8MB)
Item Type: Article
Type of entry: Secondary publication
Title: Deep learning-based pupil model predicts time and spectral dependent light responses
Language: English
Date: 4 May 2022
Place of Publication: Darmstadt
Year of primary publication: 2022
Publisher: Springer Nature
Journal or Publication Title: Scientific Reports
Volume of the journal: 11
Collation: 16 Seiten
DOI: 10.26083/tuprints-00021202
Corresponding Links:
Origin: Secondary publication via sponsored Golden Open Access
Abstract:

Although research has made significant findings in the neurophysiological process behind the pupillary light reflex, the temporal prediction of the pupil diameter triggered by polychromatic or chromatic stimulus spectra is still not possible. State of the art pupil models rested in estimating a static diameter at the equilibrium-state for spectra along the Planckian locus. Neither the temporal receptor-weighting nor the spectral-dependent adaptation behaviour of the afferent pupil control path is mapped in such functions. Here we propose a deep learning-driven concept of a pupil model, which reconstructs the pupil’s time course either from photometric and colourimetric or receptor-based stimulus quantities. By merging feed-forward neural networks with a biomechanical differential equation, we predict the temporal pupil light response with a mean absolute error below 0.1 mm from polychromatic (2007 ± 1 K, 4983 ± 3 K, 10,138 ± 22 K) and chromatic spectra (450 nm, 530 nm, 610 nm, 660 nm) at 100.01 ± 0.25 cd/m². This non-parametric and self-learning concept could open the door to a generalized description of the pupil behaviour.

Status: Publisher's Version
URN: urn:nbn:de:tuda-tuprints-212024
Classification DDC: 600 Technology, medicine, applied sciences > 600 Technology
600 Technology, medicine, applied sciences > 620 Engineering and machine engineering
Divisions: 18 Department of Electrical Engineering and Information Technology > Adaptive Lighting Systems and Visual Processing
Date Deposited: 04 May 2022 13:49
Last Modified: 27 Oct 2023 10:13
URI: https://tuprints.ulb.tu-darmstadt.de/id/eprint/21202
PPN: 494561521
Export:
Actions (login required)
View Item View Item