KIT | KIT-Bibliothek | Impressum | Datenschutz

Saliency prediction in 360° architectural scenes: Performance and impact of daylight variations

Karmann, Caroline ORCID iD icon 1; Aydemir, Bahar; Chamilothori, Kynthia; Kim, Seungryong; Süsstrunk, Sabine; Andersen, Marilyne
1 Institut Entwerfen und Bautechnik (IEB), Karlsruher Institut für Technologie (KIT)

Abstract:

Saliency models are image-based prediction models that estimate human visual attention. Such models, when applied to architectural spaces, could pave the way for design decisions where visual attention is taken into account. In this study, we tested the performance of eleven commonly used saliency models that combine traditional and deep learning methods on 126 rendered interior scenes with associated head tracking data. The data was extracted from three experiments conducted in virtual reality between 2016 and 2018. Two of these datasets pertain to the perceptual effects of daylight and include variations of daylighting conditions for a limited set of interior spaces, thereby allowing to test the influence of light conditions on human head movement. Ground truth maps were extracted from the collected head tracking logs, and the prediction accuracy of the models was tested via the correlation coefficient between ground truth and prediction maps. To address the possible inflation of results due to the equator bias, we conducted complementary analyses by restricting the area of investigation to the equatorial image regions. Although limited to immersive virtual environments, the promising performance of some traditional models such as GBVS360eq and BMS360eq for colored and textured architectural rendered spaces offers us the prospect of their possible integration into design tools. ... mehr


Verlagsausgabe §
DOI: 10.5445/IR/1000163915
Veröffentlicht am 13.11.2023
Originalveröffentlichung
DOI: 10.1016/j.jenvp.2023.102110
Scopus
Zitationen: 1
Dimensions
Zitationen: 1
Cover der Publikation
Zugehörige Institution(en) am KIT Institut Entwerfen und Bautechnik (IEB)
Publikationstyp Zeitschriftenaufsatz
Publikationsmonat/-jahr 12.2023
Sprache Englisch
Identifikator ISSN: 0272-4944, 1522-9610
KITopen-ID: 1000163915
Erschienen in Journal of Environmental Psychology
Verlag Elsevier
Band 92
Seiten Art.-NR.: 102110
Vorab online veröffentlicht am 27.10.2023
Nachgewiesen in Dimensions
Web of Science
Scopus
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page