Visual Attention Software: A New Tool for Understanding the “Subliminal” Experience of the Built Environment

Abstract

Eye-tracking technology is a biometric tool that has found many commercial and research applications. The recent advent of affordable wearable sensors has considerably expanded the range of these possibilities to fields such as computer gaming, education, entertainment, health, neuromarketing, psychology, etc. The Visual Attention Software by 3M (3M-VAS) is an artificial intelligence application that was formulated using experimental data from eye-tracking. It can be used to predict viewer reactions to images, generating fixation point probability maps and fixation point sequence estimations, thus revealing pre-attentive processing of visual stimuli with a very high degree of accuracy. We have used 3M-VAS software in an innovative implementation to analyze images of different buildings, either in their original state or photographically manipulated, as well as various geometric patterns. The software not only reveals non-obvious fixation points, but also overall relative design coherence, a key element of Christopher Alexander’s theory of geometrical order. A more evenly distributed field of attention seen in some structures contrasts with other buildings being ignored, those showing instead unconnected points of splintered attention. Our findings are non-intuitive and surprising. We link these results to both Alexander’s theory and Neuroscience, identify potential pitfalls in the software’s use, and also suggest ways to avoid them.

The Importance of Domestic Space in the Times of COVID-19

“…Tools that people can apply immediately, at least when the pandemic allows it, include biophilic design [7][8][9][10], Christopher Alexander's design patterns and theory of geometric coherence [11,16,[42][43][44], neuro-architecture [32,41], principles of Biological Architecture (environment, form, and human physiology) [10,17,51], rules of coherent complex structure [19][20][21], eye-tracking and visual attention scans [32,52,53], fractals [12][13][14][15], and so on. Each of these related techniques for evidence-based design offers descriptive texts and built examples that define a new design discipline, and it is a great shame that the world-in particular, architectural academia-continues to ignore these lessons.…”

Ошибка Александера. Почему Кристоферу Александеру Не Удалось Гуманизировать Архитектуру?

“…Тем не менее парадигма дизайна на основе изображений неоднократно тестировалась во всем мире, и она не удовлетворяет биологическим потребностям человека [18,19]. Наше тело эволюционировало, чтобы отвергать не-фрактальные формы, блестящие поверхности и неприродные материалы [10,11,20]. Академическая архитектура скрывает эти научные открытия от студентов [21].…”

Potential of eye-tracking simulation software for analyzing landscape preferences

“…Hollander et al [ 54 ] compared the outcomes between laboratory-based eye-tracking experiments and those generated by simulation software in the context of urban design perceptions; the results were highly consistent suggesting that simulation results can be used as a proxy for laboratory-based eye-tracking results. Accordingly, first studies used eye-tracking simulation software in urban settings, focusing on streetscapes and facades, providing promising perspectives for urban planning [ 59 – 61 ]. These studies used Visual Attention Software by 3M (3M-VAS), a proprietary artificial intelligence software, which simulates “first glance vision”.…”

“…These studies used Visual Attention Software by 3M (3M-VAS), a proprietary artificial intelligence software, which simulates “first glance vision”. Eye-tracking simulation of the initial fixations can provide information on the pre-attentive processing of visual components that has taken place [ 59 ]. The visual system can select salient information to guide appropriate responses with survival value.…”

“…However, this technology is not yet sufficiently explored for rural and (semi-)natural environments such as mountain landscapes, as it has only been tested in urban settings [ 59 – 61 ]. It remains unclear, which information that is generated by eye-tracking simulation software can be useful for explaining landscape preferences and whether this information can enhance modelling approaches used to estimate aesthetic landscape values [ 11 ].…”