Towards a Human-Centred Cognitive Model of Visuospatial Complexity in Everyday Driving

TL;DR

This paper presents a human-centered cognitive model of visuospatial complexity in naturalistic driving, integrating perceptual attributes and behavioral evaluation to improve understanding and analysis of driving environments.

Contribution

It introduces a novel cognitive model of visuospatial complexity based on human perception and behavior, applicable for dataset creation and explainable computational analysis.

Findings

Model incorporates structural and dynamic attributes of driving scenes.

Behavioral evaluation with human subjects validates the model.

Preliminary application for dataset creation and benchmarking.

Abstract

We develop a human-centred, cognitive model of visuospatial complexity in everyday, naturalistic driving conditions. With a focus on visual perception, the model incorporates quantitative, structural, and dynamic attributes identifiable in the chosen context; the human-centred basis of the model lies in its behavioural evaluation with human subjects with respect to psychophysical measures pertaining to embodied visuoauditory attention. We report preliminary steps to apply the developed cognitive model of visuospatial complexity for human-factors guided dataset creation and benchmarking, and for its use as a semantic template for the (explainable) computational analysis of visuospatial complexity.