A Visual Attention Model Based on Eye Tracking in 3D Scene Maps

Bincheng Yang,Hongwei Li

doi:10.3390/ijgi10100664

Abstract

Visual attention plays a crucial role in the map-reading process and is closely related to the map cognitive process. Eye-tracking data contains a wealth of visual information that can be used to identify cognitive behavior during map reading. Nevertheless, few researchers have applied these data to quantifying visual attention. This study proposes a method for quantitatively calculating visual attention based on eye-tracking data for 3D scene maps. First, eye-tracking technology was used to obtain the differences in the participants’ gaze behavior when browsing a street view map in the desktop environment, and to establish a quantitative relationship between eye movement indexes and visual saliency. Then, experiments were carried out to determine the quantitative relationship between visual saliency and visual factors, using vector 3D scene maps as stimulus material. Finally, a visual attention model was obtained by fitting the data. It was shown that a combination of three visual factors can represent the visual attention value of a 3D scene map: color, shape, and size, with a goodness of fit (R2) greater than 0.699. The current research helps to determine and quantify the visual attention allocation during map reading, laying the foundation for automated machine mapping.

Highlights

This article is a contribution to the Special Issue “Eye Tracking in Cartography”, which is dedicated to the research problem of understanding a person’s cognitive state through eye movement analysis and interpreting their cognitive processes when performing visuospatial tasks
This study focused on establishing the relationship between visual variables and human visual attention, which is essential for quantifying visual attention
The prediction accuracy of visual attention allocation for different 3D scenes was different for different models

Summary

Introduction

This article is a contribution to the Special Issue “Eye Tracking in Cartography”, which is dedicated to the research problem of understanding a person’s cognitive state through eye movement analysis and interpreting their cognitive processes when performing visuospatial tasks (such as map reading, route learning, and navigation). The research facilitates understanding the influence of map visual attributes on visual attention allocation when performing a 3D scene map-reading task. It provides a basis for studying the visual cognitive mechanisms of 3D scene maps. The study of map visual cognition involves the investigation of how humans read maps and obtain geospatial information, starting from human visual characteristics. It is usually based on subjective feelings, focusing on the reader’s evaluation of the design of abstract map symbols and the rationality of improving the map’s design [2]. Visual cognition has attracted increasing attention of researchers and has become a popular research topic with in the field of map cognition [4,5,6,7]

Methods

Results

Discussion

Conclusion