Three-Dimensional Gaze Projection Heat-Mapping of Outdoor Mobile Eye-Tracking Data

Simpson, James

doi:10.15763/issn.2470-9670.2021.v5.i1.a75

Cited by 10 publications

(5 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Technological improvements, particularly in the software used during the coding of dynamic eye-tracking data, will shorten the time-consuming process of data processing. Previous discourse has already highlighted opportunities presented by virtual-reality eye-tracking, machine-learning and automated categorisation of areas of interest (Uttley et al, 2018; Simpson, 2021). This would allow more data (in terms of number of participants and study streets) to be collected and analysed within a given time frame, which is a current limitation when seeking to undertake large-scale mobile eye-tracking studies in real-world settings.…”

Section: Discussionmentioning

confidence: 99%

Street edge subdivision: Structuring ground floor interfaces to stimulate pedestrian visual engagement

Simpson

Freeth

Simpson

et al. 2022

Environment and Planning B: Urban Analytics and City Science

Self Cite

View full text Add to dashboard Cite

There have been numerous attempts to identify what makes the ground floor interfaces of street edges engaging for pedestrians. Their subdivision has often been highlighted as important, predominantly, in line with functions along their length. However, the effect of subdivision on street edge engagement has not been empirically tested. We use mobile eye-tracking to systematically examine where and for how long pedestrians visually engage ground floors in relation to their subdivision. We consider three scales of subdivision: morphologically defined plinths (different building ground floors), territorially defined segments (different areas of territorial ownership) and spatially defined micro-segments (different spaces separated by pillars and partitions). Results show that segments dominate ground floor visual engagement, with micro-segments also having a significant influence. Plinths were shown to have no direct effect upon such engagement. We subsequently use these findings to show how subdivision should be approached by design decision-makers when seeking to actively encourage pedestrian engagement with ground floors along street edges.

show abstract

Section: Discussionmentioning

confidence: 99%

Street edge subdivision: Structuring ground floor interfaces to stimulate pedestrian visual engagement

Simpson

Freeth

Simpson

et al. 2022

Environment and Planning B: Urban Analytics and City Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…To lessen the burden of manual annotation, the authors recommended employing head-tracking technology alongside complex 3D environmental models. Simpson [28] studied gaze projection in outdoor settings using mobile eye-tracking, creating heat maps to represent the interaction of participants with their environment. The data were processed manually, which was time-consuming and error-prone.…”

Section: Examples Of Underutilized Potentials Of Eye-tracking Technologymentioning

confidence: 99%

MYFix: Automated Fixation Annotation of Eye-Tracking Videos

Alinaghi,

Hollendonner,

Giannopoulos

2024

Sensors

View full text Add to dashboard Cite

In mobile eye-tracking research, the automatic annotation of fixation points is an important yet difficult task, especially in varied and dynamic environments such as outdoor urban landscapes. This complexity is increased by the constant movement and dynamic nature of both the observer and their environment in urban spaces. This paper presents a novel approach that integrates the capabilities of two foundation models, YOLOv8 and Mask2Former, as a pipeline to automatically annotate fixation points without requiring additional training or fine-tuning. Our pipeline leverages YOLO’s extensive training on the MS COCO dataset for object detection and Mask2Former’s training on the Cityscapes dataset for semantic segmentation. This integration not only streamlines the annotation process but also improves accuracy and consistency, ensuring reliable annotations, even in complex scenes with multiple objects side by side or at different depths. Validation through two experiments showcases its efficiency, achieving 89.05% accuracy in a controlled data collection and 81.50% accuracy in a real-world outdoor wayfinding scenario. With an average runtime per frame of 1.61 ± 0.35 s, our approach stands as a robust solution for automatic fixation annotation.

show abstract

“…Kellaris and Machleit (2016), for example, published a full conceptual model of the marketing communications of signage. Other areas investigated include studies of where visual attention is focused on a sign using eye tracking (Simpson 2021), location issues in high traffic vs. low traffic areas (Hong and Issac 2021), image processing and the impact of missing information in signage (Sundar, Wu and Karda's (2019) and on-premise signs and their placement in enclosed shopping malls (Berger 2017). A recent study by Knuth, Behue and Huddleston also examined factors related to the effectiveness of retail display signs (Knuth, bee, and Huddleston 2020).…”

Section: Marketingmentioning

confidence: 99%