國立高雄大學圖資館 |

Language: English

Back

Towards Evidence-Based Urban Perception Analytics: Integrating Eye-Tracking and AI-Powered Heatmaps for Pedestrian-Centered Urban Quality Assessment  /

Record Type:	Electronic resources : Monograph/item
Title/Author:	Towards Evidence-Based Urban Perception Analytics: Integrating Eye-Tracking and AI-Powered Heatmaps for Pedestrian-Centered Urban Quality Assessment /Mahzerin Sultana.
Author:	Sultana, Mahzerin,
Description:	1 electronic resource (94 pages)
Notes:	Source: Masters Abstracts International, Volume: 87-03.
Notes:	Advisors: Chowdhury, Shuva Committee members: Gokaraju, Balakrishna; Pandey, Venktesh; Tesiero, Raymond C.
Contained By:	Masters Abstracts International87-03.
Subject:	Urban planning.
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32166223
ISBN:	9798293884049

Towards Evidence-Based Urban Perception Analytics: Integrating Eye-Tracking and AI-Powered Heatmaps for Pedestrian-Centered Urban Quality Assessment  /
Sultana, Mahzerin,

Towards Evidence-Based Urban Perception Analytics: Integrating Eye-Tracking and AI-Powered Heatmaps for Pedestrian-Centered Urban Quality Assessment  /Mahzerin Sultana. - 1 electronic resource (94 pages)

Source: Masters Abstracts International, Volume: 87-03.

Urban design often underrepresents how pedestrians perceive and visually engage with their surroundings. This study introduces an evidence-based methodological framework that integrates real-world eye-tracking data with AI-powered semantic segmentation to assess visual attention in urban streetscapes. Gaze behavior was recorded using wearable eye-trackers along pedestrian routes in a mid-density American city and categorized into seven Area of Interest (AOI) classes representing key urban elements such as roads, vegetation, buildings, vehicles, and sky. Gaze-based metrics including fixation duration, visit frequency, and pupil diameter-were normalized and weighted to compute a composite Urban Attention Index (UAI), quantifying perceptual engagement across AOI classes. A complementary Urban Quality Index (UQI) was developed based on pixel-level AOI area distributions and weighted spatial attributes such as greenness, walkability, and enclosure, offering an objective measure of environmental quality.The relationship between UAI and UQI was analyzed to reveal mismatches between perceived attention and spatial merit such as visually dominant yet low-quality zones, or high-quality areas that receive limited attention. These findings were operationalized through an interactive, AI-based evaluation tool, which enables designers, planners, and researchers to simulate, visualize, and compare human attention with urban spatial quality in a systematic, data-driven manner. Unlike traditional perceptual surveys or purely spatial analyses, this framework quantifies subconscious visual engagement and juxtaposes it with spatial quality indicators, highlighting discrepancies between design intentions and human experience.The proposed framework, implemented through an interactive, user-friendly platform, enables even non-experts to generate semantic segmentations, heatmaps, and insights for any street-level urban image. The empirical findings illustrate perceptual engagement patterns: ground-level surfaces, construction, and natural features attract higher attention, while sky, objects, and human figures tend to be peripheral. By bridging the gap between human perceptual behavior and spatial form, this approach advances both theory and practice in urban design. It establishes perceptual salience as a measurable and actionable design variable, empowering designers and decision-makers to create public spaces that more accurately reflect actual user experience and support responsive, data-informed interventions.

English

ISBN: 9798293884049Subjects--Topical Terms:

795489
Urban planning.
Subjects--Index Terms:

Eye-tracking data

Towards Evidence-Based Urban Perception Analytics: Integrating Eye-Tracking and AI-Powered Heatmaps for Pedestrian-Centered Urban Quality Assessment  /
LDR:04169nmm a22004453i 4500 001 693740
005 20260511063018.5
006 m o d
007 cr|nu||||||||
008 260819s2025 miu||||||m |||||||eng d
020 $a 9798293884049
035 $a (MiAaPQD)AAI32166223
035 $a AAI32166223
040 $a MiAaPQD $b eng $c MiAaPQD $e rda
100 1 $a Sultana, Mahzerin, $e author. $3 1010392
245 1 0 $a Towards Evidence-Based Urban Perception Analytics: Integrating Eye-Tracking and AI-Powered Heatmaps for Pedestrian-Centered Urban Quality Assessment  / $c Mahzerin Sultana.
264 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2025
300 $a 1 electronic resource (94 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 87-03.
500 $a Advisors: Chowdhury, Shuva Committee members: Gokaraju, Balakrishna; Pandey, Venktesh; Tesiero, Raymond C.
502 $b M.S. $c North Carolina Agricultural and Technical State University $d 2025.
520 $a Urban design often underrepresents how pedestrians perceive and visually engage with their surroundings. This study introduces an evidence-based methodological framework that integrates real-world eye-tracking data with AI-powered semantic segmentation to assess visual attention in urban streetscapes. Gaze behavior was recorded using wearable eye-trackers along pedestrian routes in a mid-density American city and categorized into seven Area of Interest (AOI) classes representing key urban elements such as roads, vegetation, buildings, vehicles, and sky. Gaze-based metrics including fixation duration, visit frequency, and pupil diameter-were normalized and weighted to compute a composite Urban Attention Index (UAI), quantifying perceptual engagement across AOI classes. A complementary Urban Quality Index (UQI) was developed based on pixel-level AOI area distributions and weighted spatial attributes such as greenness, walkability, and enclosure, offering an objective measure of environmental quality.The relationship between UAI and UQI was analyzed to reveal mismatches between perceived attention and spatial merit such as visually dominant yet low-quality zones, or high-quality areas that receive limited attention. These findings were operationalized through an interactive, AI-based evaluation tool, which enables designers, planners, and researchers to simulate, visualize, and compare human attention with urban spatial quality in a systematic, data-driven manner. Unlike traditional perceptual surveys or purely spatial analyses, this framework quantifies subconscious visual engagement and juxtaposes it with spatial quality indicators, highlighting discrepancies between design intentions and human experience.The proposed framework, implemented through an interactive, user-friendly platform, enables even non-experts to generate semantic segmentations, heatmaps, and insights for any street-level urban image. The empirical findings illustrate perceptual engagement patterns: ground-level surfaces, construction, and natural features attract higher attention, while sky, objects, and human figures tend to be peripheral. By bridging the gap between human perceptual behavior and spatial form, this approach advances both theory and practice in urban design. It establishes perceptual salience as a measurable and actionable design variable, empowering designers and decision-makers to create public spaces that more accurately reflect actual user experience and support responsive, data-informed interventions.
546 $a English
590 $a School code: 1544
650 4 $a Urban planning. $3 795489
653 $a Eye-tracking data
653 $a Human centered design
653 $a Urban perception
653 $a Urban quality assessment
653 $a Visual attention
690 $a 0543
690 $a 0729
690 $a 0999
690 $a 0800
710 2 $a North Carolina Agricultural and Technical State University. $b Civil Engineering. $e degree granting institution. $3 1010393
720 1 $a Chowdhury, Shuva $e degree supervisor.
773 0 $t Masters Abstracts International $g 87-03.
790 $a 1544
791 $a M.S.
792 $a 2025
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=32166223