TY - JOUR
T1 - Evaluating simulated visible greenness in urban landscapes
T2 - An examination of a midsize U.S. city
AU - Yan, Jingjing
AU - Naghedi, Reza
AU - Huang, Xiao
AU - Wang, Siqin
AU - Lu, Junyu
AU - Xu, Yang
N1 - Publisher Copyright: © 2023 Elsevier GmbH
PY - 2023/9
Y1 - 2023/9
N2 - Urban greenness is critical in evaluating urban environmental and living conditions, significantly affecting human well-being and house prices. Unfortunately, satellite imagery from a bird-eye view does not fully capture urban greenness from a human-centered perspective, while human-perceived greenness from street-view images heavily relies on road networks and vehicle accessibility. In recent years, scholars started to explore greenness measurements from a simulative perspective, among which the simulation of the Viewshed Greenness Visibility Index (VGVI) received wide attention. However, the simulated VGVI lacks a comprehensive assessment. To fill this gap, we designed a field experiment in Fayetteville, Arkansas, by collecting 360-degree panoramas in different local climate zones. Further, we segmented these panoramas via the state-of-the-art DeeplabV2 neural network to obtain the Panoramic Greenness Visibility Index (PGVI), which served as the ground-truthing human-perceived greenness. We assessed the performance of VGVI by comparing it with PGVI calculated from field-collected panoramas. The results showed that, despite the disparity of performance in different local climate zones, VGVI highly correlates to the PGVI, indicating its great potential for various domains that favor urban human-perceived greenness exposure.
AB - Urban greenness is critical in evaluating urban environmental and living conditions, significantly affecting human well-being and house prices. Unfortunately, satellite imagery from a bird-eye view does not fully capture urban greenness from a human-centered perspective, while human-perceived greenness from street-view images heavily relies on road networks and vehicle accessibility. In recent years, scholars started to explore greenness measurements from a simulative perspective, among which the simulation of the Viewshed Greenness Visibility Index (VGVI) received wide attention. However, the simulated VGVI lacks a comprehensive assessment. To fill this gap, we designed a field experiment in Fayetteville, Arkansas, by collecting 360-degree panoramas in different local climate zones. Further, we segmented these panoramas via the state-of-the-art DeeplabV2 neural network to obtain the Panoramic Greenness Visibility Index (PGVI), which served as the ground-truthing human-perceived greenness. We assessed the performance of VGVI by comparing it with PGVI calculated from field-collected panoramas. The results showed that, despite the disparity of performance in different local climate zones, VGVI highly correlates to the PGVI, indicating its great potential for various domains that favor urban human-perceived greenness exposure.
KW - 360-degree panoramas
KW - 3D urban analysis
KW - DeeplabV2 neural network
KW - Green space
KW - Visible greenness
UR - http://www.scopus.com/inward/record.url?scp=85167814722&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85167814722&partnerID=8YFLogxK
U2 - 10.1016/j.ufug.2023.128060
DO - 10.1016/j.ufug.2023.128060
M3 - Article
SN - 1618-8667
VL - 87
JO - Urban Forestry and Urban Greening
JF - Urban Forestry and Urban Greening
M1 - 128060
ER -