Predicting bicycling and walking traffic using street view imagery and destination data

被引:42
|
作者
Hankey, Steve [1 ]
Zhang, Wenwen [2 ]
Le, Huyen T. K. [3 ]
Hystad, Perry [4 ]
James, Peter [5 ,6 ,7 ]
机构
[1] Virginia Tech, Sch Publ & Int Affairs, 140 Otey St, Blacksburg, VA 24061 USA
[2] Rutgers State Univ, Edward J Bloustein Sch Planning & Publ Policy, 33 Livingston Ave, New Brunswick, NJ 08901 USA
[3] Ohio State Univ, Dept Geog, 154 N Oval Mall, Columbus, OH 43210 USA
[4] Oregon State Univ, Coll Publ Hlth & Human Sci, 2520 Campus Way, Corvallis, OR 97331 USA
[5] Harvard Med Sch, Dept Populat Med, 401 Pk Dr, Boston, MA 02215 USA
[6] Harvard Pilgrim Hlth Care Inst, 401 Pk Dr, Boston, MA 02215 USA
[7] Harvard TH Chan Sch Publ Hlth, Dept Environm Hlth, 677 Huntington Ave, Boston, MA 02115 USA
关键词
Physical activity; Activity space; Direct-demand model; Non-motorized transport; BUILT-ENVIRONMENT; HEALTH-BENEFITS; GREEN SPACES; TRAVEL; MODELS; NEIGHBORHOODS; TRANSPORT; IMPACT; TRIPS; FORM;
D O I
10.1016/j.trd.2020.102651
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Few studies predict spatial patterns of bicycling and walking across multiple cities using street level data. This study aims to model bicycle and pedestrian traffic at 4145 count locations across 20 U.S. cities using new micro-scale variables: (1) destinations from Google Point of Interest data (e.g., restaurants, schools) and (2) pixel classification from Google Street View imagery (e.g., sidewalks, trees, streetlights). We applied machine learning algorithms to assess how well street-level variables predict bicycling and walking rates. Adding street-level variables improved out-of-sample prediction accuracy of bicycling and walking activities. We also found that street-level variables (10-fold CV R-2: 0.82-0.88) may be a useful alternative to Census data (0.85-0.88). Macro-scale factors (e.g., zoning) captured by Census data and micro-scale factors (e. g., streetscapes) captured in our street-level data are both useful for predicting active travel. Our models provide a new tool for estimating and understanding the spatial patterns of active travel.
引用
收藏
页数:10
相关论文
共 50 条
  • [41] Analyzing the effects of Green View Index of neighborhood streets on walking time using Google Street View and deep learning
    Ki, Donghwan
    Lee, Sugie
    LANDSCAPE AND URBAN PLANNING, 2021, 205
  • [42] City-Scale Mapping of Urban Facade Color Using Street-View Imagery
    Zhong, Teng
    Ye, Cheng
    Wang, Zian
    Tang, Guoan
    Zhang, Wei
    Ye, Yu
    REMOTE SENSING, 2021, 13 (08)
  • [43] A review of urban physical environment sensing using street view imagery in public health studies
    Kang, Yuhao
    Zhang, Fan
    Gao, Song
    Lin, Hui
    Liu, Yu
    ANNALS OF GIS, 2020, 26 (03) : 261 - 275
  • [44] Assessment of solar photovoltaic potentials on urban noise barriers using street-view imagery
    Zhong, Teng
    Zhang, Kai
    Chen, Min
    Wang, Yijie
    Zhu, Rui
    Zhang, Zhixin
    Zhou, Zixuan
    Qian, Zhen
    Lv, Guonian
    Yan, Jinyue
    RENEWABLE ENERGY, 2021, 168 : 181 - 194
  • [45] Using Deep Learning and Google Street View Imagery to Assess and Improve Cyclist Safety in London
    Rita, Luis
    Peliteiro, Miguel
    Bostan, Tudor-Codrin
    Tamagusko, Tiago
    Ferreira, Adelino
    SUSTAINABILITY, 2023, 15 (13)
  • [46] Examining the relationship between active transport and exposure to streetscape diversity during travel: A study using GPS data and street view imagery
    Zhou, Hanlin
    Wang, Jue
    Widener, Michael
    Wilson, Kathi
    COMPUTERS ENVIRONMENT AND URBAN SYSTEMS, 2024, 110
  • [47] Assessing Climate Disaster Vulnerability in Peru and Colombia Using Street View Imagery: A Pilot Study
    Wang, Chaofeng
    Antos, Sarah E.
    Gosling-Goldsmith, Jessica G.
    Triveno, Luis M.
    Zhu, Chunwu
    von Meding, Jason
    Ye, Xinyue
    BUILDINGS, 2024, 14 (01)
  • [48] Evaluation of Street Space Renovation in Historic Areas Using Deep Learning Based on Street View Imagery in the Human Visual Field
    Zhu Xiaotong
    Bai Mei
    Bai Yuxin
    Li Min
    China City Planning Review, 2024, 33 (04) : 25 - 34
  • [49] SENSING STREETS: EXPLORING THE ASSOCIATION BETWEEN CITYSCAPE QUALITIES AND STREET PERCEPTIONS USING STREET VIEW IMAGERY AND NATURAL LANGUAGE PROCESSING
    Cheng, Sifan
    Van Ameijde, Jeroen
    PROCEEDINGS OF THE 29TH INTERNATIONAL CONFERENCE OF THE ASSOCIATION FOR COMPUTER-AIDED ARCHITECTURAL DESIGN RESEARCH IN ASIA, CAADRIA 2024, VOL 2, 2024, : 139 - 148
  • [50] Urban perception by using eye movement data on street view images
    Yang, Nai
    Deng, Zhitao
    Hu, Fangtai
    Chao, Yi
    Wan, Lin
    Guan, Qingfeng
    Wei, Zhiwei
    TRANSACTIONS IN GIS, 2024, 28 (05) : 1021 - 1042