‘Big data’ for pedestrian volume: Exploring the use of Google Street View images for pedestrian counts

New sources of data such as ‘big data’ and computational analytics have stimulated innovative pedestrian oriented research. Current studies, however, are still limited and subjective with regard to the use of Google Street View and other online sources for environment audits or pedestrian counts because of the manual information extraction and compilation, especially for large areas. This study aims to provide future research an alternative method to conduct large scale data collection more consistently and objectively on pedestrian counts and possibly for environment audits and stimulate discussion of the use of ‘big data’ and recent computational advances for planning and design. We explore and report information needed to automatically download and assemble Google Street View images, as well as other image parameters for a wide range of analysis and visualization, and explore extracting pedestrian count data based on these images using machine vision and learning technology. The reliability tests results based on pedestrian information collected from over 200 street segments in Buffalo, NY, Washington, D.C., and Boston, MA respectively suggested that the image detection method used in this study are capable of determining the presence of pedestrian with a reasonable level of accuracy. The limitation and potential improvement of the proposed method is also discussed.

[1]  Li Yin,et al.  The impact of street network connectivity on pedestrian volume , 2015 .

[2]  Emily Talen,et al.  Measuring Walkability: A Note on Auditing Methods , 2014 .

[3]  Julien O. Teitler,et al.  Using Google Street View to audit neighborhood environments. , 2011, American journal of preventive medicine.

[4]  Celia Lury,et al.  Inventive methods : the happening of the social , 2012 .

[5]  Pietro Perona,et al.  Fast Feature Pyramids for Object Detection , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Yusak O. Susilo,et al.  Comparison of pedestrian trip generation models , 2013 .

[7]  Lucas J Carr,et al.  Validation of Walk Score for estimating access to walkable amenities , 2010, British Journal of Sports Medicine.

[8]  Ronan Collobert,et al.  Recurrent Convolutional Neural Networks for Scene Labeling , 2014, ICML.

[9]  S. Gortmaker,et al.  Validation of Walk Score® for Estimating Neighborhood Walkability: An Analysis of Four US Metropolitan Areas , 2011, International journal of environmental research and public health.

[10]  Leonard H. Epstein,et al.  Neighbourhood for Playing: Using GPS, GIS and Accelerometry to Delineate Areas within which Youth are Physically Active , 2013 .

[11]  J. M. Oakes,et al.  Design and Destinations: Factors Influencing Walking and Total Physical Activity , 2008 .

[12]  Sid C. H. Chu,et al.  When and Why Do People Walk in the City: The Influence of Urban Elements on Time-pattern of Pedestrian Movement , 2005 .

[13]  Bill Triggs,et al.  Histograms of oriented gradients for human detection , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[14]  Mohan M. Trivedi,et al.  Part-Based Pedestrian Detection and Feature-Based Tracking for Driver Assistance: Real-Time, Robust Algorithms, and Evaluation , 2013, IEEE Transactions on Intelligent Transportation Systems.

[15]  Li Yin,et al.  Book Review: Measuring Urban Design: Metrics for Livable Places , 2014 .

[16]  Pascal Vincent,et al.  Representation Learning: A Review and New Perspectives , 2012, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[17]  Camille Couprie,et al.  Learning Hierarchical Features for Scene Labeling , 2013, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Bernt Schiele,et al.  Ten Years of Pedestrian Detection, What Have We Learned? , 2014, ECCV Workshops.

[19]  Li Yin,et al.  Assessing Walkability in the City of Buffalo: Application of Agent-Based Simulation , 2013 .

[20]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[21]  B W Landis,et al.  Bicycle System Performance Measures: the Interaction Hazard and Latent Demand Score Models , 1996 .

[22]  D. Watts.  A twenty-first century science , 2007, Nature.

[23]  Daniel E. O'Leary,et al.  'Big Data', the 'Internet of Things' and the 'Internet of Signs' , 2013, Intell. Syst. Account. Finance Manag..

[24]  Andrew C. Gallagher,et al.  Understanding images of groups of people , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[25]  Tara N. Sainath,et al.  Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research Groups , 2012, IEEE Signal Processing Magazine.

[26]  J. Sallis,et al.  Many Pathways from Land Use to Health: Associations between Neighborhood Walkability and Active Transportation, Body Mass Index, and Air Quality , 2006 .

[27]  Ö. Özer,et al.  WALKING INITIATIVES : a quantitative movement analysis 017 , 2007 .

[28]  Reid Ewing,et al.  Creating and validating GIS measures of urban design for health research. , 2009, Journal of environmental psychology.

[29]  Jennifer Ailshire,et al.  Using Google Earth to conduct a neighborhood audit: reliability of a virtual audit instrument. , 2010, Health & place.

[30]  Daniel Arribas-Bel,et al.  Accidental, open and everywhere: Emerging data sources for the understanding of cities , 2014 .

[31]  Christian Früh,et al.  Google Street View: Capturing the World at Street Level , 2010, Computer.

[32]  Reid Ewing,et al.  Pedestrian- and Transit-Oriented Design , 2013 .

[33]  Reid Ewing,et al.  Measuring Urban Design: Metrics for Livable Places , 2013 .

[34]  Evelyn Ruppert,et al.  Rethinking empirical social sciences , 2013 .

[35]  Jeffrey S. Olson,et al.  Sketch-Plan Method for Estimating Pedestrian Traffic for Central Business Districts and Suburban Growth Corridors , 1997 .

[36]  Michael F. Goodchild,et al.  The quality of big (geo)data , 2013 .

[37]  Daniel A. Rodriguez,et al.  The development and testing of an audit for the pedestrian environment , 2007 .

[38]  Jae Seung Lee,et al.  Virtual and actual: relative accuracy of on-site and web-based instruments in auditing the environment for physical activity. , 2013, Health & place.

[39]  H. Badland,et al.  Can Virtual Streetscape Audits Reliably Replace Physical Streetscape Audits? , 2010, Journal of Urban Health.

[40]  David R. Ragland,et al.  Pilot Model for Estimating Pedestrian Intersection Crossing Volumes , 2009 .