Assessing bikeability with street view imagery and computer vision

@article{Ito2021AssessingBW,
  title={Assessing bikeability with street view imagery and computer vision},
  author={Koichi Ito and Filip Biljecki},
  journal={ArXiv},
  year={2021},
  volume={abs/2105.08499}
}
Associations between Street-View Perceptions and Housing Prices: Subjective vs. Objective Measures Using Computer Vision and Machine Learning Techniques
This study investigated the extent to which subjectively and objectively measured street-level perceptions complement or conflict with each other in explaining property value. Street-scene
How does street space influence crash frequency? An analysis using segmented street view imagery
TLDR
It is found that an Open Road type of metropolitan street space, characterized by more visible sky, roadway, and signage are associated with the greatest increase in crashes, and that the majority of these spaces exist on arterial or collector class road segments.
Predicting the impact of urban change in pedestrian and road safety
TLDR
By considering historical accident data and Street View images, this paper details how to automatically predict the impact (increase or decrease) of urban interventions on accident incidence, and provides an interpretability analysis to unveil which specific categories of urban features impact accident rates positively or negatively.
3D building reconstruction from single street view images using deep learning
Global Building Morphology Indicators

References

SHOWING 1-10 OF 155 REFERENCES
Subjectively Measured Streetscape Perceptions to Inform Urban Design Strategies for Shanghai
TLDR
This work integrated crowdsourcing, CV, and machine learning to subjectively measure four important perceptions suggested by classical urban design theory and found a strong correlation between the predicted complexity score and the density of urban amenities and services points of interest (POI), which validates the effectiveness of subjective measures.
Developing a street level walkability index in the Philippines using 3D photogrammetry modeling from drone surveys
Walking behavior is influenced by both objective and subjective aspects of the built environment at the macro and micro scales. Most walkability studies focused on objective macro or mesoscale
Street view imagery in urban analytics and GIS: A review
Deep Learning for Automatically Detecting Sidewalk Accessibility Problems Using Streetscape Imagery
TLDR
This paper investigates two application areas: automatically validating crowdsourced labels and automatically labeling sidewalk accessibility issues and introduces and uses a residual neural network modified to support both image and non-image (contextual) features (e.g., geography).
Decoding urban landscapes: Google street view and measurement sensitivity
A Feasibility Study of Using Google Street View and Computer Vision to Track the Evolution of Urban Accessibility
TLDR
A three-stage classification framework is introduced using Google Street View's "time machine" feature to track the evolution of urban accessibility over time, manually labeling accessibility problems in one time period and classifying the labeled image patch into one of five accessibility categories.
Mapping Bikeability: A Spatial Tool to Support Sustainable Travel
TLDR
The overall bikeability score and its five component scores can guide local action to stimulate changes in cycling rates, and uses widely available data types, thus facilitating easy application in other cities.
Estimating city-level travel patterns using street imagery: A case study of using Google Street View in Britain
TLDR
A novel application, using Google Street View (GSV) to predict travel patterns at the city level, finding high correlations between GSV counts of cyclists (‘GSV-cyclists’) and cycle commute mode share and all outcomes were predicted well, except past-month walking.
The world’s user-generated road map is more than 80% complete
TLDR
Two complementary, independent methods are used to assess the completeness of OSM road data in each country in the world and find that globally, OSM is ∼83% complete, and more than 40% of countries—including several in the developing world—have a fully mapped street network.
...
...