StreetScore: Predicting the Perceived Safety of One Million Streetscapes

Using a computer

#Data

Sat, Jul 26th, 2014 21:00 by capnasty NEWS

Using a computational model, the StreetScore website lets you pick a location on a map and show off just how safe it would be perceived by a person. More information on the paper here (PDF).

StreetScore is an algorithm that assigns a score to a street view based on how safe it looks to a human — but using a computer (see FAQ). This website is a collection of map visualizations of perceived safety of street views from cities in the US as predicted by StreetScore. We will be releasing a map of perceived safety for a new city each week. The StreetScore algorithm was created by Nikhil Naik as part of a collaboration between the Macro Connections group and the Camera Culture group at MIT Media Lab. Jade Philipoom created the visualizations presented in the StreetScore website.

  900

 

You may also be interested in:

Public Domain Super Heroes
Skatepath: Visualizing Covered Distances by Skating in Vienna
Country Population, Density & Area
Machine Learning Helps Us Understand What Makes a Good Teacher
If the World's Population Lived in One City...