Neighborhood safety and its perception are important determinants of citizens’ health and well-beingWell-being. Contemporary urban design guidelines often advocate urban forms that encourage natural surveillanceNatural surveillanceor “eyes on the streetEyes on the street” to promote community safety. However, assessing a neighborhood’s level of natural surveillance is challenging due to its subjective nature and a lack of relevant data. We propose a method for measuring natural surveillance at scale by employing a combination of street-level imageryStreet-level imageryand computer visionComputer vision techniques. We detect windows on building facades and calculate sightlinesSightlines from the street level and surrounding buildings across forty neighborhoods in Amsterdam, the Netherlands. By correlating our measurements with the city’s Safety Index, we also validate how our method can be used as an estimator of neighborhood safety. We show how perceived safetyPerceived safety varies with window level and building distance from the street, and we find a non-linear relationship between natural surveillanceNatural surveillance and (perceived) safety.
“Eyes on the Street”: Estimating Natural Surveillance Along Amsterdam’s City Streets Using Street-Level Imagery
The Urban Book Series
International Conference on Computers in Urban Planning and Urban Management ; 2023 ; Montreal, QC, Canada June 20, 2023 - June 22, 2023
2023-06-02
15 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Street railway track construction in paved streets
Engineering Index Backfile | 1916
|Witkar: Amsterdam's self-drive hire city car
Online Contents | 1976
|