Abstract
Objectives
Crime diversity is a measure of the variety of criminal offenses in a local environment, similar to ecological diversity. While crime diversity distributions have been explained via neutral models, to date the environmental and social mechanisms behind crime diversity have not been investigated. Building on recent work demonstrating that crime rates can be inferred from street level imagery with neural network computer vision models, in this paper we consider the task of inferring crime diversity through street level imagery.
Methods
We use the Google Vision API, a deep learning image tagging service, to extract objects from sampled Google Street View (GSV) images in each census block of Los Angeles. For each census block we then compute indices for (1) object diversity, (2) diversity related to commonly employed census variables, and (3) crime diversity from reports provided by the Los Angeles Police Department. We then build ordinary least squares and geographically weighted regression models to explain crime diversity as a function of environmental diversity, population diversity, and population size.
Results
We show that crime diversity arises via a combination of environmental diversity (as measured through street view object diversity), household diversity (as measured through the census), and population size. Population size and area of the census block both lend credence to the neutral model proposed by Brantingham for crime diversity. However, environmental and demographic diversity combined play an equally important role in explaining variation in crime diversity.
Conclusions
Our study has two primary implications for research on crime and place. First, Google Street View (via the Google Vision API) can provide important, cost-effective empirical insights to best understand distinct geographic environments of crime. Second, environmental diversity, as measured by image tagging in GSV, was observed to be more predictive of crime diversity (variety of crime types) than commonly used census measures.
Similar content being viewed by others
References
Anselin L (2009) Spatial regression. SAGE Handbook Spatial Anal 1:255–276
Badland HM, Opit S, Witten K, Kearns RA, Mavoa S (2010) Can virtual streetscape audits reliably replace physical streetscape audits? J Urban Health 87(6):1007–1016
Ben-Joseph E, Lee JS, Cromley EK, Laden F, Troped PJ (2013) Virtual and actual: relative accuracy of on-site and web-based instruments in auditing the environment for physical activity. Health Place 19:138–150
Bernasco W (2008) Them again? same-offender involvement in repeat and near repeat burglaries. Europ J Criminol 5(4):411–431
Bivand R, Yu D, Nakaya T, Garcia-Lopez M-A, Bivand MR (2017) Package spgwr, R software package
Bloch S. An on-the-ground challenge to uses of spatial big data in assessing neighborhood character, Geographical Review
Boessen A, Hipp JR (2015) Close-ups and the scale of ecology: land uses and the geography of social context and crime. Criminology 53(3):399–426
Bowers KJ, Johnson SD (2004) Who commits near repeats? a test of the boost explanation. Western Criminol Rev 5:3
Bowers KJ, Johnson SD (2005) Domestic burglary repeats and space-time clusters: the dimensions of risk. Europ J Criminol 2(1):67–92
Braga AA, Clarke RV (2014) Explaining high-risk concentrations of crime in the city: social disorganization, crime opportunities, and important next steps. J Res Crime Delinquency 51(4):480–498
Braga AA, Weisburd D (2010) Policing problem places: crime hot spots and effective prevention. Oxford University Press, Oxford
Braga AA, Papachristos AV, Hureau DM (2014) The effects of hot spots policing on crime: an updated systematic review and meta-analysis. Justice Quarterly 31(4):633–663
Brantingham PJ (2016) Crime diversity. Criminology 54(4):553–586
Brantingham PJ, Brantingham PL et al (1981) Environmental criminology. Sage Publications, Beverly Hills
Brantingham PL, Brantingham PJ (1993) Environment, routine and situation: toward a pattern theory of crime. Adv Criminol Theory 5(2):259–94
Brantingham P, Brantingham P (1995) Criminality of place. Europ J Crim Policy Res 3(3):5–26
Brantingham P, Brantingham P (2013) Crime pattern theory, in Environmental criminology and crime analysis. Willan, pp 100–116
Bursik RJ Jr, Grasmick HG et al (1999) Neighborhoods & crime. Lexington Books
Campbell A, Both A, Sun QC (2019) Detecting and mapping traffic signs from google street view images using deep learning and gis. Comput Environ Urban Syst 77:101350
Caplan JM, Kennedy LW, Miller J (2011) Risk terrain modeling: brokering criminological theory and gis methods for crime forecasting. Justice Quarterly 28(2):360–381
Charreire H, Mackenbach JD, Ouasti M, Lakerveld J, Compernolle S, Ben-Rebah M, McKee M, Brug J, Rutter H, Oppert J-M (2014) Using remote sensing to define environmental characteristics related to physical activity and dietary behaviours: a systematic review (the spotlight project). Health Place 25:1–9
Clarke RV (1995) Situational crime prevention. Crime Justice 19:91–150
Clarke RVG (1997) Situational crime prevention. Criminal Justice Press, Monsey
Clarke RV, Cornish DB (1985) Modeling offenders’ decisions: a framework for research and policy. Crime Justice 6:147–185
Clarke P, Ailshire J, Melendez R, Bader M, Morenoff J (2010) Using google earth to conduct a neighborhood audit: reliability of a virtual audit instrument. Health Place 16(6):1224–1229
Clarke R, Eck JE (2014) Become a problem-solving crime analyst. Willan
Cloward RA, Ohlin LE (2013) Delinquency and opportunity: a study of delinquent gangs. Routledge, Milton Park
Cohen LE, Felson M (1979) Social change and crime rate trends: a routine activity approach. American sociological review, pp 588–608
Cornish DB, Clarke RV (1986) The reasoning criminal: rational choice perspectives on offending. Transaction Publishers
Eck JE (1995) A general model of the geography of illicit retail marketplaces. Crime Place 4:67–93
Eck J, Weisburd DL (2015) Crime places in crime theory, Crime and place: Crime prevention studies, vol 4
Felson M (2006) Crime and nature. Sage, Thousand Oaks
Graif C, Sampson RJ (2009) Spatial heterogeneity in the effects of immigration and diversity on neighborhood homicide rates. Homicide Stud 13(3):242–260
Groff ER, Weisburd D, Yang S-M (2010) Is it important to examine crime trends at a local micro level?: a longitudinal analysis of street to street variability in crime trajectories. J Quantitat Criminol 26(1):7–32
Haberman CP (2017) Overlapping hot spots? examination of the spatial heterogeneity of hot spots of different crime types. Criminol Public Policy 16(2):633–660
Harrell FE Jr (2015) Regression modeling strategies: with applications to linear models, logistic and ordinal regression, and survival analysis. Springer, Berlin
He L, Páez A, Liu D (2017) Built environment and violent crime: an environmental audit approach using google street view. Comput Environ Urban Syst 66:83–95
Jean PKS (2008) Pockets of crime: broken windows, collective efficacy, and the criminal point of view. University of Chicago Press, Chicago
Johnson SD (2010) A brief history of the analysis of crime concentration. Europ J Appl Math 21(4–5):349–370
Jones RW, Pridemore WA (2019) Toward an integrated multilevel theory of crime at place: Routine activities, social disorganization, and the law of crime concentration. J Quantitat Criminol 35(3):543–572
Keizer K, Lindenberg S, Steg L (2008) The spreading of disorder. Science 322(5908):1681–1685
Kelly CM, Wilson JS, Baker EA, Miller DK, Schootman M (2012) Using google street view to audit the built environment: inter-rater reliability results. Ann Behav Med 45(1):S108–S112
Kennedy LW, Caplan JM, Piza E (2011) Risk clusters, hotspots, and spatial intelligence: risk terrain modeling as an algorithm for police resource allocation strategies. J Quantitat Criminol 27(3):339–362
Kindynis T (2014) Ripping up the map: criminology and cartography reconsidered. British J Criminol 54(2):222–243
Kinney JB, Brantingham PL, Wuschke K, Kirk MG, Brantingham PJ (2008) Crime attractors, generators and detractors: land use and urban crime opportunities. Built Environ 34(1):62–74
Koper CS (1995) Just enough police presence: reducing crime and disorderly behavior by optimizing patrol time in crime hot spots. Justice Quarterly 12(4):649–672
Kuang D, Brantingham PJ, Bertozzi AL (2017) Crime topic modeling. Crime Sci 6(1):12
Kubrin CE, Weitzer R (2003) New directions in social disorganization theory. J Res Crime Delinquency 40(4):374–402
Langton SH, Steenbeek W (2017) Residential burglary target selection: an analysis at the property-level using google street view. Appl Geogr 86:292–299
Lantz B, Ruback RB (2017) A networked boost: burglary co-offending and repeat victimization using a network approach. Crime Delinquency 63(9):1066–1090
Lentz TS (2018) Crime diversity: reexamining crime richness across spatial scales. J Contemp Criminal Justice 34(3):312–335
Lopes DPF, Neves AJ. A practical study about the google vision api
Lowenkamp CT, Cullen FT, Pratt TC (2003) Replicating sampson and groves’s test of social disorganization theory: revisiting a criminological classic. J Res Crime Delinquency 40(4):351–373
Malm A, Pollard N, Brantingham P, Tinsley P, Plecas D, Brantingham P, Cohen I, Kinney B (2005) A 30 year analysis of police service delivery and costing. Int Centre Urban Res Stud (ICURS)
OBrien DT (2018) The action is everywhere, but greater at more localized spatial scales: Comparing concentrations of crime across addresses, streets, and neighborhoods. J Res Crime Delinquency, p 0022427818806040
Odgers CL, Caspi A, Bates CJ, Sampson RJ, Moffitt TE (2012) Systematic social observation of children’s neighborhoods using google street view: a reliable and cost-effective method. J Child Psychol Psychiatry 53(10):1009–1017
Osgood DW, Schreck CJ (2007) A new method for studying the extent, stability, and predictors of individual specialization in violence. Criminology 45(2):273–312
Palmer EJ, Holmes A, Hollin CR (2002) Investigating burglars’ decisions: factors influencing target choice, method of entry, reasons for offending, repeat victimisation of a property and victim awareness. Security J 15(1):7–18
Park RE, Burgess EW, McKenzie R (1925) The growth of the city: an introduction to a research project, The city, pp 47–62
Piquero A, Oster RP, Mazerolle P, Brame R, Dean CW (1999) Onset age and offense specialization. J Res Crime Delinquency 36(3):275–299
Piza EL, Carter JG (2018) Predicting initiator and near repeat events in spatiotemporal crime patterns: an analysis of residential burglary and motor vehicle theft. Justice Quarterly 35(5):842–870
Pratt TC, Cullen FT (2005) Assessing macro-level predictors and theories of crime: a meta-analysis. Crime Justice 32:373–450
Quick M, Li G, Brunton-Smith I (2018) Crime-general and crime-specific spatial patterns: a multivariate spatial analysis of four crime types at the small-area scale. J Criminal Justice 58:22–32
Ratcliffe JH, Taniguchi T, Groff ER, Wood JD (2011) The philadelphia foot patrol experiment: a randomized controlled trial of police patrol effectiveness in violent crime hotspots. Criminology 49(3):795–831
Rong X (2014) word2vec parameter learning explained. arXiv:1411.2738
Rundle AG, Bader MD, Richards CA, Neckerman KM, Teitler JO (2011) Using google street view to audit neighborhood environments. Am J Prevent Med 40(1):94–100
Sampson RJ (2013) The place of context: a theory and strategy for criminology’s hard problems. Criminology 51(1):1–31
Sampson RJ, Groves WB (1989) Community structure and crime: testing social-disorganization theory. Am J Sociol 94(4):774–802
Sampson RJ, Raudenbush SW, Earls F (1997) Neighborhoods and violent crime: a multilevel study of collective efficacy. Science 277(5328):918–924
Schreck CJ, McGloin JM, Kirk DS (2009) On the origins of the violent neighborhood: a study of the nature and predictors of crime-type differentiation across chicago neighborhoods. Justice Quarterly 26(4):771–794
Shannon CE (1948) A mathematical theory of communication. Bell Syst Tech J 27(3):379–423
Sharkey P, Torrats-Espinosa G, Takyar D (2017) Community and the crime decline: the causal effect of local nonprofits on violent crime. Am Sociol Rev 82(6):1214–1240
Shaw CR, McKay HD (1942) Juvenile Delinquency and urban areas: a study of rates in relation to differential characteristics of local communities in American life. University of Chicago Press, Chicago
Short MB, Dorsogna MR, Brantingham PJ, Tita GE (2009) Measuring and modeling repeat and near-repeat burglary effects. J Quantitat Criminol 25(3):325–339
Smith MJ (2003) Exploring target attractiveness in vandalism: an experimental approach. Crime Prevent Stud 16:197–236
Stucky TD, Ottensmann JR (2009) Land use and violent crime. Criminology 47(4):1223–1264
Sytsma VA, Piza EL (2018) Script analysis of open-air drug selling: a systematic social observation of cctv footage. J Res Crime Delinquency 55(1):78–102
Taylor RB (2015) Community criminology: Fundamentals of spatial and temporal scaling, ecological indicators, and selectivity bias. NYU Press
Taylor RB, Gottfredson S (1986) Environmental design, crime, and prevention: an examination of community dynamics. Crime Justice 8:387–416
Taylor BT, Fernando P, Bauman AE, Williamson A, Craig JC, Redman S (2011) Measuring the quality of public open space using google earth. Am J Prevent Med 40(2):105–112
Thomas WI, Znaniecki F (1918) The polish peasant in Europe and America: monograph of an immigrant group, vol 2. University of Chicago Press, Chicago
Thrasher FM (1927) The gang: a study of 1313 gangs in Chicago. University of Chicago Press, Chicago
Townsley M, Homel R, Chaseling J (2003) Infectious burglaries a test of the near repeat hypothesis. Br. J. Criminol. 43(3):615–633
Vandeviver C (2014) Applying google maps and google street view in criminological research. Crime Sci 3(1):13
Vandeviver C, Bernasco W (2019) location, location, location: Effects of neighborhood and house attributes on burglars target selection. J Quantitat Criminol, pp 1–43
Veysey BM, Messner SF (1999) Further testing of social disorganization theory: an elaboration of sampson and groves’s community structure and crime. J Res Crime Delinquency 36(2):156–174
Warner BD (2003) The role of attenuated culture in social disorganization theory. Criminology 41(1):73–98
Weisburd D (2015) The law of crime concentration and the criminology of place. Criminology 53(2):133–157
Weisburd D, Maher L, Sherman L, Buerger M, Cohn E, Petrisino A et al (1992) Contrasting crime general and crime specific theory: the case of hot spots of crime. Adv Criminol Theory 4(1):45–69
Welsh BC, Farrington DP (2004) Surveillance for crime prevention in public space: results and policy choices in britain and america. Criminol Public Policy 3(3):497–526
Willits DW, Makin DA (2018) Show me what happened: analyzing use of force through analysis of body-worn camera footage. J Res Crime Delinquency 55(1):51–77
Wilson JQ, Kelling GL (1982) Broken windows. Atlantic monthly 249(3):29–38
Wright RT, Decker SH (1996) Burglars on the job: Streetlife and residential break-ins. UPNE
Wright R, Logie RH, Decker SH (1995) Criminal expertise and offender decision making: an experimental study of the target selection process in residential burglary. J Res Crime Delinquency 32(1):39–53
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Handling Synonyms in GSV Object Detection
Appendix: Handling Synonyms in GSV Object Detection
Here we explore the sensitivity of the diversity index with regards to expanding or collapsing GSV categories. Though some image tags may appear to be synonyms, many are in fact distinct and provide a richer understanding of what is contained within a given image. For example, a family home and apartment are clearly different, so too are row houses that are physically connected as compared to standalone single family homes. While these may indeed be homes or residences that could be combined into a single category, they are unique from one another and may have implications for how offending environments are interpreted. We queried a sample of images with similar tags (or potential synonyms) and reviewed these images in an attempt to decipher differences. For example, it appears yard tends to be the backyard of a residence whereas lawn is the front lawn. Certainly these may be synonymous, but they speak to the view of a given location and how an offender may interpret. Other examples include fence which appear to be metal or commercial fencing and home fencing which appear to be smaller wood fences. They are also distinguished by other characteristics in a given image. A residential home with a fence will be tagged with home fencing whereas a commercial building with a fence will be tagged as fence.
The GSV Vision API attempts to distinguish between these similar but different structures. In fact, the classification is deterministic using a neural network where low level features (image texture, color, edges, etc.) are then mapped to high level features, and finally a prediction. However, certain classes may be similar, for example dwelling and house (though there is something in the image that is causing dwelling to be selected, so the images are somehow distinguishable). To assess the potential sensitivity of the environmental diversity index to combining synonyms into more general categories, we run the following simulation. We simulate 1000 census blocks as follows. In each block we first draw a dirichlet distribution for 20 synthetic categories. We then sample M crimes (where M is uniform from 1 to 1000) according to the dirichlet distribution and allocate them to categories. Next we simulate adding synonym noise by distributing each event to one of 5 random synonyms. We finally compute the diversity index of each of these distributions.
In Fig. 4 we see that even when adding synonym noise, the diversity index is highly correlated (.919) with the original distribution. It is also worth pointing out that both Lentz (2018) and Brantingham (2016) encounter this same issue. In both papers, crime categories themselves are somewhat arbitrary, and different types of clustering could be possible. However they both use the raw categories to compute crime diversity, which is simpler, more reproducible, and less subjective. We prefer to take this approach here, both with the crime diversity index (to match more closely with Lentz (2018), Brantingham (2016)) and the GSV index. We believe this approach is most appropriate given the limited use of GSV Vision API in criminology for purposes of future replication. This approach also avoids the subjective and arbitrary process of assigning image tags to collapsed categories.
Rights and permissions
About this article
Cite this article
Khorshidi, S., Carter, J., Mohler, G. et al. Explaining Crime Diversity with Google Street View. J Quant Criminol 37, 361–391 (2021). https://doi.org/10.1007/s10940-021-09500-1
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10940-021-09500-1