Classifying crime places by neighborhood visual appearance and police geonarratives: a machine learning approach

Abstract

The complex interrelationship between the built environment and social problems is often described but frequently lacks the data and analytical framework to explore the potential of such a relationship in different applications. We address this gap using a machine learning (ML) approach to study whether street-level built environment visuals can be used to classify locations with high-crime and lower-crime activities. For training the ML model, spatialized expert narratives are used to label different locations. Semantic categories (e.g., road, sky, greenery, etc.) are extracted from Google Street View (GSV) images of those locations through a deep learning image segmentation algorithm. From these, local visual representatives are generated and used to train the classification model. The model is applied to two cities in the U.S. to predict the locations as being linked to high crime. Results show our model can predict high- and lower-crime areas with high accuracies (above 98% and 95% in first and second test cities, accordingly).

VisualCommunity: a platform for archiving and studying communities

“…Adding in a simultaneously recorded commentary, often described as a geonarrative, further enriches these data with context. As a result, multiple topics including health, crime [ 12 ], and disasters have been studied using this approach both within the United States and in various challenging oversea environments [ 3 , 13 – 15 ]. The challenge has always been that the associated software, including spatial data processing and analysis tools have lagged behind the technological and methodological advances.…”

“…In the proposed platform street level images were used as a data source to search for localized detail [ 12 , 23 – 25 ]. The images were segmented with machine learning (ML) tools and the identified semantic categories (e.g., greenery, building, road, etc.)…”

Towards an AI-driven framework for multi-scale urban flood resilience planning and design

“…An ontology is a template defining and representing entities, ideas, and events, with all their interdependent properties and relations, according to a system of categories (i.e., flood resilience in this project). To create such a knowledge graph, there are many technical challenges that can be addressed through AI innovations in computer vision, natural language processing, and geographic information system (Amiruzzaman et al, 2021;Ye et al, 2021). Massive resilience relevant information can reside in different forms of data types, such as documents and images.…”

Techniques for Predicting Dark Web Events Focused on the Delivery of Illicit Products and Ordered Crime

“…In a AI-ML study, VLFeat was described as a library of CV algorithms used to undertake quick prototyping, the human posture may be identi ed using face detection/human recognition [7]. ML is a technique that allows a computer system to improvise from prior occurrences without having to be explicitly coded [8] and ML comprehends the exact design and frameworks [9]. Various crimes and their underlying nature appear to be unpredictable, but ML helps with pattern recognition [10] and NLP approaches using CV for information modelling.…”