Spacio-Statistical Model to Predict Crime Locations Based on Past Crime Events and UAV Based Monitoring of the Predicted Surveillance Route

Crime is heterogeneously distributed and occurs at the most vulnerable places. Crime occurs under poor surveillance and safety, due to lack of public protection and results in damage to public property or human life, and creates a public discrepancy in that particular location. Crime is disastrous because of its unpredictability and unpreparedness for enforcement officers. Finding the probability of occurrence of crimes within such vulnerabilities will help us to deploy certain countermeasures to reduce crime. Crime is limited to location and place. Geographically crime can be considered as a function of lack of surveillance, delay in mobility and control, and probably hidden escape paths utilized by criminals. In this research, a Spatio-Statistical Model was developed for probability-based Crime Prediction using past data and location intelligence technology. Neighborhood Analysis was performed to evaluate the clustering distance between individual crime occurrences within Vadodara city and individual police stations in the neighborhood. The spatial distance is converted into Geographical Coordinate System to calculate latitudinal and longitudinal extents of crime zones in each taluka of the city, which is then utilized to create the Interpolated probability raster for each crime zone with a pixel value equivalent to the probability of occurrence of crime in that location. The Inverse distance weighted (IDW) interpolation technique generated an interpolated surface which was then represented spatially with quantile divisions to form probability zones with the adjoining nearest police jurisdiction. This will enable law enforcement officers to make probability-based surveillance decisions while incorporating the past data intelligence, time of occurrence of crime, and make efficient serviceable patrolling routes and improve crime control with minimal resources. Using this model, the police officers will be able to create patrol routes based on time and zone of highest probability of crime, to ensure safety. The time-based probability of crime is also calculated using the Bayesian probability formula to get the peak crime hours so that surveillance need to be increased at the appropriate time. UAVs mounted with thermal vision can be deployed in the generated high probability zones at the highest probable time of the crime, to monitor the situation aerially without alarming the criminals. In this research it is created an open-source pixel-based route selection algorithm that could identify hotspot locations of crime so that law enforcement officers can watch human movements and follow them silently using UAV's thermal camera in nighttime also to obtain their hideouts and catch criminals.