Counter-terrorism measures and preparedness play a critical role in securing mass gatherings, soft targets, and critical infrastructures within urban environments. This paper introduces a comprehensive Decision Support System developed as part of the S4AllCitites project, designed to seamlessly integrate with existing legacy systems in Smart Cities. The system encompasses urban pedestrian and vehicular evacuation, incorporating predictive models to anticipate the progression of incendiary and mass shooting attacks, alongside a probabilistic model for threat assessment in the case of improvised explosive devices. A notable achievement of this research is the successful implementation and deployment of the system in operational environments through pilot studies. It empowers public and private security operators with real time decision support capabilities during both prevention and intervention stages of potential attacks. The decision support information provided encompasses various aspects, including optimal evacuation strategies, estimated egress times, pedestrian movement profiles, probability assessments, and the potential impact of different terrorist threats in terms of casualties. Additionally, the system offers real-time insights into the status of the traffic network under normal and unusual conditions, enabling efficient emergency management throughout its progression. This includes the ability to identify optimal intervention routes and assess the impact of anomalous traffic resulting from evacuations.

Predicting and understanding mass evacuations are important factors in disaster management and response. Current modelling approaches are useful for planning but lack of real-time capabilities to help informed decisions as the disaster event evolves. To address this challenge, a real-time Evacuation Management System (EMS) is proposed here, following a stochastic approach and combining classical models of low complexity but high reliability. The EMS computes optimal assembly points and shelters and the related network of evacuation routes using GIS-based traffic, pedestrian and routing models including damaged assets or impassable areas. To test the proper operation performances of the EMS, we conducted a case study for the Gran Canaria wildfire (August 2019—Spain).

Population sizing is essential in sociology and in various other real-life applications. Gigapixel cameras can provide high-resolution images of an entire population in many cases. However, exhaustive manual counting is tedious, slow, and difficult to verify, whereas current computer vision methods are biased and known to fail for large populations. A design unbiased method based on geometric sampling has recently been proposed. It typically requires only between 50 and 100 manual counts to achieve relative standard errors of 5–10 percent irrespective of population size. However, the large perspective effect introduced by gigapixel images may boost the relative standard error to 30–40 percent. Here, we show that projecting the sampling grid from a map onto the gigapixel image using the camera projection neutralizes the variance due to perspective effects and restores the relative standard errors back into the 5–10 percent range. The method is tested on six simulated images. A detailed step-by-step illustration is provided with a real image of a 30,000 people crowd.

Population size estimation is essential in ecology and conservation studies. Aerial photography can facilitate this laborious task with high resolution images. However, in images with thousands of individuals exhaustive manual counting is tedious, slow and difficult to verify. Computer vision software may work under some particular conditions but they are generally biased and known to fail in several situations. The CountEm software is a simple alternative based on geometric sampling. It provides a fast and unbiased size estimation for all sorts of populations. The only requirement is that the discrete objects (e.g. animals) in the target population are unambiguously distinguishable for counting in a still image. Typical relative standard errors in the 5–10% range are obtained after counting ~200 properly sampled animals in about 5 min irrespective of population size. The CountEm ver. 1.4.1 is presented here, which includes a guided mode with a simple software interface.