Morella under the lens of AI: tourist webcams for optimising visitor flows and detecting anomalies
In collaboration with the Valencian Regional Government and Morella City Council (Castellón), our IDAL's (Intelligent Data Analysis Laboratory) research team from the University of Valencia has developed a new use case within the framework of the Citcom.ai project: an advanced Artificial Intelligence solution focused on optimising visitor flow management and improving public safety in the town using real-time video analysis.
This system applies computer vision and deep learning models to the HD tourist webcams already in operation in the city. The aim of developing this solution has been to transform a promotional tool, such as a tourist camera, into an active intelligent management system capable of providing accurate, real-time information on crowd dynamics in order to optimise space management and decision-making and, ultimately, enrich the overall experience.
This solution therefore allows destinations, attractions and transport hubs to be actively monitored to estimate visitor density, track flows, and identify areas of congestion, which directly translates into greater safety for visitors.
Dual approach: crowd management and anomaly detection
The AI solution implemented focuses on two main axes that work simultaneously from the same video signal:
- Tourist flow management (counting and prediction): From a tourism perspective, the tool performs real-time crowd counting, allowing occupancy and density to be measured in key areas. By processing this data as a time series, the system not only measures but can also predict future occupancy levels. This makes it possible to detect anomalies in visitor numbers (unexpected peaks or troughs) and correlate them with external factors such as public holidays, sporting events, or inclement weather.
- Security and urban management (detection of infringements): From the perspective of the City Council and public safety, the model is trained to automatically detect infringements or abnormal situations. The specific use case implemented in Morella is the detection of vehicles in pedestrian areas. To make this function fully operational, an automatic alarm system has been implemented that instantly notifies these incidents, allowing for an immediate response.
Overall, this use case demonstrates the potential of AI to convert existing infrastructure, such as tourist webcams, into active smart management tools. The impact is twofold: it enables more sustainable flow management and, at the same time, proactively reinforces public safety.
This project can promote Morella not only as a tourist destination, but also as a Smart Tourist Destination that applies technological innovation to ensure a safer and more orderly environment and improve coexistence between residents and visitors.
If you are interested in this use case and would like to learn more about how we apply Artificial Intelligence to improve tourism management and urban safety, or if you think we could help you develop a similar solution in your municipality or project, please contact us! You can find all the information in our Contact section.
You can also consult the following scientific publication on this use case: Multimodal Video Analysis for Crowd Anomaly Detection Using Open Access Tourism Cameras.
Finally, the authors would like to thank the Regional Ministry of Innovation, Industry, Trade and Tourism (Conselleria d'Innovació, Indústria, Comerç i Turisme de la Generalitat Valenciana) for its funding under Grant Agreement No. 101100728, as part of the European Commission’s Citcom.ai project.