An Intelligent Mobile System with Edge Computing for Public Safety Incident Response

• Stefano Loss UFRN
• Karine Costa UFRN
• Alison Hedigliranes UFRN
• Pedro Varela UFRN
• João Pedro Limão UFRN
• Thais Batista UFRN
• Aluizio Rocha Neto UFRN
• Daniel Sabino UFRN
• Nélio Cacho UFRN
• Frederico Lopes UFRN
• Everton Cavalcante UFRN

DOI: https://doi.org/10.5753/semish.2025.8405

Abstract

This paper presents a mobile system that integrates functionalities for managing public safety incidents, from sending incident notifications to police vehicles to intelligent, real-time processing of videos captured by the mobile devices of police officers on duty. This processing is performed at the network’s edge and generates alerts to improve situational awareness of officers in the field. The paper also evaluates the performance of a face recognition algorithm under limited connectivity conditions, aiming to find a balance between video resolution, recognition accuracy, and energy and network bandwidth consumption on a mobile device.

References

Endsley, M. R. (1995). Toward a theory of situation awareness in dynamic systems. Human Factors.

Fórum Brasileiro de Segurança Pública (2024). 18º Anuário Brasileiro de Segurança Pública: 2024.

Huang, G. B. et al. (2007). Labeled faces in the wild: A database for studying face recognition in unconstrained environments. Technical Report 07-49, University of Massachusetts, Amherst.

Liu, Z. et al. (2015). Deep learning face attributes in the wild. Proceedings of the IEEE International Conference on Computer Vision (ICCV), pages 3730–3738.

Loss, S. et al. (2025). Framework for live situational awareness in stream-based 5g applications. In Proceedings of the 1st IEEE Latin American Conference on Internet of Things (IEEE LACIoT). IEEE.

Mahmoud, H. and Abozariba, R. (2025). A systematic review on webrtc for potential applications and challenges beyond audio video streaming. Multimedia Tools and Applications.

Nakashima, M. (2024). Desvendando o potencial e os desafios da inteligência artificial na polícia militar do paraná: Estratégias para predição e prevenção de crimes. REASE, 10(1):1321–1336.

PMSC (2017). PMSC mobile – tecnologia móvel para gestão de atendimentos policiais. Gestão Eletrônica de Trânsito – Talonário Eletrônico.

Redmon, J. et al. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Schroff, F. et al. (2015). Facenet: A unified embedding for face recognition and clustering. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

Vieira, F. et al. (2024). Aplicabilidade da inteligência artificial nas polícias militares brasileiras: Vantagens, desvantagens e/ou limitações. In Anais do Congresso Internacional de Conhecimento e Inovação (ciKi).

Zhang, J. et al. (2016). Profiling energy consumption of dash video streaming over 4g lte networks. In Proceedings of the 8th International Workshop on Mobile Video, MoVid ’16, NY, USA. ACM.