CSIS Ecosystem: Impacts of Pragmatic Detection on a Campus Surveillance Case Study

• Babacar Mane UFBA
• Fernando H. de A. Moraes Neto UFBA
• Roberto de Cerqueira Figueiredo UFBA
• Caio Nery UFBA
• Diana Romero Clavijo UFBA
• Samuel Rios da Silva UFBA
• Daniela Barreiro Claro UFBA
• Celia Ghedini Ralha UFBA
• Ana Patricia Magalhães UNEB
• Rita Suzana Pitangueira Maciel UFBA
• Marlo Vieira dos Santos e Souza UFBA
• George Marconi de Araújo Lima UFBA
• Bruno Pereira dos Santos UFBA
• Robespierre Pita UFBA
• Edlane Proença UFBA
• Luis Emanuel Neves de Jesus UFBA
• Iala Patrícia de Jesus Monteiro de Jesus UFBA

DOI: https://doi.org/10.5753/sbsi.2026.248739

Abstract

Research Context: In modern universities, where there is a constant flow of people, it is essential to implement computer vision surveillance systems to detect incidents and alert security personnel, in order to ensure the safety of all members of the academic community. Practical Problem: Universities are faced with numerous security issues, including limited resources, a diverse range of technical infrastructure, and a mix of old and new systems. Besides, traditional security methods are reactive, slow to notice incidents, which in turn makes quick response in emergencies very hard. Proposed Solution: We present the solution in the form of the Campus Surveillance Interoperability System (CSIS), which is an open-source, modular, and interoperable architecture that we put forth for the specific surveillance needs of universities. CSIS utilizes a variety of computer vision models from the YOLOv11x set, specialized in recognizing weapons, fires, floods, graffiti, suspicious behavior, and license plates. Related IS Theory: Our paper adopts a Socio-technical theory, which recognizes that the effectiveness of information systems depends on the interaction between social and technical components rather than on technology alone. Research Method: In a real-world university setting, we put our proof of concept to the test. We had real-time video stream input, ensemble-based inference, and a centralized alert management system. We assessed the accuracy of the models. Summary of Results: We achieved an average accuracy of 83% for license plate recognition, weapon detection, graffiti, and smoke detections. Although we achieved moderate accuracy in fire detection and lower performance in flood detection. Considering sociotechnical concerns, we evaluate CSIS’s ability to automate surveillance tasks. Contributions and Impact to IS Area: CSIS architecture introduces an interoperable architecture for intelligent surveillance, demonstrating a model of interoperability in real time;

References

Anagnostopoulos, T., Kostakos, P., Zaslavsky, A., Kantzavelou, I., Tsotsolas, N., Salmon, I., Morley, J., and Harle, R. (2021). Challenges and solutions of surveillance systems in iot-enabled smart campus: a survey. Ieee Access, 9:131926–131954.

Aquarium (2023). hanyang-puddle-detection-part2 bbox dataset. [link]. visited on 2024-11-26.

Assalim, J. (2024). Weapon 2 dataset. [link]. visited on 2024-11-26.

Bhutad, S. and Patil, P. K. (2021). Stagnant water. DOI: 10.21227/zrhk-tq74.

Cazzolato, M. T., Avalhais, L. P. S., Chino, D. Y. T., Ramos, J. S., Souza, J. A., Rodrigues-Jr, J. F., and Traina, A. J. M. (2017). Fismo: A compilation of datasets from emergency situations for fire and smoke analysis. In SBBD2017 - SBBD Proceedings of Satellite Events of the 32nd Brazilian Symposium on Databases - DSW (Dataset Showcase Workshop), pages 213–223. SBC.

de Andrade, A. F., Damasceno, E. Z. C., de Lima Siqueira, J. E., Rocha, A. M. S. A., Carrafa, J. P. P., dos Santos, L. B., and de Jesus, R. F. (2024). A implementação de sistemas de vigilância com tecnologia de inteligência artificial no auxílio da administração pública na prevenção de crimes. Revista Eletrônica Interdisciplinar, 16(3).

Delnevo, G., Ghini, V., Fiumana, E., and Mirri, S. (2024). A support tool for emergency management in smart campuses: Reference architecture and enhanced web user interfaces. Sensors, 24(18).

Dube, K., Wu, B., and Grimson, J. (2002). Using ECA Rules in Database Systems to Support Clinical Protocols. In Proceedings of the 13th International Conference on Database and Expert Systems Applications (DEXA 2002), volume 2453 of Lecture Notes in Computer Science, pages 226–235. Springer.

Ekpoh, U. I., Edet, A. O., and Ukpong, N. N. (2020). Security challenges in universities: Implications for safe school environment. Journal of Educational and Social Research, 10(6):112–112.

Figueiredo, R., Mane, B., Clavijo, D. C. R., Silva, S., Moraes, F., Nery, C., Magalhaes, A. P., Maciel, R. S. P., Claro, D., Souza, M., Lima, G., and Leite, J. C. (2025). Towards a SoIS model for University Surveillance. In Proceedings of the 2025 International Conference on Software Engineering for Systems-of-Systems (SESoS), ICSE 2025, page –, Ottawa, Ontario, Canada. ACM.

Gondim, J., Claro, D. B., and Souza, M. (2025). A bilingual analysis of multi-head attention mechanism for image captioning based on morphosyntactic information. Journal of the Brazilian Computer Society, 31(1):1063–1076.

Jocher, G. and Qiu, J. (2024). Ultralytics yolo11.

Keerthana, R., Kumar, M., and Prakash, S. (2023). Enhancing campus security through smart surveillance system. In Proceedings of the International Conference on Smart Technologies, pages 112–118. IEEE. Accessed: 2025-07-28.

Kerich, N., Omuterema, S. O., and Pepela, M. M. (2024). Evaluating the role of electronic security surveillance in enhancing safety in secondary schools: A case study of trans nzoia county, kenya. African Journal of Empirical Research, 5(4):163–173.

Laroca, R., Cardoso, E. V., Lucio, D. R., Estevam, V., and Menotti, D. (2022). On the cross-dataset generalization in license plate recognition. In International Conference on Computer Vision Theory and Applications (VISAPP), pages 166–178.

Laroca, R., Zanlorensi, L. A., Gonçalves, G. R., Todt, E., Schwartz, W. R., and Menotti, D. (2021). An efficient and layout-independent automatic license plate recognition system based on the yolo detector. IET Intelligent Transport Systems, 15(4):483–503.

Lim, J., Al Jobayer, M. I., Baskaran, V. M., Lim, J. M., See, J., and Wong, K. (2021). Deep multi-level feature pyramids: Application for non-canonical firearm detection in video surveillance. Engineering Applications of Artificial Intelligence, 97:104094.

Maciel, R. S. P., David, J. M. N., Claro, D. B., and Braga, R. (2019). Full interoperability: Challenges and opportunities for future information systems.

Mane, B., Magalhaes, A. P., Quinteiro, G., Maciel, R. S. P., and Claro, D. B. (2021). A domain specific language to provide middleware for interoperability among saas and daas/dbaas through a metamodel approach. In Proceedings of the 23rd International Conference on Enterprise Information Systems - Volume 1: ICEIS, pages 83–94. INSTICC, SciTePress.

Marcin, W. (2023). Grafitti finding dataset. [link]. visited on 2024-11-26.

Moura, N., Gondim, J., Claro, D., Souza, M., and Figueiredo, R. (2021). Detection of weapon possession and fire in public safety surveillance cameras. In Anais do XVIII Encontro Nacional de Inteligência Artificial e Computacional, pages 290–301, Porto Alegre, RS, Brasil. SBC.

Paschke, A. (2006). ECA-RuleML: An Approach Combining ECA Rules with Temporal Interval-Based KR Event/Action Logics and Transactional Update Logics. CoRR, arXiv:cs/0610167. Accessed: 2025-07-08.

Ralha, C. G., Claro, D. B., and Maciel, R. S. P. (2025a). Conceiving socio-technical information systems from the perspective of digital twins. In Proceedings of the Workshop on Information Systems Challenges in Brazil (2026-2036) at the Brazilian Symposium of Information Systems.

Ralha, C. G., Claro, D. B., and Stroele, V. (2025b). Information systems and artificial intelligence integration challenges. In Proceedings of the Workshop on Information Systems Challenges in Brazil (2026-2036) at the Brazilian Symposium of Information Systems.

Redmon, J., Divvala, S., Girshick, R., and Farhadi, A. (2016). You only look once: Unified, real-time object detection. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 779–788.

Ribeiro, E. L. F., de Jesus, L. E. N., Claro, D. B., and Moura, N. (2021). Towards a pragmatic interoperability on the midas middleware. In Proceedings of the Brazilian Symposium on Multimedia and the Web, WebMedia ’21, page 161–168, New York, NY, USA. Association for Computing Machinery.

Ribeiro, E. L. F., Monteiro, E. L., Claro, D. B., and Maciel, R. S. P. (2019). A conceptual framework for pragmatic interoperability. In Proceedings of the XV Brazilian Symposium on Information Systems, pages 1–8.

Santos, C. N. M., Claro, D. B., Gondim, J. M., and Mane, B. (2024). Suspicious behavior detection near vehicles in university environment: An approach using object detection and body angles. In Anais do XX Simpósio Brasileiro de Sistemas de Informação (SBSI), pages 1–8. Sociedade Brasileira de Computação.

Santos, D., Claro, D. B., and Gondim, J. (2023). Monitoring vehicle plate detection in brazilian universities. In Proceedings of the 19th Brazilian Symposium on Information Systems (SBSI). Sociedade Brasileira de Computação.

Schulzrinne, H., Rao, A., and Lanphier, R. (1998). RFC 2326: Real Time Streaming Protocol (RTSP). [link]. Accessed: November 1, 2024.

Shiri, A. (2024). Criminal policy about electronic surveillance. Iranian Journal of Public Policy, 10(3):99–111.

Silva, A. S., de Azevedo, A. R., Neto, F. H. d. A. M., and da Silva, P. H. F. (2025). Modelo basado en yolov8 para la detección automática de daños en tejados residenciales. Revista ALCONPAT, 15(1):50–63.

Tantra, B. J. and Widjaja, M. (2024). Automatic detection of dress-code surveillance in a university using yolo algorithm. IAES International Journal of Artificial Intelligence, 14(2):1568–1575.

Tian, Y., Ye, Q., and Doermann, D. (2025). Yolov12: Attention-centric real-time object detectors. arXiv preprint arXiv:2502.12524.

Wang, C.-Y. and Liao, H.-Y. M. (2024). Yolov9: Learning what you want to learn using programmable gradient information.

Xiao, Q., Wu, C., Wang, Y., Lin, B., and Zhang, H. (2024). Campus security inspection robot based on yolo algorithm. In Proceedings of the 2024 2nd International Conference on Frontiers of Intelligent Manufacturing and Automation, pages 800–806.

Zhou, Y. et al. (2022). A model for predicting the risk of campus violence in an edge intelligent computing architecture. Journal of Intelligent Fuzzy Systems, 43(4):4353–4362.