A UAV-Driven Surveillance System to Support Rescue Intervention
In recent years, the intelligent surveillance systems have attracted many application domains, due to the increasing demand on security and safety. Unmanned Areal Vehicles (AUVs) represent the reliable, low-cost solution for mobile sensor node deployment, localization, and collection of measurements.
This paper presents a surveillance UAV-based system, aimed at understanding the scene situation by collecting raw data from the environment (by exploiting some possible sensor modalities: CCTV camera, infrared camera, thermal camera, radar, etc.), processing their fusion and yielding a semantic, high-level scenario description. UAV is able to recognize objects and the spatio-temporal relations with other objects and the environment. Moreover, UAV is able to individuate alerting situations and suggest a recommended intervention to humans. A Fuzzy cognitive map model is indeed, injected in the UAV: from the semantic description of the scenario, the UAV is able to deduct casual effect of occurring situations, that enhances the scenario understanding, especially when alarming situations are discovered.
KeywordsSituation understanding Situation awareness Fuzzy cognitive maps Semantic Web
- 4.Chauvin, L., Genest, D., Loiseau, S.: Ontological cognitive map. In: 2008 20th IEEE International Conference on Tools with Artificial Intelligence, vol. 2, pp. 225–232, November 2008. https://doi.org/10.1109/ICTAI.2008.42
- 13.Li, X., Lu, H.: Object tracking based on local learning. In: 2012 19th IEEE International Conference on Image Processing, pp. 413–416, September 2012. https://doi.org/10.1109/ICIP.2012.6466883
- 15.Meditskos, G., Kompatsiaris, I.: iknow: ontology-driven situational awareness for the recognition of activities of daily living. Pervasive Mob. Comput. 40, 17–41 (2017). https://doi.org/10.1016/j.pmcj.2017.05.003. http://www.sciencedirect.com/science/article/pii/S157411921630195XCrossRefGoogle Scholar
- 17.Piccardi, M.: Background subtraction techniques: a review. In: 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583), vol. 4, pp. 3099–3104 vol. 4, October 2004. https://doi.org/10.1109/ICSMC.2004.1400815
- 19.Smedt, F.D., Hulens, D., Goedemé, T.: On-board real-time tracking of pedestrians on a UAV. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 1–8, June 2015. https://doi.org/10.1109/CVPRW.2015.7301359