Pawlak's flow graph extensions for video surveillance systems
Karol Lisowski, Andrzej Czyżewski
Citation: Proceedings of the 2015 Federated Conference on Computer Science and Information Systems, M. Ganzha, L. Maciaszek, M. Paprzycki (eds). ACSIS, Vol. 5, pages 81–87 (2015)
Abstract. The idea of the Pawlak's flow graphs is applicable to many problems in various fields related to decision algorithms or data mining. The flow graphs can be used also in the video surveillance systems. Especially in distributed multi-camera systems which are problematic to be handled by human operators because of their limited perception. In such systems automated video analysis needs to be implemented. Important part of this analysis is tracking object within a single camera and between cameras' fields of vision. One of element needed to re-identify the single real object besides object's visual features and spatio-temporal dependencies between cameras is a behaviour model. The flow graph after some modifications, is a suitable data structure, which concept is based on the rough set theory, to contained as a behaviour model in it. Additionally, the flow graph can be used to predict the future movement of given object. In this paper a survey of authors research works related to employing flowgraphs in video surveillance systems is contained. The flow graph creation based on the paths of objects inside supervised area will presented. Moreover, a method of building a probability tree on the basis of the flow graph and a method for adaptating the flowgraph to the changing topology of the camera network are also discussed.