WiseNET: smart camera network combined with ontological reasoning for smart building management

Roberto Marroquin (1) , Julien Dubois (1) , Christophe Nicolle (1)

1 Le2i - Laboratoire Electronique, Informatique et Image [UMR6306]

Visual sensor networks (VSN) have become a part of our daily life [1] [2]. Based on our experience we have identified two main problems on VSN. Firstly, the problem of selecting relevant information from the huge amount of data given by the network. Secondly, the problem of integrating the information coming from the different nodes of the network, i.e., linking the different informations together in order to take a decision. These problems can be overcome by including smart cameras in charge of extracting the significant information from the scene and by adding contextual semantic information, i.e., semantic information of what the camera observes, building information and events that may occurred. Semantic information coming from different nodes can be easily integrated in an ontology. Our approach differs from standard computer vision, which deals with algorithm improvement [3] [4] and signal processing problems [5], by dealing with a meaning problem in computer vision, where we try to improve and understand what the camera " sees " by adding contextual semantic information. We developed an innovative distributed system that combines smart cameras with semantic web technology. The proposed system is context sensitive and provides knowledge and logic rules in order to optimize the usage of a smart camera network. The main application of our system is smart building management, where we specifically focus on improving the services of the building users. The WiseNET (Wise Network) system consists of a smart camera network connected to an ontological model. The communication between the smart camera network and the ontological model is bidirectional, i.e., the cameras can send information either when the model asks for it or whenever new data becomes available. The ontological model is a semantical one that allow us to express information in our system and to take decisions according to combinations of the different information [6]. The semantical model is articulated in three sections: sensor, environment and application. All the sections are bilaterally connected between themselves by properties and relations. The sensor section consists of a semantic web vocabulary concerning the smart camera, the image processing algorithms and their results [7]. The sensor section is in charge of giving a semantic meaning to what the smart cameras observes, a problem known as semantic gap [8]. The environment section is composed by a semantic web vocabulary regarding the building information model (BIM) [9]. Finally, the application section comprises a set of rules defining some events that may be important for security applications and the different decisions to take according to the occurrence of these events [10].

Domaines: Systèmes embarqués

Roberto Marroquin, Julien Dubois, Christophe Nicolle. WiseNET: smart camera network combined with ontological reasoning for smart building management. 5th Workshop on Architecture of Smart Cameras (WASC), Jul 2016, Dijon, France. ⟨hal-01342886⟩