Project period: april 2016 – mars 2019
Partners: Vattenfall, Combitech AB, In Situ AB, LFV
Project manager: Assistant professor Najeem Lawal
Researcher: Benny Thörnberg och en ny New Post Doc.
Description: The ability to effectively identify flying objects in a given volume and characterize their activitiescan lead to improved prediction of future activity. Such prediction is applicable, for example, inimproving collision avoidance systems for wind farms. Employing a visual monitoring systemconsisting of many camera nodes that form visual sensor network (VSN) will provide more reliabledatasets compared to a human approach. Effective characterization can be achieved through robustmodels of the activities based on adequate datasets provided by the VSN. In this project we willinvestigate the requirements for VSN node architecture and deployment topology for remote outdoormonitoring. Our aim is to find a cost optimized design for the VSN nodes and topology constrainedlimited resources. These resources include energy, communication and data storage. In this project,we will investigate multi-camera node architecture (MCNA) by exploring trade-offs among theresources and node cost. We will also investigate how MCNA can lead to a cost optimized nodedeployment topology. Through close collaboration with industry partners we will be able to fulfilthe project objectives and provide the industry with a tool for predicting future activity within avolume. Although this proposal focuses on monitoring wind farms and flying birds’ activities, theresult are applicable in other fields.