![]() ![]() In our problem, tasks occur stochastically, based on detecting or receiving specific information of activities occurring in the workcell. In this paper, we investigate the online multicamera task assignment problem and propose a reactive scheduling approach that is suitable for manufacturing environments. Effective management of cameras is crucial for the network to achieve its designated monitoring goal and fulfil task-specific requirements. On top of the acquired information a conceptual situation recognition system fuses all available input data and infers potentially interesting situations in the scene leading to comprehensive situational awareness.Ĭamera networks have been increasingly adopted in manufacturing to enhance workplace safety and maintain production quality levels. The system is a reliable basis for further generic image processing and situational awareness plugins: blob detection and tracking, person detection and identification, car detection and number plate recognition, as well as action recognition. The incremental learning procedure is based on local image features. In order to control the pan-tilt-zoom camera in terms of image coordinates of the master camera, the system learns the relationship between the individual cameras automatically. The network node consists of three cameras: A high definition overview camera (the master) with a large field of view, a pan-tilt-zoom camera (the slave), and a long-wave infrared camera. ![]() In this paper we present a self-adaptive multi-camera component, which can be considered as a single node of a camera network. Automatic scene analysis using multiple cameras connected in a network is an important step to enhance the capabilities of future situation awareness tools.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |