In professional tennis training matches, the coach needs to be able to view play from the most appropriate angle in order to monitor players activities. In this paper, we present a system which can adapt the operation of a series of cameras in order to maintain optimal system performance based on a set of wireless sensors. This setup is used as a testbed for an agent based intelligent middleware that can correlate data from many different wired and wireless sensors and provide effective in-situ decision making. The proposed solution is flexible enough to allow the addition of new sensors and actuators. Within this setup we also provide details of a case study for the embedded control of cameras through the use of Ubisense data.