Condition-based placement of distributed active vision sensors for guiding robots in intelligent environment

To make intelligent environment with distributed intelligent cameras, one of the most important problems is to monitor the service area seamlessly. Since the recognized objects in the image, captured by camera, is deeply related with distance and location between the camera and the objects, even though cameras in the intelligent environment cover the entire area, the recognition error varies roughly. To provide stable service to clients, such as robot, human and other dynamic objects, the recognition results should keep a certain quality, and to satisfy this, the distributed cameras should be placed well.