Optimal_placement_of_cameras_in_floorplans_to_satisfy_task_requirements_and_cost_constraint外文翻译.pdfVIP

Optimal Placement of Cameras in Floorplans to Satisfy Task Requirements and Cost Constraints Ugur Murat Erdem and Stan Sclaroff Computer Science Department, Boston University, Boston, MA 02215 merdem@,sclaroff@ Abstract. In many multi-camera vision systems the effect of camera locations on the task-specific quality of service is ignored. Researchers in Computational Ge- ometry have proposed elegant solutions for some sensor location problem classes. Unfortunately, these solutions utilize unrealistic assumptions about the cameras’ capabilities that make these algorithms unsuitable for many real-world computer vision applications. In this paper, the general camera placement problem is first defined with assumptions that are more consistent with the capabilities of real- world cameras. Given a floorplan to be observed, the problem is to efficiently compute a camera layout such that certain task-specific constraints are met and with minimal camera setup cost. A solution to this problem is obtained via binary optimization over a discrete problem space. In preliminary experiments the per- formance of the system is demonstrated with two different practical experiments on a real floorplan. 1 Introduction Computer vision in video sensor networks has become a hot research topic. As in cel- lular telephone networks, the aim is to have as much coverage as possible within a pre-defined region, with an acceptable level of quality-of-service and with minimum setup cost. In video sensor networks, the layout of cameras should assure a minimum level of image quality needed to satisfy certain task-specific requirements – for instance, sufficient spatial resolution, depth of field, servo speed for pan-tilt-zoom cameras, etc. In Computational Geometry, extensive progress h