Multimedia Computing and Computer Vision Lab

Login  

Home

     

Courses

     

People

     

Research

     

Publications

     

Student Theses

     

Source Code / Datasets

     

Contact

     

On the Optimal Placement of Multiple Visual Sensors

From Multimedia Computing Lab - University of Augsburg


Visual sensor arrays are used in many novel multimedia applications such as video surveillance, sensing rooms, assisted living or immersive conference rooms. Often several different types of cameras are available. They differ in their ranges of view, intrinsic parameters, image sensor resolutions, optics, and costs.

Most of the above mentioned applications require the layout of video sensors to assure a minimum level of image quality or image resolution. Thus, an important issue in designing visual sensor arrays is the appropriate placement of the cameras such that they achieve one or mulitple predefined goals. As video sensor arrays are getting larger, efficient camera placement strategies need to be developed.

We are focusing on the topic of maximizing or achieving coverage with respect to a predefined 'sampling rate' guaranteeing that an object in the space will be imaged at a minimum resolution. We consider this problem in its various factes and propose different algorithms to solve these problems. The proposed algorithms can be subdivided into algorithms which determine the global optimum solution and heuristics which solve the problem within reasonable time and memory consumption, but do not necessarily determine the global optimum.

Currently a user interface is developed in order to comfortably enter and edit the layout of spaces and setup parameters of the respective optimization problem. This interface will be running as a web service.

For more information on optimal camera placement please contact Eva Hörster

Main
result configuration by greedy approach
Main
result configuration by greedy approach



References:

  1. Eva Hörster, Rainer Lienhart. Approximating Optimal Visual Sensor Placement. IEEE ICME2006, Toronto, Canada, July 10-12, 2006. Auch als Technical Report: [PDF]
  2. Eva Hörster, Rainer Lienhart. Calibrating and Optimizing Poses of Visual Sensors in Distributed Platforms. ACM Multimedia System Journal, Special Issue on Multimedia Surveillance System to appear. Technical Report: [PDF]
  3. Eva Hörster, Rainer Lienhart. On the Optimal Placement of Multiple Visual Sensors. Technical Report 2006-18, Institute of Computer Science, University of Augsburg, July 2006. [PDF]