Note: This content is accessible to all versions of every browser. However, this browser does not seem to support current Web standards, preventing the display of our site's design details.


Control of Multiple Cameras for Tracking and Surveillance


D. M. Raimondo

IfA Internal Seminar Series

Nowadays, security is a major issue in public places and video surveillance systems are being installed everywhere. Pan-tilt and zoom (PTZ) cameras are commonly used as components of wide-area surveillance systems. The goal is to design a fully automated surveillance system able to detect and track targets as they move through the whole monitored site. The cameras cooperatively track targets by dynamically exchanging targets information (i.e. position, velocity) through a network. In this talk a possible solution to the problem, based on the following assumptions, will be presented: - Ground plane: the targets move on a planar environment with no obstacles. - Overlapping field of views: neighboring cameras usually have partially overlapping field of views, so that a target can sometimes be seen by two or more cameras at the same time, from different viewpoints. - Target detection: the target is assumed to be always detected when it is completely visible inside the field of view of a camera. - Target velocity: the target maximum velocity is assumed to be known, or at least an upper bound is given. - Target priority: targets will have different priorities that can be assigned by a human operator. - Communication data: cameras exchange targets 3D position and maximum velocity. The proposed approach is based on the solution, at each time step, of a Mixed Integer Mixed Integer Quadratically Constrained Quadratic Problem (MIQCQP).


Type of Publication:


No Files for download available.
% No recipe for automatically generating a BibTex entry for (06)Talk
Permanent link