Auto calibration for multiple camera-based surveillance system

Monitoring of large sites requires coordination of multiple cameras, and methods for relating events between distributed cameras. This paper presents a planar trajectory estimation method using multiple cameras, and the use of estimated trajectories to facilitate camera calibration. The algorithm addresses the problem of recovering the relative pose of several stationary cameras that observe one or more objects in motion. Each camera tracks several objects to produce a set of trajectories in the image. Using a simple calibration procedure, we recover the relative orientation of each camera to the local ground plane. We also present experimental results on both indoor and outdoor sequences containing persons and vehicles.