On Camera Calibration for Scene Model Acquisition and Maintenance Using an Active Vision System

摘要

We present a fully integrated active vision system for interpreting dynamic scenes. We argue that even if the ego-motion of the mobile vision system is known, a single view camera calibration cannot adequately support scene model acquisition and maintenance. It is shown that stable camera/grabber chain calibration can be achieved using a multi-view calibration process. With such calibration, a predicted view of the scene from any arbitrary view point can successfully be used for object verification and scene model maintenance. Experimental results in scene interpretation confirm the benefits of the multi-view calibration approach.