3D Model Acquisition by Tracking 2D Wireframes

This paper presents a semi-automatic wireframe acquisition system. The system uses real-time (25Hz) tracking of a user specified 2D wireframe and intermittent camera pose parameters to accumulate 3D position information. The 2D tracking framework enables the application of model-based constraints in an intuitive way which interacts naturally with the Kalman filter formulation used. In particular, this is used to introduce feedback from the current 3D shape estimate to improve the robustness of the 2D tracking. The scheme allows wireframe models of simple edge based objects to be built in around 5 minutes.

• Type: Conference
• Year: 2000
• Where: BMVC
• Authors: M. Brown, Tom Drummond, Roberto Cipolla
• Keywords: 2D Tracking, 2D Tracking Framework, BMVC 2000, Computer Vision, Semi-automatic Wireframe Acquisition