Real-time camera pose estimation via line tracking

Real-time camera calibration has been intensively studied in augmented reality. However, for texture-less and texture-repeated scenes as well as poorly illuminated scenes, obtaining a stable calibration is still an open problem. In the paper, we propose a method of calibrating a live video by tracking orthogonal vanishing points. Since vanishing points cannot be obtained directly on the image, the tracking is achieved by tracking parallel lines. This is a changeling problem due to the fact that vanishing points are sensitive to image noise, camera movement, and illumination variation. We tackle the challenges by three optimization procedures and flexible process of degenerated cases. During three optimizations, several explicitly geometric constraints are incorporated, ensuring the calibration result robust to poor illumination and camera movement. A variety of challenging examples demonstrate that the proposed algorithm outperforms state-of-the-art methods for texture-less and texture-repeated scenes.