Linear Global Translation Estimation with Feature Tracks
This addresses camera pose estimation in computer vision, offering a robust solution for collinear motion and weak associations, but it is incremental as it builds on existing methods with specific improvements.
The paper tackles the problem of global camera translation estimation by deriving a novel linear position constraint that avoids scene point coordinates, resulting in a method that is robust, accurate, and efficient, as demonstrated in experiments on sequential and unordered images.
This paper derives a novel linear position constraint for cameras seeing a common scene point, which leads to a direct linear method for global camera translation estimation. Unlike previous solutions, this method deals with collinear camera motion and weak image association at the same time. The final linear formulation does not involve the coordinates of scene points, which makes it efficient even for large scale data. We solve the linear equation based on $L_1$ norm, which makes our system more robust to outliers in essential matrices and feature correspondences. We experiment this method on both sequentially captured images and unordered Internet images. The experiments demonstrate its strength in robustness, accuracy, and efficiency.