Sparse bundle adjustment and Sparse pose adjustment.
Sparse Bundle Adjustment, or SBA, is used for reconstructing 3D structure and camera pose from a series of monocular or stereo images. The technique is usually used for refining existing estimates of 3D geometry and camera pose.
In most cases, you will want to use the sba::SysSBA class to set up a system consisting of sba::Node and sba::Track.
Each sba::Node represents a camera pose and also contains camera projection matrices.
An sba::Track contains a single sba::Point and a map of sba::Proj, containing the projections of the point into each node in which it can be seen. The map is indexed by sba::Node index.