LiDAR Enhanced Structure-from-Motion
This work addresses robustness issues in SfM for applications like inspection, though it appears incremental as it enhances an existing technique with additional sensor data.
The paper tackles the problem of Structure-from-Motion (SfM) being less robust in close-distance imaging with low overlap by proposing a LiDAR-enhanced pipeline that jointly processes LiDAR and stereo camera data, resulting in improved model consistency and rejection of false matches in large-scale environments.
Although Structure-from-Motion (SfM) as a maturing technique has been widely used in many applications, state-of-the-art SfM algorithms are still not robust enough in certain situations. For example, images for inspection purposes are often taken in close distance to obtain detailed textures, which will result in less overlap between images and thus decrease the accuracy of estimated motion. In this paper, we propose a LiDAR-enhanced SfM pipeline that jointly processes data from a rotating LiDAR and a stereo camera pair to estimate sensor motions. We show that incorporating LiDAR helps to effectively reject falsely matched images and significantly improve the model consistency in large-scale environments. Experiments are conducted in different environments to test the performance of the proposed pipeline and comparison results with the state-of-the-art SfM algorithms are reported.