Quantitative Endoscopy: Uncertainty Analysis of Motion Estimation with Robust Feature Matching

Feature matching based 3D reconstruction is a standard technique in 3D Computer Vision. An natural extension is to reconstruct dynamic surfaces from videos, such as reconstructing sinus surfaces from endoscopic videos. However, since the camera is moving and the sinus surfaces are normally deformable and non-planar, the feature matching is usually unsatisfactory. We will employ a state-of-the-art feature matching strategy in the domain of minimally invasive image analysis. Instead of restricting inliers using a global affine transformation, multiple affine components are hierarchically clustered. Qualitative results verify that this Hierachical Multi-Affine (HMA) strategy works well for non-planar and deformable surfaces. Also conducted are the empirical uncertainty analysis of the estimated motion in a leaving-one-out cross validation setting. A series of comparison between HMA matching and SIFT matching are presented as well.