🤖 AI Summary
Existing curve shape analysis methods rely solely on first-order geometric information (e.g., tangent vectors), leading to registration artifacts and interpolation distortions. To address this, we propose a Riemannian geometric modeling framework grounded in the Frenet–Serret apparatus. By incorporating generalized curvature—comprising both curvature and torsion—and constructing the Square Root Velocity Transformation (SRVT), we embed open and closed curves from Euclidean space into a Riemannian manifold endowed with a well-defined metric structure. This representation is the first to jointly exploit curvature and torsion within an invariant framework, thereby fully capturing higher-order differential geometric features. The approach significantly improves physical interpretability and visual fidelity in geodesic distance computation, shape averaging, and interpolation. Extensive evaluation on synthetic data and real-world sign language motion trajectories demonstrates superior modeling accuracy and robustness over conventional first-order methods.
📝 Abstract
Geometric frameworks for analyzing curves are common in applications as they focus on invariant features and provide visually satisfying solutions to standard problems such as computing invariant distances, averaging curves, or registering curves. We show that for any smooth curve in R^d, d>1, the generalized curvatures associated with the Frenet-Serret equation can be used to define a Riemannian geometry that takes into account all the geometric features of the shape. This geometry is based on a Square Root Curvature Transform that extends the square root-velocity transform for Euclidean curves (in any dimensions) and provides likely geodesics that avoid artefacts encountered by representations using only first-order geometric information. Our analysis is supported by simulated data and is especially relevant for analyzing human motions. We consider trajectories acquired from sign language, and show the interest of considering curvature and also torsion in their analysis, both being physically meaningful.