Riemannian Computing in Computer Vision

ISBN-13: 9783319360959 / Angielski / Miękka / 2016 / 391 str.

Pavan K. Turaga; Anuj Srivastava

Spis treści

Riemannian analysis of closed curves and applications in medical imaging.- Human Activity analysis using manifold models of linear dynamical systems.- Pedestrian detection and tracking on tensor manifolds.- Face Recognition using subspaces and Grassmann manifold.- Domain Adaptation using parallel transports on Grassmann manifold.- Kernels on Riemannian Manifolds.- Sparse coding on manifolds and applications to diffusion tensor imaging.- Robust statistics on manifolds and applications to chromatic filtering.- Lighting insensitive face recognition.- Lie-algebraic averaging in Structure from motion problems.- Lie-algebraic methods for Robotic localization problems.- Clustering on Gauss maps for real-time interactive media.- Medical Shape Analysis.- Bayesian Shape Analysis in Images.- Tensor Data Analysis in Medical Imaging.- Trajectories on Manifolds for Activity Recognition.- Data approximation and summarization algorithms on manifolds

O autorze

Pavan Turaga is an Assistant Professor at Arizona State University Anuj Srivastava is a Professor at Florida State University

Blurb

This book presents a comprehensive treatise on Riemannian geometric computations and related statistical inferences in several computer vision problems. This edited volume includes chapter contributions from leading figures in the field of computer vision who are applying Riemannian geometric approaches in problems such as face recognition, activity recognition, object detection, biomedical image analysis, and structure-from-motion. Some of the mathematical entities that necessitate a geometric analysis include rotation matrices (e.g. in modeling camera motion), stick figures (e.g. for activity recognition), subspace comparisons (e.g. in face recognition), symmetric positive-definite matrices (e.g. in diffusion tensor imaging), and function-spaces (e.g. in studying shapes of closed contours).

 

·         Illustrates Riemannian computing theory on applications in computer vision, machine learning, and robotics

·         Emphasis on algorithmic advances that will allow re-application in other contexts

·         Written by leading researchers in computer vision and Riemannian computing, from universities and industry