Robust and Efficient 3-D Optical Flow Computing Framework

ISBN-13: 9783639173000 / Angielski / Miękka / 2009 / 152 str.

Chang-Ming Tsai

Opis

This book presents a framework that improves the robustness and accuracyin computing dense optical-flow fields. We propose a global formulationwith a regularization term that can handle the 3D flow patterns, such as rotation, zoom, and their combinations, induced by a 3D rigid-body motion. The movitation of this book is that the traditionaloptical flow regularizers incorrectly penalize the above 3D flow patterns andresult in biased estimates. Hence, the purpose of this work is to derive a new suite of regularization expressions that treat all valid flow patterns resulting from a 3D rigid-body motion equally, without unfairly penalizing any of them. Furthermore, we develop a framework of optical flow computation and flow model inference method. The proposed framework can fully utilize the power of the proposed 3D rigid body motion regularizers. The proposed framework is well suited for implementing real-time and high accuracy image and video processing applications.

O autorze

Chang-Ming Tsai was born in Kaohsiung, Taiwan. His major
research fields include computer vision, computer grahics,
machine
learning and numerical methods. He received
the B.S. and M.S degree in computer science from Nation Taiwan
University, and also received the M.S. and PhD degree from
University of California, Santa Barbara.