TY - GEN

T1 - Robust direct vision-based pose tracking using normalized mutual information

AU - Luo, Hang

AU - Pape, Christian

AU - Reithmeier, Eduard

PY - 2018/11/2

Y1 - 2018/11/2

N2 - This paper presents a novel visual tracking approach that combines the NMI metric and the traditional SSD metric within a gradient-based optimization frame, which can be used for direct visual odometry and SLAM. We firstly derivate the closed form expression for first- and second-order analytical NMI derivatives under the assumption of rigid-body transformations, which then can be used by subsequent Newton-like optimization methods. Then we develop a robust tracking scheme that utilizes the robustness of NMI metric while keeping the optimization characteristics of SSD-based Lucas-Kanade (LK) tracking methods. To validate the robustness and accuracy of the proposed approach, several experiments are performed on synthetic datasets as well as real image datasets. The experimental results demonstrate that our approach can provide fast, accurate pose estimation and obtain better tracking performance over standard SSD-based methods in most cases.

AB - This paper presents a novel visual tracking approach that combines the NMI metric and the traditional SSD metric within a gradient-based optimization frame, which can be used for direct visual odometry and SLAM. We firstly derivate the closed form expression for first- and second-order analytical NMI derivatives under the assumption of rigid-body transformations, which then can be used by subsequent Newton-like optimization methods. Then we develop a robust tracking scheme that utilizes the robustness of NMI metric while keeping the optimization characteristics of SSD-based Lucas-Kanade (LK) tracking methods. To validate the robustness and accuracy of the proposed approach, several experiments are performed on synthetic datasets as well as real image datasets. The experimental results demonstrate that our approach can provide fast, accurate pose estimation and obtain better tracking performance over standard SSD-based methods in most cases.

KW - Direct visual tracking

KW - Nonlinear optimization

KW - Normalized mutual information

KW - Sum of squared differences

UR - http://www.scopus.com/inward/record.url?scp=85059357461&partnerID=8YFLogxK

U2 - 10.1117/12.2500857

DO - 10.1117/12.2500857

M3 - Conference contribution

AN - SCOPUS:85059357461

T3 - Proceedings of SPIE - The International Society for Optical Engineering

BT - Optical Metrology and Inspection for Industrial Applications V

A2 - Yoshizawa, Toru

A2 - Zhang, Song

A2 - Han, Sen

A2 - Han, Sen

PB - SPIE

T2 - Optical Metrology and Inspection for Industrial Applications V 2018

Y2 - 11 October 2018 through 13 October 2018

ER -