Uncertainty Quantification of Lucas Kanade Feature Track and Application to Visual Odometry Conference Paper

abstract

• 2017 IEEE. An uncertainty quantification approach to estimate the errors incurred by the Kanade Lucas Tomasi (KLT) feature tracking algorithm is presented. The covariance analysis is based on the linearized sensitivity calculations of the KLT algorithm. Track uncertainty thus computed is utilized to quantify the errors associated with feature based relative pose estimation algorithms. This paper also show that the uncertainty analysis result can serve as a mean to measures reliability of feature correspondences. Proposed technique show that a large amount of outlier can be ejected effectively, and thus improve the efficiency of iterative method such as RANSAC.

name of conference

• 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)

authors

• Majji, Manoranjan

published proceedings

• 2017 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION WORKSHOPS (CVPRW)

author list (cited authors)

• Wong, X. I., & Majji, M.

citation count

• 5

complete list of authors

• Wong, Xue Iuan||Majji, Manoranjan

publication date

• July 2017

publisher

• Institute of Electrical and Electronics Engineers (IEEE)  Publisher

published in

• Conference on Computer Vision and Pattern Recognition Workshops IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Workshops  Journal

keywords

• 40 Engineering
• 4007 Control Engineering, Mechatronics And Robotics

Digital Object Identifier (DOI)

• 10.1109/CVPRW.2017.131

International Standard Book Number (ISBN) 13

• 9781538607336

start page

• 950

end page

• 958

volume

• 2017-July

URL

• http://dx.doi.org/10.1109/cvprw.2017.131