Orthogonality Index Based Optimal Feature Selection for Visual Odometry

The performance of visual odometry is dependent upon the quality of features selected for computing the frame-to-frame transformation. In order to ensure the quality of selected features, conventional approaches consider the spatial distribution of the selected features, in addition to their counts...

Full description

Saved in:
Bibliographic Details
Main Authors: Huu Hung Nguyen, Sukhan Lee
Format: Article
Language:English
Published: IEEE 2019-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/8712508/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846151990795567104
author Huu Hung Nguyen
Sukhan Lee
author_facet Huu Hung Nguyen
Sukhan Lee
author_sort Huu Hung Nguyen
collection DOAJ
description The performance of visual odometry is dependent upon the quality of features selected for computing the frame-to-frame transformation. In order to ensure the quality of selected features, conventional approaches consider the spatial distribution of the selected features, in addition to their counts and matching scores, in which a small number of features are selected randomly from each of the uniformly distributed buckets. In this paper, we show that features can be selected optimally, rather than randomly, using a well-defined mathematical formalism. The proposed method of optimal feature selection minimizes the degree of uncertainty in estimating the essential, fundamental, or homography matrix involved in visual odometry by maximizing the orthogonality index of individual equations and constraints associated with computation. We found that, at a constant noise level, the mean of the residual error and the variance of an estimated essential, fundamental, or homography matrix decrease monotonically with increasing orthogonality index. The simulation validates the increased accuracy of the feature selection based on the proposed orthogonality index compared with the conventional random selection. For instance, it enhances accuracy by as much as 35% when a small number of feature sets, say, 20 feature sets, are used. The experiments using the KITTI and Devon Island datasets further reinforce the performance enhancement of simulations by 9% and 20%, respectively.
format Article
id doaj-art-99964a0188df4b7c9a7d7332eab5bae3
institution Kabale University
issn 2169-3536
language English
publishDate 2019-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-99964a0188df4b7c9a7d7332eab5bae32024-11-27T00:00:16ZengIEEEIEEE Access2169-35362019-01-017622846229910.1109/ACCESS.2019.29161908712508Orthogonality Index Based Optimal Feature Selection for Visual OdometryHuu Hung Nguyen0https://orcid.org/0000-0002-7098-1102Sukhan Lee1Intelligent Systems Research Institute (ISRI), Sungkynkwan University, Suwon, South KoreaIntelligent Systems Research Institute (ISRI), Sungkynkwan University, Suwon, South KoreaThe performance of visual odometry is dependent upon the quality of features selected for computing the frame-to-frame transformation. In order to ensure the quality of selected features, conventional approaches consider the spatial distribution of the selected features, in addition to their counts and matching scores, in which a small number of features are selected randomly from each of the uniformly distributed buckets. In this paper, we show that features can be selected optimally, rather than randomly, using a well-defined mathematical formalism. The proposed method of optimal feature selection minimizes the degree of uncertainty in estimating the essential, fundamental, or homography matrix involved in visual odometry by maximizing the orthogonality index of individual equations and constraints associated with computation. We found that, at a constant noise level, the mean of the residual error and the variance of an estimated essential, fundamental, or homography matrix decrease monotonically with increasing orthogonality index. The simulation validates the increased accuracy of the feature selection based on the proposed orthogonality index compared with the conventional random selection. For instance, it enhances accuracy by as much as 35% when a small number of feature sets, say, 20 feature sets, are used. The experiments using the KITTI and Devon Island datasets further reinforce the performance enhancement of simulations by 9% and 20%, respectively.https://ieeexplore.ieee.org/document/8712508/Visual odometryego-motion estimationfeature selectionorthogonality index
spellingShingle Huu Hung Nguyen
Sukhan Lee
Orthogonality Index Based Optimal Feature Selection for Visual Odometry
IEEE Access
Visual odometry
ego-motion estimation
feature selection
orthogonality index
title Orthogonality Index Based Optimal Feature Selection for Visual Odometry
title_full Orthogonality Index Based Optimal Feature Selection for Visual Odometry
title_fullStr Orthogonality Index Based Optimal Feature Selection for Visual Odometry
title_full_unstemmed Orthogonality Index Based Optimal Feature Selection for Visual Odometry
title_short Orthogonality Index Based Optimal Feature Selection for Visual Odometry
title_sort orthogonality index based optimal feature selection for visual odometry
topic Visual odometry
ego-motion estimation
feature selection
orthogonality index
url https://ieeexplore.ieee.org/document/8712508/
work_keys_str_mv AT huuhungnguyen orthogonalityindexbasedoptimalfeatureselectionforvisualodometry
AT sukhanlee orthogonalityindexbasedoptimalfeatureselectionforvisualodometry