A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds

Three-dimensional structure-based localization aims to estimate the six-DOF camera pose of a query image by means of feature matches against a 3D Structure-from-Motion (SfM) point cloud. For city-scale SfM point clouds with tens of millions of points, it becomes more and more difficult to disambigua...

Full description

Saved in:
Bibliographic Details
Main Authors: Cheng, Wentao, Chen, Kan, Lin, Weisi, Goesele, Michael, Zhang, Xinfeng, Zhang, Yabin
Other Authors: School of Computer Science and Engineering
Format: Article
Language:English
Published: 2020
Subjects:
Online Access:https://hdl.handle.net/10356/137993
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-137993
record_format dspace
spelling sg-ntu-dr.10356-1379932020-09-26T21:52:24Z A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds Cheng, Wentao Chen, Kan Lin, Weisi Goesele, Michael Zhang, Xinfeng Zhang, Yabin School of Computer Science and Engineering Fraunhofer Singapore Engineering::Electrical and electronic engineering City-scale Localization Outlier Filter Three-dimensional structure-based localization aims to estimate the six-DOF camera pose of a query image by means of feature matches against a 3D Structure-from-Motion (SfM) point cloud. For city-scale SfM point clouds with tens of millions of points, it becomes more and more difficult to disambiguate matches. Therefore, a 3D structure-based localization method, which can efficiently handle matches with very large outlier ratios, is needed. We propose a two-stage outlier filtering framework for city-scale localization that leverages both visibility and geometry intrinsics of the SfM point clouds. First, we propose a visibility-based outlier filter, which is based on a bipartite visibility graph, to filter outliers on a coarse level. Second, we apply a geometry-based outlier filter to generate a set of fine-grained matches with a novel data-driven geometrical constraint for efficient inlier evaluation. The proposed two-stage outlier filtering framework only relies on the intrinsic information of the SfM point cloud. It is thus widely applicable to be embedded into the existing localization approaches. The experimental results on two real-world datasets demonstrate the effectiveness of the proposed two-stage outlier filtering framework for city-scale localization. NRF (Natl Research Foundation, S’pore) Accepted version 2020-04-21T08:00:51Z 2020-04-21T08:00:51Z 2019 Journal Article Cheng, W., Chen, K., Lin, W., Goesele, M., Zhang, X., & Zhang, Y. (2019). A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds. IEEE Transactions on Image Processing, 28(10), 4857-4869. doi:10.1109/TIP.2019.2910662 1941-0042 https://hdl.handle.net/10356/137993 10.1109/TIP.2019.2910662 10 28 4857 4869 en IEEE Transactions on Image Processing © 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/TIP.2019.2910662 application/pdf
institution Nanyang Technological University
building NTU Library
country Singapore
collection DR-NTU
language English
topic Engineering::Electrical and electronic engineering
City-scale Localization
Outlier Filter
spellingShingle Engineering::Electrical and electronic engineering
City-scale Localization
Outlier Filter
Cheng, Wentao
Chen, Kan
Lin, Weisi
Goesele, Michael
Zhang, Xinfeng
Zhang, Yabin
A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds
description Three-dimensional structure-based localization aims to estimate the six-DOF camera pose of a query image by means of feature matches against a 3D Structure-from-Motion (SfM) point cloud. For city-scale SfM point clouds with tens of millions of points, it becomes more and more difficult to disambiguate matches. Therefore, a 3D structure-based localization method, which can efficiently handle matches with very large outlier ratios, is needed. We propose a two-stage outlier filtering framework for city-scale localization that leverages both visibility and geometry intrinsics of the SfM point clouds. First, we propose a visibility-based outlier filter, which is based on a bipartite visibility graph, to filter outliers on a coarse level. Second, we apply a geometry-based outlier filter to generate a set of fine-grained matches with a novel data-driven geometrical constraint for efficient inlier evaluation. The proposed two-stage outlier filtering framework only relies on the intrinsic information of the SfM point cloud. It is thus widely applicable to be embedded into the existing localization approaches. The experimental results on two real-world datasets demonstrate the effectiveness of the proposed two-stage outlier filtering framework for city-scale localization.
author2 School of Computer Science and Engineering
author_facet School of Computer Science and Engineering
Cheng, Wentao
Chen, Kan
Lin, Weisi
Goesele, Michael
Zhang, Xinfeng
Zhang, Yabin
format Article
author Cheng, Wentao
Chen, Kan
Lin, Weisi
Goesele, Michael
Zhang, Xinfeng
Zhang, Yabin
author_sort Cheng, Wentao
title A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds
title_short A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds
title_full A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds
title_fullStr A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds
title_full_unstemmed A two-stage outlier filtering framework for city-scale localization using 3D SfM point clouds
title_sort two-stage outlier filtering framework for city-scale localization using 3d sfm point clouds
publishDate 2020
url https://hdl.handle.net/10356/137993
_version_ 1681059636180942848