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...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/137993 |
| _version_ | 1824455977495166976 |
|---|---|
| author | Cheng, Wentao Chen, Kan Lin, Weisi Goesele, Michael Zhang, Xinfeng Zhang, Yabin |
| 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 |
| author_sort | Cheng, Wentao |
| collection | NTU |
| 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. |
| first_indexed | 2025-02-19T03:46:47Z |
| format | Journal Article |
| id | ntu-10356/137993 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:46:47Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | ntu-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 |
| 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 |
| title | 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_short | 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 |
| topic | Engineering::Electrical and electronic engineering City-scale Localization Outlier Filter |
| url | https://hdl.handle.net/10356/137993 |
| work_keys_str_mv | AT chengwentao atwostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT chenkan atwostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT linweisi atwostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT goeselemichael atwostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT zhangxinfeng atwostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT zhangyabin atwostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT chengwentao twostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT chenkan twostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT linweisi twostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT goeselemichael twostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT zhangxinfeng twostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds AT zhangyabin twostageoutlierfilteringframeworkforcityscalelocalizationusing3dsfmpointclouds |