Automatic hierarchical registration of aerial and terrestrial image-based point clouds
Point cloud registration has been a major research challenge in recent years. In this paper, a novel hierarchical method is proposed for registering Aerial and Terrestrial image-based Point Clouds (APC & TPC). This registration aims to yield a complete and dense coverage on both top and side fac...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2018-01-01
|
| Series: | European Journal of Remote Sensing |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/22797254.2018.1444946 |
| _version_ | 1811233442271068160 |
|---|---|
| author | Amin Baghani Mohammad Javad Valadan Zoej Mehdi Mokhtarzade |
| author_facet | Amin Baghani Mohammad Javad Valadan Zoej Mehdi Mokhtarzade |
| author_sort | Amin Baghani |
| collection | DOAJ |
| description | Point cloud registration has been a major research challenge in recent years. In this paper, a novel hierarchical method is proposed for registering Aerial and Terrestrial image-based Point Clouds (APC & TPC). This registration aims to yield a complete and dense coverage on both top and side faces in urban areas. The main challenges, however, arise from their heterogeneous views and very low overlap as well as the high discrepancies in scale and three-dimensional rotations between the World Coordinate System (WCS) of APC and the Camera Coordinate System (CCS) of TPC. The proposed method begins by an innovative TPC-sufficient method to solve two rotations of TPC around x- and y-axis. After that, in horizontal registration phase, 2D façade lines were extracted from both datasets; and accordingly a novel polar parameterised mathematical model was extended for simultaneous robust matching and parameter estimation. Finally, vertical registration was done through calculating the dominant vertical shift between the points of the ground planes extracted from both datasets. The evaluation results in two different modes, which were conducted on two different urban datasets, showed the efficiency of the proposed method (RMSE error of 0.12 m/0.10 m in horizontal/vertical direction). |
| first_indexed | 2024-04-12T11:20:17Z |
| format | Article |
| id | doaj.art-9c74f3ef759c4fa1b2656cef5e64628a |
| institution | Directory Open Access Journal |
| issn | 2279-7254 |
| language | English |
| last_indexed | 2024-04-12T11:20:17Z |
| publishDate | 2018-01-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | European Journal of Remote Sensing |
| spelling | doaj.art-9c74f3ef759c4fa1b2656cef5e64628a2022-12-22T03:35:24ZengTaylor & Francis GroupEuropean Journal of Remote Sensing2279-72542018-01-0151143645610.1080/22797254.2018.14449461444946Automatic hierarchical registration of aerial and terrestrial image-based point cloudsAmin Baghani0Mohammad Javad Valadan Zoej1Mehdi Mokhtarzade2K. N. Toosi University of TechnologyK. N. Toosi University of TechnologyK. N. Toosi University of TechnologyPoint cloud registration has been a major research challenge in recent years. In this paper, a novel hierarchical method is proposed for registering Aerial and Terrestrial image-based Point Clouds (APC & TPC). This registration aims to yield a complete and dense coverage on both top and side faces in urban areas. The main challenges, however, arise from their heterogeneous views and very low overlap as well as the high discrepancies in scale and three-dimensional rotations between the World Coordinate System (WCS) of APC and the Camera Coordinate System (CCS) of TPC. The proposed method begins by an innovative TPC-sufficient method to solve two rotations of TPC around x- and y-axis. After that, in horizontal registration phase, 2D façade lines were extracted from both datasets; and accordingly a novel polar parameterised mathematical model was extended for simultaneous robust matching and parameter estimation. Finally, vertical registration was done through calculating the dominant vertical shift between the points of the ground planes extracted from both datasets. The evaluation results in two different modes, which were conducted on two different urban datasets, showed the efficiency of the proposed method (RMSE error of 0.12 m/0.10 m in horizontal/vertical direction).http://dx.doi.org/10.1080/22797254.2018.1444946Aerial point cloudterrestrial point cloudimage-based point cloudregistrationfaçade extractiontilt removal |
| spellingShingle | Amin Baghani Mohammad Javad Valadan Zoej Mehdi Mokhtarzade Automatic hierarchical registration of aerial and terrestrial image-based point clouds European Journal of Remote Sensing Aerial point cloud terrestrial point cloud image-based point cloud registration façade extraction tilt removal |
| title | Automatic hierarchical registration of aerial and terrestrial image-based point clouds |
| title_full | Automatic hierarchical registration of aerial and terrestrial image-based point clouds |
| title_fullStr | Automatic hierarchical registration of aerial and terrestrial image-based point clouds |
| title_full_unstemmed | Automatic hierarchical registration of aerial and terrestrial image-based point clouds |
| title_short | Automatic hierarchical registration of aerial and terrestrial image-based point clouds |
| title_sort | automatic hierarchical registration of aerial and terrestrial image based point clouds |
| topic | Aerial point cloud terrestrial point cloud image-based point cloud registration façade extraction tilt removal |
| url | http://dx.doi.org/10.1080/22797254.2018.1444946 |
| work_keys_str_mv | AT aminbaghani automatichierarchicalregistrationofaerialandterrestrialimagebasedpointclouds AT mohammadjavadvaladanzoej automatichierarchicalregistrationofaerialandterrestrialimagebasedpointclouds AT mehdimokhtarzade automatichierarchicalregistrationofaerialandterrestrialimagebasedpointclouds |