Fast and accurate multi‐view reconstruction by multi‐stage prioritised matching
In this study, the authors propose a multi‐view stereo reconstruction method which creates a three‐dimensional point cloud of a scene from multiple calibrated images captured from different viewpoints. The method is based on a prioritised match expansion technique, which starts from a sparse set of...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2015-08-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/iet-cvi.2014.0281 |
| _version_ | 1797684943900377088 |
|---|---|
| author | Markus Ylimäki Juho Kannala Jukka Holappa Sami S. Brandt Janne Heikkilä |
| author_facet | Markus Ylimäki Juho Kannala Jukka Holappa Sami S. Brandt Janne Heikkilä |
| author_sort | Markus Ylimäki |
| collection | DOAJ |
| description | In this study, the authors propose a multi‐view stereo reconstruction method which creates a three‐dimensional point cloud of a scene from multiple calibrated images captured from different viewpoints. The method is based on a prioritised match expansion technique, which starts from a sparse set of seed points, and iteratively expands them into neighbouring areas by using multiple expansion stages. Each seed point represents a surface patch and has a position and a surface normal vector. The location and surface normal of the seeds are optimised using a homography‐based local image alignment. The propagation of seeds is performed in a prioritised order in which the most promising seeds are expanded first and removed from the list of seeds. The first expansion stage proceeds until the list of seeds is empty. In the following expansion stages, the current reconstruction may be further expanded by finding new seeds near the boundaries of the current reconstruction. The prioritised expansion strategy allows efficient generation of accurate point clouds and their experiments show its benefits compared with non‐prioritised expansion. In addition, a comparison to the widely used patch‐based multi‐view stereo software shows that their method is significantly faster and produces more accurate and complete reconstructions. |
| first_indexed | 2024-03-12T00:37:08Z |
| format | Article |
| id | doaj.art-635f0cdfcd964f759bb8296686832e7a |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-03-12T00:37:08Z |
| publishDate | 2015-08-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-635f0cdfcd964f759bb8296686832e7a2023-09-15T09:33:33ZengWileyIET Computer Vision1751-96321751-96402015-08-019457658710.1049/iet-cvi.2014.0281Fast and accurate multi‐view reconstruction by multi‐stage prioritised matchingMarkus Ylimäki0Juho Kannala1Jukka Holappa2Sami S. Brandt3Janne Heikkilä4Department of Computer Science and EngineeringUniversity of OuluP.O. Box 4500Oulu90014FinlandDepartment of Computer Science and EngineeringUniversity of OuluP.O. Box 4500Oulu90014FinlandDepartment of Computer Science and EngineeringUniversity of OuluP.O. Box 4500Oulu90014FinlandDepartment of Computer ScienceUniversity of CopenhagenUniversitetsparken 12100CopenhagenDenmarkDepartment of Computer Science and EngineeringUniversity of OuluP.O. Box 4500Oulu90014FinlandIn this study, the authors propose a multi‐view stereo reconstruction method which creates a three‐dimensional point cloud of a scene from multiple calibrated images captured from different viewpoints. The method is based on a prioritised match expansion technique, which starts from a sparse set of seed points, and iteratively expands them into neighbouring areas by using multiple expansion stages. Each seed point represents a surface patch and has a position and a surface normal vector. The location and surface normal of the seeds are optimised using a homography‐based local image alignment. The propagation of seeds is performed in a prioritised order in which the most promising seeds are expanded first and removed from the list of seeds. The first expansion stage proceeds until the list of seeds is empty. In the following expansion stages, the current reconstruction may be further expanded by finding new seeds near the boundaries of the current reconstruction. The prioritised expansion strategy allows efficient generation of accurate point clouds and their experiments show its benefits compared with non‐prioritised expansion. In addition, a comparison to the widely used patch‐based multi‐view stereo software shows that their method is significantly faster and produces more accurate and complete reconstructions.https://doi.org/10.1049/iet-cvi.2014.0281homography-based local image alignmentsurface patchsurface normal vectorseed point representationiterative methodprioritised match expansion technique |
| spellingShingle | Markus Ylimäki Juho Kannala Jukka Holappa Sami S. Brandt Janne Heikkilä Fast and accurate multi‐view reconstruction by multi‐stage prioritised matching IET Computer Vision homography-based local image alignment surface patch surface normal vector seed point representation iterative method prioritised match expansion technique |
| title | Fast and accurate multi‐view reconstruction by multi‐stage prioritised matching |
| title_full | Fast and accurate multi‐view reconstruction by multi‐stage prioritised matching |
| title_fullStr | Fast and accurate multi‐view reconstruction by multi‐stage prioritised matching |
| title_full_unstemmed | Fast and accurate multi‐view reconstruction by multi‐stage prioritised matching |
| title_short | Fast and accurate multi‐view reconstruction by multi‐stage prioritised matching |
| title_sort | fast and accurate multi view reconstruction by multi stage prioritised matching |
| topic | homography-based local image alignment surface patch surface normal vector seed point representation iterative method prioritised match expansion technique |
| url | https://doi.org/10.1049/iet-cvi.2014.0281 |
| work_keys_str_mv | AT markusylimaki fastandaccuratemultiviewreconstructionbymultistageprioritisedmatching AT juhokannala fastandaccuratemultiviewreconstructionbymultistageprioritisedmatching AT jukkaholappa fastandaccuratemultiviewreconstructionbymultistageprioritisedmatching AT samisbrandt fastandaccuratemultiviewreconstructionbymultistageprioritisedmatching AT janneheikkila fastandaccuratemultiviewreconstructionbymultistageprioritisedmatching |