CONTINUOUS BIM ALIGNMENT FOR MIXED REALITY VISUALISATION
Several methods exist that can be used to perform initial alignment of Building information models (BIMs) to the real building for Mixed Reality (MR) applications, such as marker-based or markerless visual methods, but this alignment is susceptible to drift over time. The existing model-based method...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Copernicus Publications
2023-12-01
|
| Series: | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| Online Access: | https://isprs-annals.copernicus.org/articles/X-1-W1-2023/279/2023/isprs-annals-X-1-W1-2023-279-2023.pdf |
| _version_ | 1827594852777328640 |
|---|---|
| author | M. Radanovic M. Radanovic K. Khoshelham K. Khoshelham C. S. Fraser D. Acharya |
| author_facet | M. Radanovic M. Radanovic K. Khoshelham K. Khoshelham C. S. Fraser D. Acharya |
| author_sort | M. Radanovic |
| collection | DOAJ |
| description | Several methods exist that can be used to perform initial alignment of Building information models (BIMs) to the real building for Mixed Reality (MR) applications, such as marker-based or markerless visual methods, but this alignment is susceptible to drift over time. The existing model-based methods that can be used to maintain this alignment have multiple limitations, such as the use of iterative processes and poor performance in environments with either too many or not enough lines. To address these issues, we propose an end-to-end trainable Convolutional Neural Network (CNN) that takes a real and synthetic BIM image pair as input to regress the 6 DoF relative camera pose difference between them directly. By correcting the relative pose error we are able to considerably improve the alignment of the BIM to the real building. Furthermore, the results of our experiments demonstrate good performance in a challenging environment and high resilience to domain shift between synthetic and real images. A high localisation accuracy of approximately 7.0 cm and 0.9° is achieved which indicates the method can be used to reduce the camera tracking drift for MR applications. |
| first_indexed | 2024-03-09T02:43:18Z |
| format | Article |
| id | doaj.art-6c356809d6ac450e9c792f552a524822 |
| institution | Directory Open Access Journal |
| issn | 2194-9042 2194-9050 |
| language | English |
| last_indexed | 2024-03-09T02:43:18Z |
| publishDate | 2023-12-01 |
| publisher | Copernicus Publications |
| record_format | Article |
| series | ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| spelling | doaj.art-6c356809d6ac450e9c792f552a5248222023-12-06T00:10:08ZengCopernicus PublicationsISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences2194-90422194-90502023-12-01X-1-W1-202327928610.5194/isprs-annals-X-1-W1-2023-279-2023CONTINUOUS BIM ALIGNMENT FOR MIXED REALITY VISUALISATIONM. Radanovic0M. Radanovic1K. Khoshelham2K. Khoshelham3C. S. Fraser4D. Acharya5Building 4.0 CRC, Caulfield East, Victoria 3145, AustraliaDepartment of Infrastructure Engineering, The University of Melbourne, Parkville, Victoria 3010, AustraliaBuilding 4.0 CRC, Caulfield East, Victoria 3145, AustraliaDepartment of Infrastructure Engineering, The University of Melbourne, Parkville, Victoria 3010, AustraliaDepartment of Infrastructure Engineering, The University of Melbourne, Parkville, Victoria 3010, AustraliaGeospatial Science, RMIT University, Melbourne, Victoria 3000, AustraliaSeveral methods exist that can be used to perform initial alignment of Building information models (BIMs) to the real building for Mixed Reality (MR) applications, such as marker-based or markerless visual methods, but this alignment is susceptible to drift over time. The existing model-based methods that can be used to maintain this alignment have multiple limitations, such as the use of iterative processes and poor performance in environments with either too many or not enough lines. To address these issues, we propose an end-to-end trainable Convolutional Neural Network (CNN) that takes a real and synthetic BIM image pair as input to regress the 6 DoF relative camera pose difference between them directly. By correcting the relative pose error we are able to considerably improve the alignment of the BIM to the real building. Furthermore, the results of our experiments demonstrate good performance in a challenging environment and high resilience to domain shift between synthetic and real images. A high localisation accuracy of approximately 7.0 cm and 0.9° is achieved which indicates the method can be used to reduce the camera tracking drift for MR applications.https://isprs-annals.copernicus.org/articles/X-1-W1-2023/279/2023/isprs-annals-X-1-W1-2023-279-2023.pdf |
| spellingShingle | M. Radanovic M. Radanovic K. Khoshelham K. Khoshelham C. S. Fraser D. Acharya CONTINUOUS BIM ALIGNMENT FOR MIXED REALITY VISUALISATION ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences |
| title | CONTINUOUS BIM ALIGNMENT FOR MIXED REALITY VISUALISATION |
| title_full | CONTINUOUS BIM ALIGNMENT FOR MIXED REALITY VISUALISATION |
| title_fullStr | CONTINUOUS BIM ALIGNMENT FOR MIXED REALITY VISUALISATION |
| title_full_unstemmed | CONTINUOUS BIM ALIGNMENT FOR MIXED REALITY VISUALISATION |
| title_short | CONTINUOUS BIM ALIGNMENT FOR MIXED REALITY VISUALISATION |
| title_sort | continuous bim alignment for mixed reality visualisation |
| url | https://isprs-annals.copernicus.org/articles/X-1-W1-2023/279/2023/isprs-annals-X-1-W1-2023-279-2023.pdf |
| work_keys_str_mv | AT mradanovic continuousbimalignmentformixedrealityvisualisation AT mradanovic continuousbimalignmentformixedrealityvisualisation AT kkhoshelham continuousbimalignmentformixedrealityvisualisation AT kkhoshelham continuousbimalignmentformixedrealityvisualisation AT csfraser continuousbimalignmentformixedrealityvisualisation AT dacharya continuousbimalignmentformixedrealityvisualisation |