Feature Consistent Point Cloud Registration in Building Information Modeling
Point Cloud Registration contributes a lot to measuring, monitoring, and simulating in building information modeling (BIM). In BIM applications, the robustness and generalization of point cloud features are particularly important due to the huge differences in sampling environments. We notice two po...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/24/9694 |
| _version_ | 1797455407642312704 |
|---|---|
| author | Hengyu Jiang Pongsak Lasang Georges Nader Zheng Wu Takrit Tanasnitikul |
| author_facet | Hengyu Jiang Pongsak Lasang Georges Nader Zheng Wu Takrit Tanasnitikul |
| author_sort | Hengyu Jiang |
| collection | DOAJ |
| description | Point Cloud Registration contributes a lot to measuring, monitoring, and simulating in building information modeling (BIM). In BIM applications, the robustness and generalization of point cloud features are particularly important due to the huge differences in sampling environments. We notice two possible factors that may lead to poor generalization, the normal ambiguity of boundaries on hard edges leading to less accuracy in transformation; and the fact that existing methods focus on spatial transformation accuracy, leaving the advantages of feature matching unaddressed. In this work, we propose a boundary-encouraging local frame reference, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><mi>y</mi><mi>r</mi><mi>a</mi><mi>m</mi><mi>i</mi><mi>d</mi><mspace width="3.33333pt"></mspace><mi>F</mi><mi>e</mi><mi>a</mi><mi>t</mi><mi>u</mi><mi>r</mi><mi>e</mi><mspace width="3.33333pt"></mspace><mo>(</mo><mi>P</mi><mi>M</mi><mi>D</mi><mo>)</mo></mrow></semantics></math></inline-formula>, consisting of point-level, line-level, and mesh-level information to extract a more generalizing and continuous point cloud feature to encourage the knowledge of boundaries to overcome the normal ambiguity. Furthermore, instead of registration guided by spatial transformation accuracy alone, we suggest another supervision to extract consistent hybrid features. A large number of experiments have demonstrated the superiority of our PyramidNet (PMDNet), especially when the training (ModelNet40) and testing (BIM) sets are very different, PMDNet still achieves very high scalability. |
| first_indexed | 2024-03-09T15:52:59Z |
| format | Article |
| id | doaj.art-df445afe65bd4049bf27c5b3b7c140f4 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T15:52:59Z |
| publishDate | 2022-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-df445afe65bd4049bf27c5b3b7c140f42023-11-24T17:53:47ZengMDPI AGSensors1424-82202022-12-012224969410.3390/s22249694Feature Consistent Point Cloud Registration in Building Information ModelingHengyu Jiang0Pongsak Lasang1Georges Nader2Zheng Wu3Takrit Tanasnitikul4School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing 210000, ChinaPanasonic R&D Center Singapore, Singapore 469332, SingaporePanasonic R&D Center Singapore, Singapore 469332, SingaporePanasonic R&D Center Singapore, Singapore 469332, SingaporePanasonic R&D Center Singapore, Singapore 469332, SingaporePoint Cloud Registration contributes a lot to measuring, monitoring, and simulating in building information modeling (BIM). In BIM applications, the robustness and generalization of point cloud features are particularly important due to the huge differences in sampling environments. We notice two possible factors that may lead to poor generalization, the normal ambiguity of boundaries on hard edges leading to less accuracy in transformation; and the fact that existing methods focus on spatial transformation accuracy, leaving the advantages of feature matching unaddressed. In this work, we propose a boundary-encouraging local frame reference, the <inline-formula><math xmlns="http://www.w3.org/1998/Math/MathML" display="inline"><semantics><mrow><mi>P</mi><mi>y</mi><mi>r</mi><mi>a</mi><mi>m</mi><mi>i</mi><mi>d</mi><mspace width="3.33333pt"></mspace><mi>F</mi><mi>e</mi><mi>a</mi><mi>t</mi><mi>u</mi><mi>r</mi><mi>e</mi><mspace width="3.33333pt"></mspace><mo>(</mo><mi>P</mi><mi>M</mi><mi>D</mi><mo>)</mo></mrow></semantics></math></inline-formula>, consisting of point-level, line-level, and mesh-level information to extract a more generalizing and continuous point cloud feature to encourage the knowledge of boundaries to overcome the normal ambiguity. Furthermore, instead of registration guided by spatial transformation accuracy alone, we suggest another supervision to extract consistent hybrid features. A large number of experiments have demonstrated the superiority of our PyramidNet (PMDNet), especially when the training (ModelNet40) and testing (BIM) sets are very different, PMDNet still achieves very high scalability.https://www.mdpi.com/1424-8220/22/24/9694point cloud registrationbuilding information modelingfeature consistent |
| spellingShingle | Hengyu Jiang Pongsak Lasang Georges Nader Zheng Wu Takrit Tanasnitikul Feature Consistent Point Cloud Registration in Building Information Modeling Sensors point cloud registration building information modeling feature consistent |
| title | Feature Consistent Point Cloud Registration in Building Information Modeling |
| title_full | Feature Consistent Point Cloud Registration in Building Information Modeling |
| title_fullStr | Feature Consistent Point Cloud Registration in Building Information Modeling |
| title_full_unstemmed | Feature Consistent Point Cloud Registration in Building Information Modeling |
| title_short | Feature Consistent Point Cloud Registration in Building Information Modeling |
| title_sort | feature consistent point cloud registration in building information modeling |
| topic | point cloud registration building information modeling feature consistent |
| url | https://www.mdpi.com/1424-8220/22/24/9694 |
| work_keys_str_mv | AT hengyujiang featureconsistentpointcloudregistrationinbuildinginformationmodeling AT pongsaklasang featureconsistentpointcloudregistrationinbuildinginformationmodeling AT georgesnader featureconsistentpointcloudregistrationinbuildinginformationmodeling AT zhengwu featureconsistentpointcloudregistrationinbuildinginformationmodeling AT takrittanasnitikul featureconsistentpointcloudregistrationinbuildinginformationmodeling |