A Cluster-Based 3D Reconstruction System for Large-Scale Scenes
The reconstruction of realistic large-scale 3D scene models using aerial images or videos has significant applications in smart cities, surveying and mapping, the military and other fields. In the current state-of-the-art 3D-reconstruction pipeline, the massive scale of the scene and the enormous am...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-02-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/23/5/2377 |
| _version_ | 1797614353402298368 |
|---|---|
| author | Yao Li Yue Qi Chen Wang Yongtang Bao |
| author_facet | Yao Li Yue Qi Chen Wang Yongtang Bao |
| author_sort | Yao Li |
| collection | DOAJ |
| description | The reconstruction of realistic large-scale 3D scene models using aerial images or videos has significant applications in smart cities, surveying and mapping, the military and other fields. In the current state-of-the-art 3D-reconstruction pipeline, the massive scale of the scene and the enormous amount of input data are still considerable obstacles to the rapid reconstruction of large-scale 3D scene models. In this paper, we develop a professional system for large-scale 3D reconstruction. First, in the sparse point-cloud reconstruction stage, the computed matching relationships are used as the initial camera graph and divided into multiple subgraphs by a clustering algorithm. Multiple computational nodes execute the local structure-from-motion (SFM) technique, and local cameras are registered. Global camera alignment is achieved by integrating and optimizing all local camera poses. Second, in the dense point-cloud reconstruction stage, the adjacency information is decoupled from the pixel level by red-and-black checkerboard grid sampling. The optimal depth value is obtained using normalized cross-correlation (NCC). Additionally, during the mesh-reconstruction stage, feature-preserving mesh simplification, Laplace mesh-smoothing and mesh-detail-recovery methods are used to improve the quality of the mesh model. Finally, the above algorithms are integrated into our large-scale 3D-reconstruction system. Experiments show that the system can effectively improve the reconstruction speed of large-scale 3D scenes. |
| first_indexed | 2024-03-11T07:11:13Z |
| format | Article |
| id | doaj.art-325354a1bc464045b187e16dc5e1fe86 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-11T07:11:13Z |
| publishDate | 2023-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-325354a1bc464045b187e16dc5e1fe862023-11-17T08:33:55ZengMDPI AGSensors1424-82202023-02-01235237710.3390/s23052377A Cluster-Based 3D Reconstruction System for Large-Scale ScenesYao Li0Yue Qi1Chen Wang2Yongtang Bao3State Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, ChinaState Key Laboratory of Virtual Reality Technology and Systems, Beihang University, Beijing 100191, ChinaSchool of Computer Science and Engineering, Beijing Technology and Business University, Beijing 100048, ChinaCollege of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao 266590, ChinaThe reconstruction of realistic large-scale 3D scene models using aerial images or videos has significant applications in smart cities, surveying and mapping, the military and other fields. In the current state-of-the-art 3D-reconstruction pipeline, the massive scale of the scene and the enormous amount of input data are still considerable obstacles to the rapid reconstruction of large-scale 3D scene models. In this paper, we develop a professional system for large-scale 3D reconstruction. First, in the sparse point-cloud reconstruction stage, the computed matching relationships are used as the initial camera graph and divided into multiple subgraphs by a clustering algorithm. Multiple computational nodes execute the local structure-from-motion (SFM) technique, and local cameras are registered. Global camera alignment is achieved by integrating and optimizing all local camera poses. Second, in the dense point-cloud reconstruction stage, the adjacency information is decoupled from the pixel level by red-and-black checkerboard grid sampling. The optimal depth value is obtained using normalized cross-correlation (NCC). Additionally, during the mesh-reconstruction stage, feature-preserving mesh simplification, Laplace mesh-smoothing and mesh-detail-recovery methods are used to improve the quality of the mesh model. Finally, the above algorithms are integrated into our large-scale 3D-reconstruction system. Experiments show that the system can effectively improve the reconstruction speed of large-scale 3D scenes.https://www.mdpi.com/1424-8220/23/5/2377large-scale scenestructure from motionmulti-view stereomesh optimizationcluster systemlarge-scale 3D-reconstruction system |
| spellingShingle | Yao Li Yue Qi Chen Wang Yongtang Bao A Cluster-Based 3D Reconstruction System for Large-Scale Scenes Sensors large-scale scene structure from motion multi-view stereo mesh optimization cluster system large-scale 3D-reconstruction system |
| title | A Cluster-Based 3D Reconstruction System for Large-Scale Scenes |
| title_full | A Cluster-Based 3D Reconstruction System for Large-Scale Scenes |
| title_fullStr | A Cluster-Based 3D Reconstruction System for Large-Scale Scenes |
| title_full_unstemmed | A Cluster-Based 3D Reconstruction System for Large-Scale Scenes |
| title_short | A Cluster-Based 3D Reconstruction System for Large-Scale Scenes |
| title_sort | cluster based 3d reconstruction system for large scale scenes |
| topic | large-scale scene structure from motion multi-view stereo mesh optimization cluster system large-scale 3D-reconstruction system |
| url | https://www.mdpi.com/1424-8220/23/5/2377 |
| work_keys_str_mv | AT yaoli aclusterbased3dreconstructionsystemforlargescalescenes AT yueqi aclusterbased3dreconstructionsystemforlargescalescenes AT chenwang aclusterbased3dreconstructionsystemforlargescalescenes AT yongtangbao aclusterbased3dreconstructionsystemforlargescalescenes AT yaoli clusterbased3dreconstructionsystemforlargescalescenes AT yueqi clusterbased3dreconstructionsystemforlargescalescenes AT chenwang clusterbased3dreconstructionsystemforlargescalescenes AT yongtangbao clusterbased3dreconstructionsystemforlargescalescenes |