Robust and Efficient CPU-Based RGB-D Scene Reconstruction
3D scene reconstruction is an important topic in computer vision. A complete scene is reconstructed from views acquired along the camera trajectory, each view containing a small part of the scene. Tracking in textureless scenes is well known to be a Gordian knot of camera tracking, and how to obtain...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/18/11/3652 |
| _version_ | 1818014667587452928 |
|---|---|
| author | Jianwei Li Wei Gao Heping Li Fulin Tang Yihong Wu |
| author_facet | Jianwei Li Wei Gao Heping Li Fulin Tang Yihong Wu |
| author_sort | Jianwei Li |
| collection | DOAJ |
| description | 3D scene reconstruction is an important topic in computer vision. A complete scene is reconstructed from views acquired along the camera trajectory, each view containing a small part of the scene. Tracking in textureless scenes is well known to be a Gordian knot of camera tracking, and how to obtain accurate 3D models quickly is a major challenge for existing systems. For the application of robotics, we propose a robust CPU-based approach to reconstruct indoor scenes efficiently with a consumer RGB-D camera. The proposed approach bridges feature-based camera tracking and volumetric-based data integration together and has a good reconstruction performance in terms of both robustness and efficiency. The key points in our approach include: (i) a robust and fast camera tracking method combining points and edges, which improves tracking stability in textureless scenes; (ii) an efficient data fusion strategy to select camera views and integrate RGB-D images on multiple scales, which enhances the efficiency of volumetric integration; (iii) a novel RGB-D scene reconstruction system, which can be quickly implemented on a standard CPU. Experimental results demonstrate that our approach reconstructs scenes with higher robustness and efficiency compared to state-of-the-art reconstruction systems. |
| first_indexed | 2024-04-14T06:47:17Z |
| format | Article |
| id | doaj.art-15c32c170ba24d12b329b4658ba787a0 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T06:47:17Z |
| publishDate | 2018-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-15c32c170ba24d12b329b4658ba787a02022-12-22T02:07:07ZengMDPI AGSensors1424-82202018-10-011811365210.3390/s18113652s18113652Robust and Efficient CPU-Based RGB-D Scene ReconstructionJianwei Li0Wei Gao1Heping Li2Fulin Tang3Yihong Wu4National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, ChinaNational Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing 100190, China3D scene reconstruction is an important topic in computer vision. A complete scene is reconstructed from views acquired along the camera trajectory, each view containing a small part of the scene. Tracking in textureless scenes is well known to be a Gordian knot of camera tracking, and how to obtain accurate 3D models quickly is a major challenge for existing systems. For the application of robotics, we propose a robust CPU-based approach to reconstruct indoor scenes efficiently with a consumer RGB-D camera. The proposed approach bridges feature-based camera tracking and volumetric-based data integration together and has a good reconstruction performance in terms of both robustness and efficiency. The key points in our approach include: (i) a robust and fast camera tracking method combining points and edges, which improves tracking stability in textureless scenes; (ii) an efficient data fusion strategy to select camera views and integrate RGB-D images on multiple scales, which enhances the efficiency of volumetric integration; (iii) a novel RGB-D scene reconstruction system, which can be quickly implemented on a standard CPU. Experimental results demonstrate that our approach reconstructs scenes with higher robustness and efficiency compared to state-of-the-art reconstruction systems.https://www.mdpi.com/1424-8220/18/11/36523D reconstructioncamera trackingvolumetric integrationsimultaneous localization and mapping (SLAM) |
| spellingShingle | Jianwei Li Wei Gao Heping Li Fulin Tang Yihong Wu Robust and Efficient CPU-Based RGB-D Scene Reconstruction Sensors 3D reconstruction camera tracking volumetric integration simultaneous localization and mapping (SLAM) |
| title | Robust and Efficient CPU-Based RGB-D Scene Reconstruction |
| title_full | Robust and Efficient CPU-Based RGB-D Scene Reconstruction |
| title_fullStr | Robust and Efficient CPU-Based RGB-D Scene Reconstruction |
| title_full_unstemmed | Robust and Efficient CPU-Based RGB-D Scene Reconstruction |
| title_short | Robust and Efficient CPU-Based RGB-D Scene Reconstruction |
| title_sort | robust and efficient cpu based rgb d scene reconstruction |
| topic | 3D reconstruction camera tracking volumetric integration simultaneous localization and mapping (SLAM) |
| url | https://www.mdpi.com/1424-8220/18/11/3652 |
| work_keys_str_mv | AT jianweili robustandefficientcpubasedrgbdscenereconstruction AT weigao robustandefficientcpubasedrgbdscenereconstruction AT hepingli robustandefficientcpubasedrgbdscenereconstruction AT fulintang robustandefficientcpubasedrgbdscenereconstruction AT yihongwu robustandefficientcpubasedrgbdscenereconstruction |