A platform for research: civil engineering, architecture and urbanism
A platform for research: civil engineering, architecture and urbanism
Automatic point cloud coarse registration using geometric keypoint descriptors for indoor scenes
https://orcid.org/0000-0003-1174-7401
https://orcid.org/0000-0003-0320-4191
AbstractLaser scanner is a powerful tool which helps in the control of as-built construction projects. The automatic registration of the acquired point clouds without the use of artificial targets is a relevant subject in current investigation. This work focuses on extracting descriptive keypoints from geometric point descriptors, in such a way that keypoints are suitable to perform 4 Points Congruent Sets coarse registration without artificial targets. These keypoints are obtained via 3D Difference of Gaussians over geometric scalar values of the points resulting in characteristic salient features. The registration procedure reduced the RMSE around 2cm during coarse registration comparing against state of the art algorithms. These RMSE values allow the subsequence use of fine registration via ICP completing the automation of the registration process. Geometric keypoints are demonstrated to be a suitable way to obtain automatic point cloud registration and open the way to future developments.
HighlightsFully automatic coarse registration for indoor scenes No prior knowledge of the scanner positions is needed for coarse registration. Use of geometric point descriptors as the basis for keypoint extraction Keypoint extraction is performed with reliable 3D keypoint detectors. Coarse registration performed well to serve as input of fine registration algorithms.
Automatic point cloud coarse registration using geometric keypoint descriptors for indoor scenes
https://orcid.org/0000-0003-1174-7401
https://orcid.org/0000-0003-0320-4191
AbstractLaser scanner is a powerful tool which helps in the control of as-built construction projects. The automatic registration of the acquired point clouds without the use of artificial targets is a relevant subject in current investigation. This work focuses on extracting descriptive keypoints from geometric point descriptors, in such a way that keypoints are suitable to perform 4 Points Congruent Sets coarse registration without artificial targets. These keypoints are obtained via 3D Difference of Gaussians over geometric scalar values of the points resulting in characteristic salient features. The registration procedure reduced the RMSE around 2cm during coarse registration comparing against state of the art algorithms. These RMSE values allow the subsequence use of fine registration via ICP completing the automation of the registration process. Geometric keypoints are demonstrated to be a suitable way to obtain automatic point cloud registration and open the way to future developments.
HighlightsFully automatic coarse registration for indoor scenes No prior knowledge of the scanner positions is needed for coarse registration. Use of geometric point descriptors as the basis for keypoint extraction Keypoint extraction is performed with reliable 3D keypoint detectors. Coarse registration performed well to serve as input of fine registration algorithms.
Automatic point cloud coarse registration using geometric keypoint descriptors for indoor scenes
https://orcid.org/0000-0003-1174-7401
https://orcid.org/0000-0003-0320-4191
AbstractLaser scanner is a powerful tool which helps in the control of as-built construction projects. The automatic registration of the acquired point clouds without the use of artificial targets is a relevant subject in current investigation. This work focuses on extracting descriptive keypoints from geometric point descriptors, in such a way that keypoints are suitable to perform 4 Points Congruent Sets coarse registration without artificial targets. These keypoints are obtained via 3D Difference of Gaussians over geometric scalar values of the points resulting in characteristic salient features. The registration procedure reduced the RMSE around 2cm during coarse registration comparing against state of the art algorithms. These RMSE values allow the subsequence use of fine registration via ICP completing the automation of the registration process. Geometric keypoints are demonstrated to be a suitable way to obtain automatic point cloud registration and open the way to future developments.
HighlightsFully automatic coarse registration for indoor scenes No prior knowledge of the scanner positions is needed for coarse registration. Use of geometric point descriptors as the basis for keypoint extraction Keypoint extraction is performed with reliable 3D keypoint detectors. Coarse registration performed well to serve as input of fine registration algorithms.
Automatic point cloud coarse registration using geometric keypoint descriptors for indoor scenes
Bueno, M. (author) / González-Jorge, H. (author) / Martínez-Sánchez, J. (author) / Lorenzo, H. (author)
Automation in Construction ; 81 ; 134-148
2017-06-10
15 pages
Article (Journal)
Electronic Resource
English
Automatic point cloud coarse registration using geometric keypoint descriptors for indoor scenes
| British Library Online Contents | 2017
Automatic 3D Surface Co-Registration Using Keypoint Matching
| Online Contents | 2017
Keypoint based autonomous registration of terrestrial laser point-clouds
| Online Contents | 2008
Keypoint based autonomous registration of terrestrial laser point-clouds
| Online Contents | 2008