Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors
Establishing an effective local feature descriptor and using an accurate key point matching algorithm are two crucial tasks in recognizing and registering on the 3D point cloud. Because the descriptors need to keep enough descriptive ability against the effect of noise, occlusion, and incomplete reg...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/2/417 |
| _version_ | 1797490639424716800 |
|---|---|
| author | Jinlong Li Bingren Chen Meng Yuan Qian Zhao Lin Luo Xiaorong Gao |
| author_facet | Jinlong Li Bingren Chen Meng Yuan Qian Zhao Lin Luo Xiaorong Gao |
| author_sort | Jinlong Li |
| collection | DOAJ |
| description | Establishing an effective local feature descriptor and using an accurate key point matching algorithm are two crucial tasks in recognizing and registering on the 3D point cloud. Because the descriptors need to keep enough descriptive ability against the effect of noise, occlusion, and incomplete regions in the point cloud, a suitable key point matching algorithm can get more precise matched pairs. To obtain an effective descriptor, this paper proposes a Multi-Statistics Histogram Descriptor (MSHD) that combines spatial distribution and geometric attributes features. Furthermore, based on deep learning, we developed a new key point matching algorithm that could identify more corresponding point pairs than the existing methods. Our method is evaluated based on Stanford 3D dataset and four real component point cloud dataset from the train bottom. The experimental results demonstrate the superiority of MSHD because its descriptive ability and robustness to noise and mesh resolution are greater than those of carefully selected baselines (e.g., FPFH, SHOT, RoPS, and SpinImage descriptors). Importantly, it has been confirmed that the error of rotation and translation matrix is much smaller based on our key point matching algorithm, and the precise corresponding point pairs can be captured, resulting in enhanced recognition and registration for three-dimensional surface matching. |
| first_indexed | 2024-03-10T00:35:53Z |
| format | Article |
| id | doaj.art-e57b746b83414d2d88cc67d5a577f5ff |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T00:35:53Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-e57b746b83414d2d88cc67d5a577f5ff2023-11-23T15:18:17ZengMDPI AGSensors1424-82202022-01-0122241710.3390/s22020417Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram DescriptorsJinlong Li0Bingren Chen1Meng Yuan2Qian Zhao3Lin Luo4Xiaorong Gao5School of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, ChinaSchool of Physical Science and Technology, Southwest Jiaotong University, Chengdu 610031, ChinaEstablishing an effective local feature descriptor and using an accurate key point matching algorithm are two crucial tasks in recognizing and registering on the 3D point cloud. Because the descriptors need to keep enough descriptive ability against the effect of noise, occlusion, and incomplete regions in the point cloud, a suitable key point matching algorithm can get more precise matched pairs. To obtain an effective descriptor, this paper proposes a Multi-Statistics Histogram Descriptor (MSHD) that combines spatial distribution and geometric attributes features. Furthermore, based on deep learning, we developed a new key point matching algorithm that could identify more corresponding point pairs than the existing methods. Our method is evaluated based on Stanford 3D dataset and four real component point cloud dataset from the train bottom. The experimental results demonstrate the superiority of MSHD because its descriptive ability and robustness to noise and mesh resolution are greater than those of carefully selected baselines (e.g., FPFH, SHOT, RoPS, and SpinImage descriptors). Importantly, it has been confirmed that the error of rotation and translation matrix is much smaller based on our key point matching algorithm, and the precise corresponding point pairs can be captured, resulting in enhanced recognition and registration for three-dimensional surface matching.https://www.mdpi.com/1424-8220/22/2/417three-dimensional point cloudfeature descriptorkey point matching algorithm3D surface matching |
| spellingShingle | Jinlong Li Bingren Chen Meng Yuan Qian Zhao Lin Luo Xiaorong Gao Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors Sensors three-dimensional point cloud feature descriptor key point matching algorithm 3D surface matching |
| title | Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors |
| title_full | Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors |
| title_fullStr | Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors |
| title_full_unstemmed | Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors |
| title_short | Matching Algorithm for 3D Point Cloud Recognition and Registration Based on Multi-Statistics Histogram Descriptors |
| title_sort | matching algorithm for 3d point cloud recognition and registration based on multi statistics histogram descriptors |
| topic | three-dimensional point cloud feature descriptor key point matching algorithm 3D surface matching |
| url | https://www.mdpi.com/1424-8220/22/2/417 |
| work_keys_str_mv | AT jinlongli matchingalgorithmfor3dpointcloudrecognitionandregistrationbasedonmultistatisticshistogramdescriptors AT bingrenchen matchingalgorithmfor3dpointcloudrecognitionandregistrationbasedonmultistatisticshistogramdescriptors AT mengyuan matchingalgorithmfor3dpointcloudrecognitionandregistrationbasedonmultistatisticshistogramdescriptors AT qianzhao matchingalgorithmfor3dpointcloudrecognitionandregistrationbasedonmultistatisticshistogramdescriptors AT linluo matchingalgorithmfor3dpointcloudrecognitionandregistrationbasedonmultistatisticshistogramdescriptors AT xiaoronggao matchingalgorithmfor3dpointcloudrecognitionandregistrationbasedonmultistatisticshistogramdescriptors |