Extrinsic Calibration for LiDAR–Camera Systems Using Direct 3D–2D Correspondences
Recent advances in the fields of driverless cars, intelligent robots and remote-sensing measurement have shown that the use of LiDAR fused with cameras can provide more comprehensive and reliable sensing of surroundings. However, since it is difficult to extract features from sparse LiDAR data to cr...
| Główni autorzy: | , , , |
|---|---|
| Format: | Artykuł |
| Język: | English |
| Wydane: |
MDPI AG
2022-11-01
|
| Seria: | Remote Sensing |
| Hasła przedmiotowe: | |
| Dostęp online: | https://www.mdpi.com/2072-4292/14/23/6082 |
| _version_ | 1827642550247227392 |
|---|---|
| author | Hao Yi Bo Liu Bin Zhao Enhai Liu |
| author_facet | Hao Yi Bo Liu Bin Zhao Enhai Liu |
| author_sort | Hao Yi |
| collection | DOAJ |
| description | Recent advances in the fields of driverless cars, intelligent robots and remote-sensing measurement have shown that the use of LiDAR fused with cameras can provide more comprehensive and reliable sensing of surroundings. However, since it is difficult to extract features from sparse LiDAR data to create 3D–2D correspondences, finding a method for accurate external calibration of all types of LiDAR with cameras has become a research hotspot. To solve this problem, this paper proposes a method to directly obtain the 3D–2D correspondences of LiDAR–camera systems to complete accurate calibration. In this method, a laser detector card is used as an auxiliary tool to directly obtain the correspondences between laser spots and image pixels, thus solving the problem of difficulty in extracting features from sparse LiDAR data. In addition, a two-stage framework from coarse to fine is designed in this paper, which not only can solve the perspective-n-point problem with observation errors, but also requires only four LiDAR data points and the corresponding pixel information for more accurate external calibration. Finally, extensive simulations and experimental results show that the effectiveness and accuracy of our method are better than existing methods. |
| first_indexed | 2024-03-09T17:33:49Z |
| format | Article |
| id | doaj.art-6bf2088d8aff42eeb51e7a87e5d8c694 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T17:33:49Z |
| publishDate | 2022-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6bf2088d8aff42eeb51e7a87e5d8c6942023-11-24T12:05:29ZengMDPI AGRemote Sensing2072-42922022-11-011423608210.3390/rs14236082Extrinsic Calibration for LiDAR–Camera Systems Using Direct 3D–2D CorrespondencesHao Yi0Bo Liu1Bin Zhao2Enhai Liu3Key Laboratory of Science and Technology on Space Optoelectronic Precision Measurement, Chinese Academy of Sciences, Chengdu 610209, ChinaKey Laboratory of Science and Technology on Space Optoelectronic Precision Measurement, Chinese Academy of Sciences, Chengdu 610209, ChinaKey Laboratory of Science and Technology on Space Optoelectronic Precision Measurement, Chinese Academy of Sciences, Chengdu 610209, ChinaKey Laboratory of Science and Technology on Space Optoelectronic Precision Measurement, Chinese Academy of Sciences, Chengdu 610209, ChinaRecent advances in the fields of driverless cars, intelligent robots and remote-sensing measurement have shown that the use of LiDAR fused with cameras can provide more comprehensive and reliable sensing of surroundings. However, since it is difficult to extract features from sparse LiDAR data to create 3D–2D correspondences, finding a method for accurate external calibration of all types of LiDAR with cameras has become a research hotspot. To solve this problem, this paper proposes a method to directly obtain the 3D–2D correspondences of LiDAR–camera systems to complete accurate calibration. In this method, a laser detector card is used as an auxiliary tool to directly obtain the correspondences between laser spots and image pixels, thus solving the problem of difficulty in extracting features from sparse LiDAR data. In addition, a two-stage framework from coarse to fine is designed in this paper, which not only can solve the perspective-n-point problem with observation errors, but also requires only four LiDAR data points and the corresponding pixel information for more accurate external calibration. Finally, extensive simulations and experimental results show that the effectiveness and accuracy of our method are better than existing methods.https://www.mdpi.com/2072-4292/14/23/6082LiDAR–camera systemextrinsic calibrationperspective-n-point |
| spellingShingle | Hao Yi Bo Liu Bin Zhao Enhai Liu Extrinsic Calibration for LiDAR–Camera Systems Using Direct 3D–2D Correspondences Remote Sensing LiDAR–camera system extrinsic calibration perspective-n-point |
| title | Extrinsic Calibration for LiDAR–Camera Systems Using Direct 3D–2D Correspondences |
| title_full | Extrinsic Calibration for LiDAR–Camera Systems Using Direct 3D–2D Correspondences |
| title_fullStr | Extrinsic Calibration for LiDAR–Camera Systems Using Direct 3D–2D Correspondences |
| title_full_unstemmed | Extrinsic Calibration for LiDAR–Camera Systems Using Direct 3D–2D Correspondences |
| title_short | Extrinsic Calibration for LiDAR–Camera Systems Using Direct 3D–2D Correspondences |
| title_sort | extrinsic calibration for lidar camera systems using direct 3d 2d correspondences |
| topic | LiDAR–camera system extrinsic calibration perspective-n-point |
| url | https://www.mdpi.com/2072-4292/14/23/6082 |
| work_keys_str_mv | AT haoyi extrinsiccalibrationforlidarcamerasystemsusingdirect3d2dcorrespondences AT boliu extrinsiccalibrationforlidarcamerasystemsusingdirect3d2dcorrespondences AT binzhao extrinsiccalibrationforlidarcamerasystemsusingdirect3d2dcorrespondences AT enhailiu extrinsiccalibrationforlidarcamerasystemsusingdirect3d2dcorrespondences |