CoMask: Corresponding Mask-Based End-to-End Extrinsic Calibration of the Camera and LiDAR
The integration of the camera and LiDAR has played an important role in the field of autonomous driving, for example in visual–LiDAR SLAM and 3D environment fusion perception, which rely on precise geometrical extrinsic calibration. In this paper, we proposed a fully automatic end-to-end method base...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/12/1925 |
| _version_ | 1797565345885585408 |
|---|---|
| author | Lu Yin Bin Luo Wei Wang Huan Yu Chenjie Wang Chengyuan Li |
| author_facet | Lu Yin Bin Luo Wei Wang Huan Yu Chenjie Wang Chengyuan Li |
| author_sort | Lu Yin |
| collection | DOAJ |
| description | The integration of the camera and LiDAR has played an important role in the field of autonomous driving, for example in visual–LiDAR SLAM and 3D environment fusion perception, which rely on precise geometrical extrinsic calibration. In this paper, we proposed a fully automatic end-to-end method based on the 3D–2D corresponding mask (CoMask) to directly estimate the extrinsic parameters with high precision. Simple subtraction was applied to extract the candidate point cluster from the complex background, and then 3D LiDAR points located on checkerboard were selected and refined by spatial growth clustering. Once the distance transform of 2D checkerboard mask was generated, the extrinsic calibration of the two sensors could be converted to 3D–2D mask correspondence alignment. A simple but efficient strategy combining the genetic algorithm with the Levenberg–Marquardt method was used to solve the optimization problem globally without any initial estimates. Both simulated and realistic experiments showed that the proposed method could obtain accurate results without manual intervention, special environment setups, or prior initial parameters. Compared with the state of the art, our method has obvious advantages in accuracy, robustness, and noise resistance. Our code is open-source on GitHub. |
| first_indexed | 2024-03-10T19:10:51Z |
| format | Article |
| id | doaj.art-20799090ed39497c9a4643faecdcf9e0 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T19:10:51Z |
| publishDate | 2020-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-20799090ed39497c9a4643faecdcf9e02023-11-20T03:47:14ZengMDPI AGRemote Sensing2072-42922020-06-011212192510.3390/rs12121925CoMask: Corresponding Mask-Based End-to-End Extrinsic Calibration of the Camera and LiDARLu Yin0Bin Luo1Wei Wang2Huan Yu3Chenjie Wang4Chengyuan Li5State Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaState Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaState Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaWuhan InDriving Technology Co., Ltd., Innovation Building 1802, Hongshan District, Wuhan 430079, ChinaState Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaState Key Laboratory for Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, 129 Luoyu Road, Wuhan 430079, ChinaThe integration of the camera and LiDAR has played an important role in the field of autonomous driving, for example in visual–LiDAR SLAM and 3D environment fusion perception, which rely on precise geometrical extrinsic calibration. In this paper, we proposed a fully automatic end-to-end method based on the 3D–2D corresponding mask (CoMask) to directly estimate the extrinsic parameters with high precision. Simple subtraction was applied to extract the candidate point cluster from the complex background, and then 3D LiDAR points located on checkerboard were selected and refined by spatial growth clustering. Once the distance transform of 2D checkerboard mask was generated, the extrinsic calibration of the two sensors could be converted to 3D–2D mask correspondence alignment. A simple but efficient strategy combining the genetic algorithm with the Levenberg–Marquardt method was used to solve the optimization problem globally without any initial estimates. Both simulated and realistic experiments showed that the proposed method could obtain accurate results without manual intervention, special environment setups, or prior initial parameters. Compared with the state of the art, our method has obvious advantages in accuracy, robustness, and noise resistance. Our code is open-source on GitHub.https://www.mdpi.com/2072-4292/12/12/1925camera and LiDAR fusioncorresponding maskautomatic extractionextrinsic calibration |
| spellingShingle | Lu Yin Bin Luo Wei Wang Huan Yu Chenjie Wang Chengyuan Li CoMask: Corresponding Mask-Based End-to-End Extrinsic Calibration of the Camera and LiDAR Remote Sensing camera and LiDAR fusion corresponding mask automatic extraction extrinsic calibration |
| title | CoMask: Corresponding Mask-Based End-to-End Extrinsic Calibration of the Camera and LiDAR |
| title_full | CoMask: Corresponding Mask-Based End-to-End Extrinsic Calibration of the Camera and LiDAR |
| title_fullStr | CoMask: Corresponding Mask-Based End-to-End Extrinsic Calibration of the Camera and LiDAR |
| title_full_unstemmed | CoMask: Corresponding Mask-Based End-to-End Extrinsic Calibration of the Camera and LiDAR |
| title_short | CoMask: Corresponding Mask-Based End-to-End Extrinsic Calibration of the Camera and LiDAR |
| title_sort | comask corresponding mask based end to end extrinsic calibration of the camera and lidar |
| topic | camera and LiDAR fusion corresponding mask automatic extraction extrinsic calibration |
| url | https://www.mdpi.com/2072-4292/12/12/1925 |
| work_keys_str_mv | AT luyin comaskcorrespondingmaskbasedendtoendextrinsiccalibrationofthecameraandlidar AT binluo comaskcorrespondingmaskbasedendtoendextrinsiccalibrationofthecameraandlidar AT weiwang comaskcorrespondingmaskbasedendtoendextrinsiccalibrationofthecameraandlidar AT huanyu comaskcorrespondingmaskbasedendtoendextrinsiccalibrationofthecameraandlidar AT chenjiewang comaskcorrespondingmaskbasedendtoendextrinsiccalibrationofthecameraandlidar AT chengyuanli comaskcorrespondingmaskbasedendtoendextrinsiccalibrationofthecameraandlidar |