An Accurate and Robust Method for Absolute Pose Estimation with UAV Using RANSAC
In this paper, we proposed an accurate and robust method for absolute pose estimation with UAV (unmanned aerial vehicle) using RANSAC (random sample consensus). Because the artificial 3D control points with high accuracy are time-consuming and the small point set may lead low measuring accuracy, we...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/22/15/5925 |
| _version_ | 1797432635957444608 |
|---|---|
| author | Kai Guo Hu Ye Xin Gao Honglin Chen |
| author_facet | Kai Guo Hu Ye Xin Gao Honglin Chen |
| author_sort | Kai Guo |
| collection | DOAJ |
| description | In this paper, we proposed an accurate and robust method for absolute pose estimation with UAV (unmanned aerial vehicle) using RANSAC (random sample consensus). Because the artificial 3D control points with high accuracy are time-consuming and the small point set may lead low measuring accuracy, we designed a customized UAV to efficiently obtain mass 3D points. A light source was mounted on the UAV and used as a 3D point. The position of the 3D point was given by RTK (real-time kinematic) mounted on the UAV, and the position of the corresponding 2D point was given by feature extraction. The 2D–3D point correspondences exhibited some outliers because of the failure of feature extraction, the error of RTK, and wrong matches. Hence, RANSAC was used to remove the outliers and obtain the coarse pose. Then, we proposed a method to refine the coarse pose, whose procedure was formulated as the optimization of a cost function about the reprojection error based on the error transferring model and gradient descent to refine it. Before that, normalization was given for all the valid 2D–3D point correspondences to improve the estimation accuracy. In addition, we manufactured a prototype of a UAV with RTK and light source to obtain mass 2D–3D point correspondences for real images. Lastly, we provided a thorough test using synthetic data and real images, compared with several state-of-the-art perspective-n-point solvers. Experimental results showed that, even with a high outlier ratio, our proposed method had better performance in terms of numerical stability, noise sensitivity, and computational speed. |
| first_indexed | 2024-03-09T10:04:28Z |
| format | Article |
| id | doaj.art-77e9464e211e4e0c8db29c89418e182a |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-09T10:04:28Z |
| publishDate | 2022-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-77e9464e211e4e0c8db29c89418e182a2023-12-01T23:11:00ZengMDPI AGSensors1424-82202022-08-012215592510.3390/s22155925An Accurate and Robust Method for Absolute Pose Estimation with UAV Using RANSACKai Guo0Hu Ye1Xin Gao2Honglin Chen3Northwest Institute of Nuclear Technology, Xi’an 710024, ChinaNorthwest Institute of Nuclear Technology, Xi’an 710024, ChinaNorthwest Institute of Nuclear Technology, Xi’an 710024, ChinaNorthwest Institute of Nuclear Technology, Xi’an 710024, ChinaIn this paper, we proposed an accurate and robust method for absolute pose estimation with UAV (unmanned aerial vehicle) using RANSAC (random sample consensus). Because the artificial 3D control points with high accuracy are time-consuming and the small point set may lead low measuring accuracy, we designed a customized UAV to efficiently obtain mass 3D points. A light source was mounted on the UAV and used as a 3D point. The position of the 3D point was given by RTK (real-time kinematic) mounted on the UAV, and the position of the corresponding 2D point was given by feature extraction. The 2D–3D point correspondences exhibited some outliers because of the failure of feature extraction, the error of RTK, and wrong matches. Hence, RANSAC was used to remove the outliers and obtain the coarse pose. Then, we proposed a method to refine the coarse pose, whose procedure was formulated as the optimization of a cost function about the reprojection error based on the error transferring model and gradient descent to refine it. Before that, normalization was given for all the valid 2D–3D point correspondences to improve the estimation accuracy. In addition, we manufactured a prototype of a UAV with RTK and light source to obtain mass 2D–3D point correspondences for real images. Lastly, we provided a thorough test using synthetic data and real images, compared with several state-of-the-art perspective-n-point solvers. Experimental results showed that, even with a high outlier ratio, our proposed method had better performance in terms of numerical stability, noise sensitivity, and computational speed.https://www.mdpi.com/1424-8220/22/15/5925pose estimationRANSACperspective-n-pointUAVhigh outlier ratio |
| spellingShingle | Kai Guo Hu Ye Xin Gao Honglin Chen An Accurate and Robust Method for Absolute Pose Estimation with UAV Using RANSAC Sensors pose estimation RANSAC perspective-n-point UAV high outlier ratio |
| title | An Accurate and Robust Method for Absolute Pose Estimation with UAV Using RANSAC |
| title_full | An Accurate and Robust Method for Absolute Pose Estimation with UAV Using RANSAC |
| title_fullStr | An Accurate and Robust Method for Absolute Pose Estimation with UAV Using RANSAC |
| title_full_unstemmed | An Accurate and Robust Method for Absolute Pose Estimation with UAV Using RANSAC |
| title_short | An Accurate and Robust Method for Absolute Pose Estimation with UAV Using RANSAC |
| title_sort | accurate and robust method for absolute pose estimation with uav using ransac |
| topic | pose estimation RANSAC perspective-n-point UAV high outlier ratio |
| url | https://www.mdpi.com/1424-8220/22/15/5925 |
| work_keys_str_mv | AT kaiguo anaccurateandrobustmethodforabsoluteposeestimationwithuavusingransac AT huye anaccurateandrobustmethodforabsoluteposeestimationwithuavusingransac AT xingao anaccurateandrobustmethodforabsoluteposeestimationwithuavusingransac AT honglinchen anaccurateandrobustmethodforabsoluteposeestimationwithuavusingransac AT kaiguo accurateandrobustmethodforabsoluteposeestimationwithuavusingransac AT huye accurateandrobustmethodforabsoluteposeestimationwithuavusingransac AT xingao accurateandrobustmethodforabsoluteposeestimationwithuavusingransac AT honglinchen accurateandrobustmethodforabsoluteposeestimationwithuavusingransac |