Machine vision-based detection methods have been widely applied in the detection of aircraft skin damage. During drone inspection processes, a key step is to spatially locate high-resolution detailed images of aircraft skin from multiple angles onto a three-dimensional point cloud model of the aircraft. This relies on the rigid registration of image center position coordinate point cloud with the aircraft 3D point cloud. To address the issues of low accuracy and poor robustness encountered by existing registration algorithms when dealing with heterogeneous point clouds with significant differences in density and low overlap, this paper presents a novel cross-source point cloud registration network. The network integrates multi-scale information from the point cloud and employs an attention mechanism to identify representative overlapping points. First, the network achieves initial correspondences using the multi-scale geometric features and positional information of the point cloud. Then, an overlapping feature guidance module predicts the overlapping score of the point cloud. By utilizing information interaction through the attention mechanism, the network combines point overlapping scores with fused features to filter out representative overlapping points, achieving precise correspondences in the point cloud. The network employs weighted singular value decomposition (SVD) to estimate two sets of transformation matrices, yielding the relative pose parameters of the point cloud. Experiments were conducted in an unsupervised manner.The experimental results on the ModelNet40 dataset and the aero object dataset aircraft measurement data showed that, compared to other existing traditional and learning-based methods, this approach demonstrated excellent performance in terms of registration accuracy and robustness.
Acknowledgement
I would like to express my gratitude to the reviewers and editors.
Declaration of conflicting interests
The authors have no conflict of interests related to this publication.
| [1] |
YANDOUZI M, GAYDOS S, GUO D, et al. Aircraft skin restoration and evaluation. Journal of Thermal Spray Technology, 2014, 23(8): 1281-1290.
|
| [2] |
LI D R, LI M. Research advance and application prospect of unmanned aerial vehicle remote sensing system. Geomatics and Information Science of Wuhan University, 2014, 39(5): 505-513.
|
| [3] |
LU R S, WU A, ZHANG T D, et al. Review on automated optical (visual) inspection and its applications in defect detection. Acta Optica Sinica, 2018, 38(8): 0815002.
|
| [4] |
BESL P J, MCKAY N D. A method for registration of 3-D shapes. IEEE Trans Pattern Anal Mach Intell, 1992, 14: 239-256.
|
| [5] |
CENSI A. An ICP variant using a point-to-line metric//2008 IEEE International Conference on Robotics and Automation, May 19-23, 2008, Pasadena, CA, USA. New York: IEEE, 2008: 19-25.
|
| [6] |
YANG J L, LI H D, CAMPBELL D, et al. Go-ICP: a globally optimal solution to 3D ICP point-set registration. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016, 38(11): 2241-2254.
|
| [7] |
ZHOU Q Y, PARK J, KOLTUN V. Fast global registration//Computer Vision-ECCV 2016. Cham: Springer International Publishing, 2016: 766-782.
|
| [8] |
AOKI Y, GOFORTH H, SRIVATSAN R A, et al. PointNetLK: robust & efficient point cloud registration using PointNet//2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 15-20, 2019, Long Beach, CA, USA. New York: IEEE, 2020: 7156-7165.
|
| [9] |
SARODE V, LI X Q, GOFORTH H, et al. PCRNet: point cloud registration network using PointNet encoding. 2019: arXiv: 1908.07906.
|
| [10] |
CHARLES R Q, HAO S, MO K C, et al. PointNet: deep learning on point sets for 3D classification and segmentation//2017 IEEE Conference on Computer Vision and Pattern Recognition, July 21-26, 2017, Honolulu, HI, USA. New York: IEEE, 2017: 77-85.
|
| [11] |
LUCAS BD, KANADE T. An iterative image registration technique with an application to stereo vision. Morgan Kaufmann Publishers Inc, 1981: 674-679.
|
| [12] |
CHOE J, PARK C, RAMEAU F, et al. PointMixer: MLP-mixer forPoint cloud understanding. Computer Vision-ECCV 2022. Cham: Springer, 2022: 620-640.
|
| [13] |
WANG Y, SOLOMON J. Deep closest point: learning representations for point cloud registration//2019 IEEE/CVF International Conference on Computer Vision, October 27-November 2, 2019. Seoul, Korea. New York: IEEE, 2019: 3522-3531.
|
| [14] |
WANG Y, SUN Y B, LIU Z W, et al. Dynamic graph CNN for learning on point clouds. ACM Transactions on Graphics, 2019, 38(5): 1-12.
|
| [15] |
WANG Y, SOLOMON J. Prnet: Self-supervised learning for partial-to-partial registration//33rd Conference on Neural Information Processing Systems (NeurIPS), December 8-14, 2019, Vancouver, CANADA. La Jolla: NIPS, 2019.
|
| [16] |
JANG E, GU SS, POOLE B. Categorical reparameterization with gumbel-softmax. ArXiv, 2016, abs/1611.01144.
|
| [17] |
MA J Y, PENG C L, TIAN X, et al. DBDnet: a deep boosting strategy for image denoising. IEEE Transactions on Multimedia, 2022, 24: 3157-3168.
|
| [18] |
XU H, LIU S C, WANG G F, et al. OMNet: learning overlapping mask for partial-to-partial point cloud registration//2021 IEEE/CVF International Conference on Computer Vision, October 10-17, 2021, Montreal, QC, Canada. New York: IEEE, 2022: 3112-3121.
|
| [19] |
FU L H, SUN Y J, SUN C K, et al. Pose measurement without marked points based on prediction of overlapping area with hybrid features. Journal of Measurement Science and Instrumentation, 2023, 14(3): 253-262.
|
| [20] |
WANG P, ZHAO M H, SUN C K, et al. Research on image scanning and positioning system of aircraft skin. Chinese Journal of Sensors and Actuators, 2023, 36(11): 1706-1713.
|
| [21] |
WEI X, WANG M Y, LIN S J, et al. Multi-scale geometry-aware transformer for 3D point cloud classification. 2023: arXiv: 2304.05694.
|
| [22] |
VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need//31st Annual Conference on Neural Information Processing Systems (NIPS), December 4-9, 2017, Long Beach, CA. La Jolla: NIPS, 2017: 6000-6010.
|
| [23] |
KINGMA DP, BA J. Adam: A method for stochastic optimization. Computing research repository, 2014, abs/1412.6980.
|
| [24] |
WU Z R, SONG S R, KHOSLA A, et al. 3D ShapeNets: a deep representation for volumetric shapes//2015 IEEE Conference on Computer Vision and Pattern Recognition, June 7-12, 2015, Boston, MA, USA. New York: IEEE, 2015: 1912-1920.
|
| [25] |
YEW Z J, LEE G H. RPM-net: robust point matching using learned features//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition, June 13-19, 2020. Seattle, WA, USA. New York: IEEE, 2020: 11821-11830.
|
| [26] |
ZHOU Q Y, PARK J, KOLTUN V. Open3d: A modern library for 3d data processing. ArXiv, 2018, abs/1801.09847.
|
PDF
(8982KB)
