journal article·2018-06-06Open access

Line Matching Based on Viewpoint-Invariance for Stereo Wide-Baseline Aerial Images

Qiang Wang, Haimeng Zhao, Zhenxin Zhang, Ximin Cui, Sana Ullah, Shanlin Sun, Fan Liu

Applied Sciences· Volume 8· Issue 6

Abstract

Line matching is the foundation of three-dimensional (3D) outline reconstruction for city buildings in aerial photogrammetry. Many existing studies have good line matching effects when dealing with aerial images with short baselines and small viewing angles. However, when faced with wide-baseline and large viewing-angle images, the matching effect drops sharply or even fails altogether. This paper deals with an efficient and simple method to achieve better line matching performance by a pair of wide-baseline aerial images, which make use of viewpoint-in variance to conduct line matching in rectified image spaces. Firstly, the perspective transformation relationship between the image plane and the geoid plane can be established from a Positioning and Orientation System (POS). Then, according to perspective projection matrices, two original images are separately rectified to conformal images, whose perspective deformation of large viewing-angle can be eliminated. Finally, the rectified images are used to conduct line matching, and the matched line segments obtained are back-projected to the original images. Four pairs of urban oblique aerial images are used to demonstrate the validity and efficiency of this method. Compared with line matching on original images, the number and the correctness of the matched line segments are greatly improved. Moreover, there is no loss of time efficiency. The proposed method can also be applied to general UAV (Unmanned Aerial Vehicle) aerial photogrammetry and introduced into matching for other geometric features, such as points, circles, curves, etc.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Robotics and Sensor-Based Localization · Advanced Image and Video Retrieval Techniques · 3D Surveying and Cultural Heritage

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

College of Geoscience and Surveying Engineering, China University of Mining &Technology, Beijing 100083, China

Key Laboratory of Unmanned Aerial Vehicle Telemetry, Guilin University of Aerospace Technology, Guilin 541004, China

Beijing Key Laboratory of Spatial Information Integration and Its Application, Peking University, Beijing 100871, China

Advanced Innovation Center for Imaging Technology, Capital Normal University, Beijing 100048, China

Funding

National Natural Science Foundation of China · The Key Research and Development Program of Guangxi

References (29)

Show source-provided references
1. ASIFT: A New Framework for Fully Affine Invariant Image Comparison10.1137/080732730 ↗
2. Xiao, X., and Zhang, C. (2013, January 25–29). Robust and rapid matching of oblique UAV images of urban area. Proceedings of the SPIE—The International Society for Optical Engineering, San Diego, CA, USA.10.1117/12.2030497 ↗
3. Tuytelaars, T. (2000, January 11–14). Wide baseline stereo matching based on local, affinely invariant regions. Proceedings of the 11th British Machine Vision Conference, Bristol, UK.10.5244/C.14.38 ↗
4. Relative orientation of image triples using straight linear features
5. Wang, Q., Yan, L., Sun, Y., Cui, X., Mortimer, H., and Li, Y. True orthophoto generation using line segment matches. Photogramm. Rec., 2018.10.1111/phor.12229 ↗
6. Zhang, Z., and Faugeras, O. (1990, January 16–21). Building a 3D world model with a mobile robot: 3D line segment representation and integration. Proceedings of the 10th IEE International Conference on Pattern Recognition, Atlantic City, NJ, USA.
7. 3D line segments reconstruction for building facades with line matching across multi-image with non-geometry constraint
8. The Triplet Measured by Aerial Camera Using Line Segments Line Matching-Based Relative Orientation Using Triplet Camera10.5194/isprsarchives-XL-4-W5-217-2015 ↗
9. Ok, A.Ö., Wegner, J.D., Heipke, C., Rottensteiner, F., Soergel, U., and Toprak, V. (2011). In-Strip Matching and Recons-truction of Line Segments from UHR Aerial Image Triplets. Photogrammetric Image Analysis, Springer.10.1007/978-3-642-24393-6_6 ↗
10. Bay, H., Ferraris, V., and Van Gool, L. (2005, January 20–25). Wide-baseline stereo matching with line segments. Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA.
11. The line segment match method for extracting road network from high-resolution satellite images10.1109/36.992826 ↗
12. MSLD: A robust descriptor for line matching10.1016/j.patcog.2008.08.035 ↗
13. Two-view line matching algorithm based on context and appearance in low-textured images10.1016/j.patcog.2014.11.018 ↗
14. Fan, B., Wu, F., and Hu, Z. (2010, January 13–18). Line matching leveraged by point correspondences. Proceedings of the 2010 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), San Diego, CA, USA.10.1109/CVPR.2010.5540186 ↗
15. Jia, Q., Gao, X., Fan, X., Luo, Z., Li, H., and Chen, Z. (2016). Novel Coplanar Line-Points Invariants for Robust Line Matching Across Views. European Conference on Computer Vision, Springer.10.1007/978-3-319-46484-8_36 ↗
16. Matching disparate views of planar surfaces using projective invariants10.1016/S0262-8856(99)00071-2 ↗
17. An efficient and robust line segment matching approach based on LBD descriptor and pairwise geometric consistency10.1016/j.jvcir.2013.05.006 ↗
18. Baillard, C., Schmid, C., Zisserman, A., and Fitzgibbon, A. (1999, January 8–10). Automatic line matching and 3D reconstruction of buildings from multiple views. Proceedings of the ISPRS Conference on Automatic Extraction of GIS Objects from Digital Imagery, Munich, Germany.
19. Wang, L., Neumann, U., and You, S. (October, January 29). Wide-baseline image matching using Line Signatures. Proceedings of the 2009 12th IEEE International Conference on Computer Vision, Kyoto, Japan.
20. Meltzer, J., and Soatto, S. (2008, January 23–28). Edge descriptors for robust wide-baseline correspondence. Proceedings of the 2008 IEEE Conference on Computer Vision and Pattern Recognition, CVPR, Anchorage, AK, USA.10.1109/CVPR.2008.4587684 ↗
21. Li, K., Yao, J., and Lu, X. (2014). Robust line matching based on ray-point-ray structure descriptor. Asian Conference on Computer Vision, Springer.
22. Hierarchical line matching based on line-junction-line structure descriptor and local homography estimation10.1016/j.neucom.2015.07.137 ↗
23. Line matching based on planar homography for stereo aerial images10.1016/j.isprsjprs.2014.12.003 ↗
24. Line matching using a disparity map in rectified image space for stereo aerial images10.1080/2150704X.2016.1184352 ↗
25. Hartley, R., and Zisserman, A. (2003). Multiple View Geometry in Computer Vision, Cambridge University Press.10.1017/CBO9780511811685 ↗
26. LSD: A line segment detector10.5201/ipol.2012.gjmr-lsd ↗
27. Constrained line-photogrammetric 3D reconstruction from stereopairs
28. Line-photogrammetric mathematical model for the reconstruction of polyhedral objects
29. Using horizontal and vertical building structure to constrain indirect sensor orientation10.1016/j.isprsjprs.2010.11.002 ↗