A novel image points matching method by intersecting into space for close-range photogrammetry
| Autor: | Ruan Guowei, Wei Wang, Bin Zhang, Yuhang Zhang, Chengli Zhang, Long Changyu, Li Tao, Liu Guangtong, Ziwen Wang |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Matching (graph theory)
business.industry Computer science Epipolar geometry Distortion (optics) ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION Process (computing) Bundle adjustment Image (mathematics) Constraint (information theory) Photogrammetry Computer Science::Computer Vision and Pattern Recognition Computer vision Artificial intelligence business |
| Zdroj: | 2019 International Conference on Optical Instruments and Technology: Optoelectronic Measurement Technology and Systems. |
| DOI: | 10.1117/12.2542374 |
| Popis: | Image points matching between multiple uncalibrated images has always been an important task in Close-range photogrammetry and difficulties are often experienced. Epipolar geometry constraint method is considered to be an effective way to solve this problem and it has been studied in detail. However, large amount of applications have shown that epipolar geometry is hard to be recovered accurately due to image distortion and positioning error, which leads to numerous mismatches when image points are distributed intensively. In order to solve this problem, an alternative image points matching technique to the epipolar geometry constraint method is investigated, which matches the image points combining with a bundle adjustment process and using their corresponding spatial collinear lines intersected on 3D space instead of finding on 2D epipolar line. In this paper, the matching principle and process of this method are described in detail. Experiment results and comparison with epipolar geometry constraint method are displayed, which verifies the flexibility and effectiveness of this method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|