journal article·2016-01-02

Feature-based 3D reconstruction of fabric by binocular stereo-vision

Pinghua Xu, Xuemei Ding, Rongwu Wang, Xiongying Wu

Publisher page

Abstract

Generally, image-based evaluation on the performance of textile appearance such as smoothness and pilling was interfered by fabric pattern, color, and illumination. In this paper, a new method was used to reconstruct a 3D surface of fabric based on image’s features which could eliminate the influence of surface texture. Concretely, two parallel-placed digital cameras were calibrated based on planar pattern and the captured binocular images were rectified through epipolar line. The feature points of binocular images were extracted by the Scale-Invariant Feature Transform which could detect and describe local features of images was insensitive to transformations and colors. Based on the similarity in descriptor and a geometric constraint, pairs of sparse matched points were detected and were regarded as the source points of diffusion regions. Remaining points of the overlapped areas were then matched based on normalized cross correlation in “best-first” principle. The outputs of the system included a surface disparity map and the space coordinate of fabric. The experimental results showed that the high-fidelity 3D fabric surface reconstructed by the new method was insusceptible to fabric structures, colors, fiber contents, etc., providing available solution for the further inspection on the performance of textile appearance.
Source: openalex_inverted_index · Quality: baseline

Research context

OpenAlex topics: Industrial Vision Systems and Defect Detection · Optical measurement and interference techniques · Color Science and Applications

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

References (16)

Show source-provided references
1. 10.1177/00405175050750010510.1177/004051750507500105 ↗
2. 10.1109/CVPR.2000.85494410.1109/CVPR.2000.854944 ↗
3. 10.1007/BF0232269510.1007/BF02322695 ↗
4. 10.1177/00405175010710051310.1177/004051750107100513 ↗
5. 10.1023/B:VISI.0000029664.99615.9410.1023/B:VISI.0000029664.99615.94 ↗
6. Mutch J. · 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. · 2006 · 1 · 1110.1109/CVPR.2006.200 ↗
7. 10.1177/004051751142453010.1177/0040517511424530 ↗
8. 10.1177/004051751039599910.1177/0040517510395999 ↗
9. Urbiola L. · Textile Research Journal · 2013 · 83 · 1648
10. 10.1186/gb-2002-3-7-research003410.1186/gb-2002-3-7-research0034 ↗
11. 10.1108/0955622001032490210.1108/09556220010324902 ↗
12. 10.1080/0040500950863131610.1080/00405009508631316 ↗
13. 10.1177/004051751141856410.1177/0040517511418564 ↗
14. 10.1177/00405175030730051310.1177/004051750307300513 ↗
15. 10.1177/004051750809049710.1177/0040517508090497 ↗
16. 10.1109/34.88871810.1109/34.888718 ↗