Search

Your search keyword '"Wanzhong Song"' showing total 4 results
Start Over Author "Wanzhong Song" Search Limiters Available in Library Collection
4 results on '"Wanzhong Song"'

1. Weakly Supervised Depth Estimation for 3D Imaging with Single Camera Fringe Projection Profilometry

Author

Chunqian Tan and Wanzhong Song

Subjects
fringe projection profilometry, depth estimation, weakly supervised learning, Chemical technology, TP1-1185
Abstract

Fringe projection profilometry (FPP) is widely used for high-accuracy 3D imaging. However, employing multiple sets of fringe patterns ensures 3D reconstruction accuracy while inevitably constraining the measurement speed. Conventional dual-frequency FPP reduces the number of fringe patterns for one reconstruction to six or fewer, but the highest period-number of fringe patterns generally is limited because of phase errors. Deep learning makes depth estimation from fringe images possible. Inspired by unsupervised monocular depth estimation, this paper proposes a novel, weakly supervised method of depth estimation for single-camera FPP. The trained network can estimate the depth from three frames of 64-period fringe images. The proposed method is more efficient in terms of fringe pattern efficiency by at least 50% compared to conventional FPP. The experimental results show that the method achieves competitive accuracy compared to the supervised method and is significantly superior to the conventional dual-frequency methods.

Published
2024
Full Text
View/download PDF

2. Self-supervised phase unwrapping in fringe projection profilometry

Author

Junzhe Lei, CHUNQIAN TAN, Xiaomin Gao, and Wanzhong Song

Subjects
FOS: Computer and information sciences, Computer Vision and Pattern Recognition (cs.CV), Image and Video Processing (eess.IV), Computer Science - Computer Vision and Pattern Recognition, FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Image and Video Processing
Abstract

Fast-speed and high-accuracy three-dimensional (3D) shape measurement has been the goal all along in fringe projection profilometry (FPP). The dual-frequency temporal phase unwrapping method (DF-TPU) is one of the prominent technologies to achieve this goal. However, the period number of the high-frequency pattern of existing DF-TPU approaches is usually limited by the inevitable phase errors, setting a limit to measurement accuracy. Deep-learning-based phase unwrapping methods for single-camera FPP usually require labeled data for training. In this letter, a novel self-supervised phase unwrapping method for single-camera FPP systems is proposed. The trained network can retrieve the absolute fringe order from one phase map of 64-period and overperform DF-TPU approaches in terms of depth accuracy. Experimental results demonstrate the validation of the proposed method on real scenes of motion blur, isolated objects, low reflectivity, and phase discontinuity.

Published
2023
Full Text
View/download PDF

3. Deep Learning-enabled Spatial Phase Unwrapping for 3D Measurement

Author

Wanzhong Song, Xiaolong Luo, Songlin Bai, Yu Li, and Zhihe Zhao

Subjects
FOS: Computer and information sciences, History, Polymers and Plastics, Computer Vision and Pattern Recognition (cs.CV), I.4.5, Image and Video Processing (eess.IV), Computer Science - Computer Vision and Pattern Recognition, FOS: Electrical engineering, electronic engineering, information engineering, Electrical Engineering and Systems Science - Image and Video Processing, Business and International Management, Industrial and Manufacturing Engineering
Abstract

In terms of 3D imaging speed and system cost, the single-camera system projecting single-frequency patterns is the ideal option among all proposed Fringe Projection Profilometry (FPP) systems. This system necessitates a robust spatial phase unwrapping (SPU) algorithm. However, robust SPU remains a challenge in complex scenes. Quality-guided SPU algorithms need more efficient ways to identify the unreliable points in phase maps before unwrapping. End-to-end deep learning SPU methods face generality and interpretability problems. This paper proposes a hybrid method combining deep learning and traditional path-following for robust SPU in FPP. This hybrid SPU scheme demonstrates better robustness than traditional quality-guided SPU methods, better interpretability than end-to-end deep learning scheme, and generality on unseen data. Experiments on the real dataset of multiple illumination conditions and multiple FPP systems differing in image resolution, the number of fringes, fringe direction, and optics wavelength verify the effectiveness of the proposed method., Comment: 26 pages

Published
2022
Full Text
View/download PDF

4. 3D fingerprint modelling and synthesis.

Author

Shuqin Long, Shuiwang Li, Qijun Zhao, and Wanzhong Song

Subjects
HUMAN fingerprints, THREE-dimensional imaging, FINGERPRINT databases, STATISTICAL shape analysis, PRINCIPAL components analysis
Abstract

Two-dimensional (2D) synthetic fingerprint images have been successfully used for evaluating large-scale automated fingerprint identification systems (AFISs). However, they are limited in assessing the whole process involved in an AFIS, particularly fingerprint image acquisition and fingerprint deformation. Hence, it is desired to develop synthetic 3D fingerprints and 3D fingerprint phantoms. In this reported work, a first attempt to establish a statistical shape model of 3D fingerprints is made by first re-sampling and aligning a set of training 3D fingerprint data and then applying the principal component analysis method. On the basis of the proposed model, synthetic 3D fingerprint shapes can be generated randomly. By further mapping fingerprint textures onto the shapes, synthetic 3D fingerprints can be obtained. Example results are provided demonstrating the effectiveness of the proposed model and method. The model and code will be publicly available for academic purposes. [ABSTRACT FROM AUTHOR]

Published
2015
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results