journal article·2023-02-24Open access

Research on Automatic Error Data Recognition Method for Structured Light System Based on Residual Neural Network

Aozhuo Ding, Qi Xue, Xulong Ding, Xiaohong Sun, Xiaonan Yang, Huiying Ye

Applied Sciences· Volume 13· Issue 5

Abstract

In a structured light system, the positioning accuracy of the stripe is one of the determinants of measurement accuracy. However, the quality of the structured light stripe is reduced by noise, object shape, color, etc. The positioning accuracy of the low-quality stripe center will be decreased, and the large error will be introduced into measurement results, which can only be recognized by a human. To address this problem, this paper proposes a method to identify data with relatively large errors in 3D measurement results by evaluating the quality of the grayscale distribution of stripes. In this method, the undegraded and degraded stripe images are captured. Then, the residual neural network is trained using the grayscale distribution of the two types of stripes. The captured stripes are classified by the trained model. Finally, the data corresponding to the degraded stripes, which correspond to large errors in the data, can be identified according to the classified results. The experiment shows that the algorithm proposed in this paper can effectively identify the data with large errors automatically.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: Optical measurement and interference techniques · Remote Sensing and LiDAR Applications · Surface Roughness and Optical Measurements

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

Affiliations

School of Electrical and Information Engineering, Zhengzhou University, No. 100, Kexue Avenue, Zhengzhou 450001, China

Funding

Science and Technology Research Program of Henan Province · Strategic Priority Research Program of the Chinese Academy of Sciences · National Natural Science Foundation of China · Cangzhou Key research and development Program Guidance Project

References (40)

Show source-provided references
1. Real-time structured light profilometry: A review10.1016/j.optlaseng.2016.01.011 ↗
2. A direct calibration method for line structured light measurement system based on parallel lines10.1016/j.optcom.2021.127699 ↗
3. Large depth-of-field 3d measurement with a microscopic structured-light system10.1016/j.optcom.2020.126540 ↗
4. Automated calibration of multi-camera-projector structured light systems for volumetric high-speed 3d surface reconstructions10.1364/OE.26.033278 ↗
5. Initial experience with using a structured light 3d scanner and image registration to plan bedside subdural evacuating port system placement–sciencedirect10.1016/j.wneu.2020.01.203 ↗
6. A universal method for the calibration of swing-scanning line structured light measurement system10.1016/j.ijleo.2021.166930 ↗
7. Wang, M., Zhang, Q., Li, Q., Wu, Z., Chen, C., Xu, J., and Xue, J. (2022). Research on morphology detection of metal additive manufacturing process based on fringe projection and binocular vision. Appl. Sci., 12.10.3390/app12189232 ↗
8. Wang, Y., Guo, W., Zhao, S., Xue, B., and Xing, Z. (2022). A scraper conveyor coal flow monitoring method based on speckle structured light data. Appl. Sci., 12.10.3390/app12146955 ↗
9. Correction model of linear structured light sensor in underwater environment10.1016/j.optlaseng.2022.107013 ↗
10. Modeling of structured light projection on vibrating surfaces: Amplitude and phase mapping by fringe visibility evaluation10.1016/j.ijleo.2022.168833 ↗
11. Analysis and compensation of lateral chromatic aberration of structured light 3d measurement system10.1016/j.optcom.2021.126871 ↗
12. An accurate and robust strip-edge-based structured light means for shiny surface micromeasurement in 3-D10.1109/TIE.2012.2188875 ↗
13. Pham, D., Ha, M., and Xiao, C. (2023). Color structured light Stripe edge detection method based on generative adversarial networks. Appl. Sci., 13.10.3390/app13010198 ↗
14. An unbiased detector of curvilinear structures10.1109/34.659930 ↗
15. Huang, K., Yang, J., Xu, D., Sun, Y., Chen, Y., and Li, X. (2019, January 15–17). Line laser based researches on a three-dimensional measuring system. Proceedings of the 2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference (ITNEC), Chengdu, China.10.1109/ITNEC.2019.8729303 ↗
16. Laser stripe center detection under the condition of uneven scattering metal surface for geometric measurement10.1109/TIM.2019.2921440 ↗
17. Xi, J., Bao, H., and Li, T. (2018, January 9–11). Research on the algorithm of noisy laser stripe center extraction. Proceedings of the 2018 Chinese Control And Decision Conference (CCDC), Shenyang, China.10.1109/CCDC.2018.8408235 ↗
18. Improving the extracting precision of stripe center for structured light measurement10.1016/j.ijleo.2019.163816 ↗
19. A structured light image quality evaluation method based on no-reference quality assessment10.1088/1742-6596/1914/1/012005 ↗
20. A novel structural damage identification method based on the acceleration responses under ambient vibration and an optimized deep residual algorithm10.1177/14759217211065009 ↗
21. An effective method for damage assessment based on limited measured locations in skeletal structures10.1177/1369433220947193 ↗
22. Data-driven method of damage detection using sparse sensors installation by SEREPa10.1007/s13349-019-00345-8 ↗
23. Kang, C., Kim, T., Kwon, O.S., and Song, J. (2022). Deep neural network-based regional seismic loss assessment considering correlation between EDP residuals of building structures. Earthq. Eng. Struct. Dyn., 1–21.10.1002/eqe.3775 ↗
24. Deep residual network training for reinforced concrete defects intelligent classifier10.1080/19648189.2021.2003250 ↗
25. Qian, L., Pan, Q., Lv, Y., and Zhao, X. (2022). Fault Detection of Bearing by ResNet Classifier with Model-Based Data Augmentation. Machines, 10.10.3390/machines10070521 ↗
26. Fan, Z., Lin, H., Li, C., Su, J., Bruno, S., and Loprencipe, G. (2022). Use of Parallel ResNet for High-Performance Pavement Crack Detection and Measurement. Sustainability, 14.10.3390/su14031825 ↗
27. Zhong, C., Gao, Z., Wang, X., Shao, S., and Gao, C. (2019). Structured light three-dimensional measurement based on machine learning. Sensors, 19.10.3390/s19143229 ↗
28. Knowledge-based automatic extraction of multi-structured light stripes10.1007/s11554-019-00851-4 ↗
29. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
30. Imagenet classification with deep convolutional neural networks10.1145/3065386 ↗
31. Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., Erhan, D., Vanhoucke, V., and Rabinovich, A. (2015, January 7–12). Going deeper with convolutions. Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298594 ↗
32. Simonyan, K., and Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. arXiv.
33. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
34. Srivastava, R.K., Greff, K., and Schmidhuber, J. (2015). Highway networks. arXiv.
35. A practical and intuitive calibration technique for cross-line structured light10.1016/j.ijleo.2016.06.098 ↗
36. A flexible and high precision calibration method for the structured light vision system10.1016/j.ijleo.2015.09.178 ↗
37. Speckle reduction in optical coherence tomography images of human finger skin by wavelet modified bm3d filter10.1016/j.optcom.2012.10.053 ↗
38. Improving the measuring accuracy of structured light measurement system10.1117/1.OE.53.11.112204 ↗
39. Calibration of a camera–projector measurement system and error impact analysis10.1088/0957-0233/23/12/125402 ↗
40. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.