Multiview intelligent networking based on the genetic evolution algorithm for precise 3D measurements

Yujing Qiao; Ning Lv; Baoming Jia; Yujing Qiao; Ning Lv; Baoming Jia

doi:10.3934/mbe.2023638

Mathematical Biosciences and Engineering

2023, Volume 20, Issue 8: 14260-14280. doi: 10.3934/mbe.2023638

Previous Article Next Article

Research article Special Issues

Multiview intelligent networking based on the genetic evolution algorithm for precise 3D measurements

1.
School of Mechanical Engineering, Yangzhou Polytechnic College, Yangzhou 225009, China
2.
Intelligent Machine Institute, Harbin University of Science and Technology, Harbin 150080, China

Academic Editor: Francisco J. G. Silva

Received: 13 April 2023 Revised: 04 June 2023 Accepted: 11 June 2023 Published: 28 June 2023

The use of multi-visual network 3D measurements is increasing; however, finding ways to apply low-cost industrial cameras to achieve intelligent networking and efficient measurement is a key problem that has not been fully solved. In this paper, the multivision stereo vision 3D measurement principle and multivision networking process constraints are analyzed in depth, and an intelligent networking method based on the genetic evolution algorithm (GEA) is proposed. The genetic operation is improved, and the fitness function is dynamically calibrated. Based on the visual sphere model, the best observation distance is assigned as the radius of the visual sphere, and the required constraints are fused to establish an intelligent networking design of the centering multivision. A simulation and experiment show that the proposed algorithm is widely feasible, and its measurement accuracy meets the requirements of the industrial field. Our multiview intelligent networking algorithms and methods provide solid theoretical and technical support for low-cost and efficient on-site 3D measurements of industrial structures.
- 3D measurement,
- multiview intelligent networking,
- genetic evolution algorithm,
- visual sphere model,
- constraint condition
Citation: Yujing Qiao, Ning Lv, Baoming Jia. Multiview intelligent networking based on the genetic evolution algorithm for precise 3D measurements[J]. Mathematical Biosciences and Engineering, 2023, 20(8): 14260-14280. doi: 10.3934/mbe.2023638

Related Papers:

Abstract

The use of multi-visual network 3D measurements is increasing; however, finding ways to apply low-cost industrial cameras to achieve intelligent networking and efficient measurement is a key problem that has not been fully solved. In this paper, the multivision stereo vision 3D measurement principle and multivision networking process constraints are analyzed in depth, and an intelligent networking method based on the genetic evolution algorithm (GEA) is proposed. The genetic operation is improved, and the fitness function is dynamically calibrated. Based on the visual sphere model, the best observation distance is assigned as the radius of the visual sphere, and the required constraints are fused to establish an intelligent networking design of the centering multivision. A simulation and experiment show that the proposed algorithm is widely feasible, and its measurement accuracy meets the requirements of the industrial field. Our multiview intelligent networking algorithms and methods provide solid theoretical and technical support for low-cost and efficient on-site 3D measurements of industrial structures.

References

[1]	Y. Tang, L. Li, C. Wang, M. Chen, W. Feng, X. Zou, et al., Real-time detection of surface deformation and strain in recycled aggregate concrete-filled steel tubular columns via four-ocular vision, Rob. Comput. Integr. Manuf., 59 (2019), 36–46. https://doi.org/10.1016/j.rcim.2019.03.001 doi: 10.1016/j.rcim.2019.03.001
[2]	Y. Wang, V. C. Guizilini, T. Zhang, Y. Wang, H. Zhao, J. Solomon, Detr3d: 3d object detection from multi-view images via 3d-to-2d queries, in Conference on Robot Learning, PMLR, (2022), 180–191. https://doi.org/10.48550/arXiv.2110.06922
[3]	Y. Tang, Z. Huang, Z. Chen, M. Chen, H. Zhou, H. Zhang, et al., Novel visual crack width measurement based on backbone double-scale features for improved detection automation, Eng. Struct., 274 (2023), 115158. https://doi.org/10.1016/j.engstruct.2022.115158 doi: 10.1016/j.engstruct.2022.115158
[4]	M. Chen, Y. Tang, X. Zou, K. Huang, L. Li, Y. He, High-accuracy multi-camera reconstruction enhanced by adaptive point cloud correction algorithm, Opt. Lasers Eng., 122 (2019), 170–183. https://doi.org/10.1016/j.optlaseng.2019.06.011 doi: 10.1016/j.optlaseng.2019.06.011
[5]	Available from: https://www.keyence.com.cn/products/measure/laser-2d/.
[6]	R. Chen, S. Han, J. Xu, H. Su, Point-based multi-view stereo network, in Proceedings of the IEEE/CVF international conference on computer vision, (2019), 1538–1547.
[7]	A. Chen, Z. Xu, F. Zhao, X. Zhang, F. Xiang, J. Yu, et al., Mvsnerf: Fast generalizable radiance field reconstruction from multi-view stereo, in Proceedings of the IEEE/CVF International Conference on Computer Vision, (2021), 14124–14133.
[8]	R. Weilharter, F. Fraundorfer, Highres-mvsnet: A fast multi-view stereo network for dense 3d reconstruction from high-resolution images, IEEE Access, 9 (2021), 11306–11315. https://doi.org/10.1109/ACCESS.2021.3050556 doi: 10.1109/ACCESS.2021.3050556
[9]	S. Shuai, Y. Ling, S. Liang, H. Zhong, X. Tian, C. Liu, et al., Research on 3D surface reconstruction and body size measurement of pigs based on multi-view RGB-D cameras, Comput. Electron. Agric., 175 (2020), 105543. https://doi.org/10.1016/j.compag.2020.105543 doi: 10.1016/j.compag.2020.105543
[10]	T. Wu, J. H. Liu, S. Liu, P. Jin, H. Huang, W. Liu, A measurement method of free-form tube based on multi-view vision for industrial assembly, Assem. Autom., 40 (2020), 553–564. https://doi.org/10.1108/AA-05-2019-0087 doi: 10.1108/AA-05-2019-0087
[11]	L. Yang, Q. Huang, X. Song, M. Li, C. Hou, Z. Xiong, Girth measurement based on multi-view stereo images for garment design, IEEE Access, 8 (2020), 160338–160354. https://doi.org/10.1109/ACCESS.2020.3021019. doi: 10.1109/ACCESS.2020.3021019
[12]	M. Saadat-Seresht, F. Samdzadegan, A. Azizi, M. Hahn, Camera placement for network design in vision metrology based on fuzzy inference system, in XXth ISPRS Congress, 16 (2004), 88.
[13]	Y. Cai, X. Qin, Q. Liu, S. Zhang, Study on high-precision inspection multi-vision cameras space layout, in 2010 Second International Conference on Communication Systems, Networks and Applications, 1 (2010), 168–171. https://doi.org/10.1109/ICCSNA.2010.5588677
[14]	B. S. Alsadik, M. Gerke, G. Vosselman, Optimal camera network design for 3D modeling of cultural heritage, ISPRS Ann. Photogramm. Remote Sens. Spatial Inf. Sci., 3 (2012), 7–12. https://doi.org/10.5194/isprsannals-I-3-7-2012 doi: 10.5194/isprsannals-I-3-7-2012
[15]	H. Chen, K. Ding, C. Qin, P. Zhang, M. Xiao, Optimization design of camera pose for network base on multi-view stereo vision, in Journal of Physics: Conference Series, 2170 (2022), 012018. https://doi.org/10.1088/1742-6596/2170/1/012018
[16]	J. Chen, M. Dong, Photogrammetric network design for large-scale trough concentrator surface measurement, Renewable Energy Res., 34 (2016), 1671–5292. https://doi.org/10.13941/j.cnki.21-1469/tk.2016.03.006 doi: 10.13941/j.cnki.21-1469/tk.2016.03.006
[17]	Y. Qiao, S. Tan, J. Jiang, A multi-vision measurement network planning strategy, Acta Opt. Sin., 38 (2018), 216−223. https://doi.org/10.3788/AOS201838.0515005 doi: 10.3788/AOS201838.0515005
[18]	Y. Qiao, B. Jia, J. Jiang, J. Wang, Networking method of multi-view stereo-vision measurement network, Infrared Laser Eng., 49 (2020), 20190492. https://doi.org/10.3788/IRLA20190492 doi: 10.3788/IRLA20190492
[19]	E. Eriksson, G. Dán, V. Fodor, Coordinating distributed algorithms for feature extraction offloading in multi-camera visual sensor networks, IEEE Trans. Circuits Syst. Video Technol., 28 (2017), 3288–3299. https://doi.org/10.1109/TCSVT.2017.2745102 doi: 10.1109/TCSVT.2017.2745102
[20]	M. Ren, L. Wang, J. Zhao, Z. Tang, Viewpoint planning of surface structured light scanning for complex surface parts, Chin. Opt., 16 (2023), 1–14. http://dx.doi.org/10.37188/CO.2022-0026
[21]	R. Mahony, T. Hamel, J. Trumpf, An homogeneous space geometry for simultaneous localisation and mapping, Annu. Rev. Control, 51 (2021), 254–267. https://doi.org/10.1016/j.arcontrol.2021.04.012 doi: 10.1016/j.arcontrol.2021.04.012
[22]	N. D. M. Phan, Y. Quinsat, S. Lavernhe, C. Lartigue, Scanner path planning with the control of overlap for part inspection with an industrial robot, Int. J. Adv. Manuf. Technol., 98 (2018), 629–643. https://doi.org/10.1007/s00170-018-2336-8 doi: 10.1007/s00170-018-2336-8
[23]	I. D. Lee, J. H. Seo, Y. M. Kim, J. Choi, S. Han, B. Yoo, Automatic pose generation for robotic 3-D scanning of mechanical parts, IEEE Trans. Rob., 36 (2020), 1219–1238. https://doi.org/10.1109/TRO.2020.2980161 doi: 10.1109/TRO.2020.2980161
[24]	P. Osiński, J. Markiewicz, J. Nowisz, M. Remiszewski, A. Rasiński, R. Sitnik, A novel approach for dynamic (4d) multi-view stereo system camera network design, Sensors, 22 (2022), 1576. https://doi.org/10.3390/s22041576 doi: 10.3390/s22041576
[25]	S. Mirjalili, Evolutionary algorithms and neural networks, in Studies in computational intelligence, Berlin/Heidelberg, Germany, Springer, 780 (2019).
[26]	A. Slowik, H. Kwasnicka, Evolutionary algorithms and their applications to engineering problems, Neural Comput. Appl., 32 (2020), 12363–12379. https://doi.org/10.1007/s00521-020-04832-8 doi: 10.1007/s00521-020-04832-8
[27]	R. Hartley, A. Zisserman, Multiple View Geometry in Computer Vision, Cambridge University Press, 2003.
[28]	Y. Qiao, S. Gao, Y. Pi, Optimization method of node pose for measurement network based on multi-view stereo vision, Laser Optoelectron. Prog., 56 (2019).

Reader Comments

Your name:*

Email:*
© 2023 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)