Single-Pixel Moving Object Classification with Differential Measuring in Transform Domain and Deep Learning
Abstract
:1. Introduction
2. Methods and System Architecture
2.1. The System Architecture
2.2. Differential Measuring in Transform Domain
2.3. Neural Network Design and Training
2.4. Data Rolling Utilization for Repeated Tests
3. Neural Network Performance Test
3.1. Network Performance Test with Simulation Data
3.2. Network Performance Test with Experiment Data of Static Objects
3.3. Network Performance Test with Experiment Data of Moving Objects
4. Discussions
5. Conclusions
Supplementary Materials
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Marr, D. Vision: A Computational Investigation into the Human Representation and Processing of Visual Information; The MIT Press: Cambridge, UK, 2010. [Google Scholar]
- Rawat, W.; Wang, Z. Deep convolutional neural networks for image classification: A comprehensive review. Neural Comput. 2017, 29, 2352–2449. [Google Scholar] [CrossRef]
- Ciregan, D.; Meier, U.; Schmidhuber, J. Multi-column deep neural networks for image classification. In Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, France, 16–21 June 2012. [Google Scholar]
- Sermanet, P.; LeCun, Y. Traffic sign recognition with multi-scale convolutional networks. In Proceedings of the 2011 International Joint Conference on Neural Networks (IJCNN), San Jose, CA, USA, 31 July–5 August 2011. [Google Scholar]
- Bruce, V.; Young, A. Understanding face recognition. Br. J. Psychol 1986, 77, 305–327. [Google Scholar] [CrossRef] [PubMed]
- Jiankang, D.; Jia, G.; Niannan, X.; Stefanos, Z. Arcface: Additive angular margin loss for deep face recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach, CA, USA, 16–20 June 2019. [Google Scholar]
- Zhao, R.; Yan, R.; Chen, Z.; Mao, K.; Wang, P.; Gao, R.X. Deep learning and its applications to machine health monitoring. Mech. Syst. Signal. Process. 2019, 115, 213–237. [Google Scholar]
- Andreopoulos, A.; Tsotsos, J.K. 50 years of object recognition: Directions forward. Comput. Vis. Image Und. 2013, 117, 827–891. [Google Scholar] [CrossRef]
- Vollmer, M.; Möllmann, K.P. High speed and slow motion: The technology of modern high speed cameras. Phys. Educ. 2011, 46, 191–202. [Google Scholar] [CrossRef]
- Edgar, M.P.; Gibson, G.M.; Padgett, M.J. Principles and prospects for single-pixel imaging. Nat. Photonics 2019, 13, 13–20. [Google Scholar] [CrossRef]
- Zhang, Z.; Ma, X.; Zhong, J. Single-pixel imaging by means of Fourier spectrum acquisition. Nat. Commun. 2015, 6, 6225. [Google Scholar] [CrossRef] [Green Version]
- Gibson, G.M.; Johnson, S.D.; Padgett, M.J. Single-pixel imaging 12 years on: A review. Opt. Express 2020, 28, 28190–28208. [Google Scholar] [CrossRef]
- Sun, B.; Edgar, M.; Bowman, P.R.; Vittert, L.E.; Welsh, S.; Bowman, A.; Padgettet, M.J. 3D computational imaging with single-pixel detectors. Science 2013, 340, 844–847. [Google Scholar] [CrossRef] [Green Version]
- Sun, M.J.; Zhang, J.M. Single-pixel imaging and its application in three-dimensional reconstruction: A brief review. Sensors 2019, 19, 732. [Google Scholar] [CrossRef] [Green Version]
- Yao, M.; Cai, Z.; Qiu, X.; Li, S.; Peng, J.; Zhong, J. Full-color light-field microscopy via single-pixel imaging. Opt. Express 2020, 28, 6521–6536. [Google Scholar] [CrossRef]
- Carmona, P.L.; Traver, V.J.; Sánchez, J.S.; Tajahuerce, E. Online reconstruction-free single-pixel image classification. Image Vision Comput. 2019, 86, 28–37. [Google Scholar] [CrossRef]
- He, X.; Zhao, S.; Wang, L. Ghost Handwritten Digit Recognition based on Deep Learning. arXiv 2020, arXiv:2004.02068. [Google Scholar] [CrossRef]
- Rizvi, S.; Cao, J.; Hao, Q. High-speed image-free target detection and classification in single-pixel imaging. In Proceedings of the SPIE Future Sensing Technologies, Online, 9–13 November 2020. [Google Scholar]
- Fu, H.; Bian, L.; Zhang, J. Single-pixel sensing with optimal binarized modulation. Opt. Lett. 2020, 45, 3111–3114. [Google Scholar] [CrossRef]
- Jiao, S.; Feng, J.; Gao, Y.; Lei, T.; Xie, Z.; Yuan, X. Optical machine learning with incoherent light and a single-pixel detector. Opt. Lett. 2019, 44, 5186–5189. [Google Scholar] [CrossRef]
- Zhang, Z.; Li, X.; Zheng, S.; Yao, M.; Zheng, G.; Zhong, J. Image-free classification of fast-moving objects using “learned” structured illumination and single-pixel detection. Opt. Express 2020, 28, 13269–13278. [Google Scholar] [CrossRef]
- Alzubaidi, L.; Zhang, J.; Humaidi, A.J.; Dujaili, A.A.; Duan, Y.; Shamma, O.A.; Santamaría, J.; Fadhel, M.A.; Amidie, M.A.; Farhan, L. Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. J. Big Data 2021, 8, 53. [Google Scholar] [CrossRef]
- Kellman, M.R.; Bostan, E.; Repina, N.A.; Waller, L. Physics-based learned design: Optimized coded-illumination for quantitative phase imaging. IEEE Trans. Comput. Imaging 2019, 5, 344–353. [Google Scholar] [CrossRef] [Green Version]
- Wang, F.; Wang, H.; Wang, H.; Li, G.; Situ, G. Learning from simulation: An end-to-end deep-learning approach for computational ghost imaging. Opt. Express 2019, 27, 25560–25572. [Google Scholar] [CrossRef]
- Gonzales, R.C.; Woods, R.E. Digital Image Processing, 4th ed.; Pearson Global Edition: Edinburgh, UK, 2020. [Google Scholar]
- Aelterman, J.; Luong, H.Q.; Goossens, B.; Pižurica, A.; Philips, W. COMPASS: A joint framework for parallel imaging and compressive sensing in MRI. In Proceedings of the 2010 IEEE International Conference on Image Processing (ICIP), Hong Kong, 12–15 September 2010. [Google Scholar]
- Sun, B.; Edgar, M.; Bowman, P.R.; Vittert, L.E.; Welsh1, S.; Bowman, A.; Padgett, M.J. Differential computational ghost imaging. In Proceedings of the Computational Optical Sensing and Imaging, Arlington, TX, USA, 23–27 June 2013. [Google Scholar]
- Welsh, S.S.; Edgar, M.P.; Bowman, R.; Jonathan, P.; Sun, B.; Padgett, M.J. Fast full-color computational imaging with single-pixel detectors. Opt. Express 2013, 21, 23068–23074. [Google Scholar] [CrossRef]
- LeCun, Y.; Cortes, C.; Burges, C.J.C. The MNIST Database of Handwritten Digits. Available online: http://yann.lecun.com/exdb/mnist/ (accessed on 22 February 2022).
- Zhang, Z.; Wang, X.; Zheng, G.; Zhong, J. Fast Fourier single-pixel imaging via binary illumination. Sci. Rep. 2017, 7, 12029. [Google Scholar] [CrossRef] [PubMed]
a | 10 | 20 | 30 | 40 | 50 | 60 | 70 |
---|---|---|---|---|---|---|---|
SNR (dB) | 7.22 | 4.21 | 2.45 | 1.20 | 0.23 | −0.56 | −1.23 |
Mode | Number of Coefficients | Noise-Free | Noisy | ||
---|---|---|---|---|---|
Correct | Correct/Total (%) | Correct | Correct/Total (%) | ||
Non-differential | 9 | 3 | 12.50 | 3 | 12.50 |
15 | 11 | 45.83 | 3 | 12.50 | |
22 | 18 | 75.00 | 6 | 25.00 | |
33 | 24 | 100.00 | 15 | 62.50 | |
Differential | 9 | 20 | 83.33 | 21 | 87.50 |
15 | 18 | 75.00 | 21 | 87.50 | |
22 | 24 | 100.00 | 24 | 100.00 | |
33 | 24 | 100.00 | 24 | 100.00 |
Label | “4” | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
Result | “0” | “1” | “2” | “3” | “4” | “5” | “6” | “7” | “8” | “9” |
Number of tests | 0 | 74 | 20 | 0 | 198 | 0 | 0 | 0 | 0 | 30 |
Linear Velocity (m/s) | Mode | Number of Coefficients | Noise-Free | Noisy | ||||
---|---|---|---|---|---|---|---|---|
Correct | Total | Correct/Total | Correct | Total | Correct/Total | |||
0.729 | Non- differential | 9 | 18 | 43 | 41.86 | 6 | 42 | 14.29 |
15 | 37 | 44 | 84.09 | 8 | 41 | 19.51 | ||
22 | 40 | 42 | 95.24 | 18 | 42 | 42.86 | ||
33 | 42 | 43 | 97.67 | 17 | 40 | 42.50 | ||
Differential | 9 | 29 | 43 | 67.44 | 27 | 43 | 62.79 | |
15 | 43 | 43 | 100.00 | 40 | 43 | 93.02 | ||
22 | 42 | 42 | 100.00 | 42 | 42 | 100.00 | ||
33 | 44 | 44 | 100.00 | 41 | 41 | 100.00 | ||
1.638 | Non- differential | 9 | 41 | 91 | 45.05 | 14 | 93 | 15.05 |
15 | 79 | 94 | 84.04 | 17 | 91 | 18.68 | ||
22 | 90 | 94 | 95.74 | 39 | 94 | 41.49 | ||
33 | 92 | 92 | 100.00 | 39 | 92 | 42.39 | ||
Differential | 9 | 79 | 91 | 86.81 | 60 | 92 | 65.22 | |
15 | 91 | 92 | 98.91 | 86 | 91 | 94.51 | ||
22 | 95 | 95 | 100.00 | 90 | 90 | 100.00 | ||
33 | 86 | 92 | 93.48 | 87 | 92 | 94.57 | ||
4.265 | Non- differential | 9 | 85 | 220 | 38.64 | 33 | 232 | 14.22 |
15 | 143 | 221 | 64.71 | 42 | 231 | 18.18 | ||
22 | 196 | 220 | 89.09 | 79 | 231 | 34.20 | ||
33 | 139 | 219 | 63.47 | 73 | 230 | 31.74 | ||
Differential | 9 | 155 | 220 | 70.45 | 132 | 232 | 56.90 | |
15 | 145 | 221 | 65.61 | 161 | 231 | 69.70 | ||
22 | 121 | 219 | 55.25 | 143 | 231 | 61.90 | ||
33 | 88 | 219 | 40.18 | 93 | 231 | 40.26 | ||
6.626 | Non- differential | 9 | 102 | 356 | 28.65 | 52 | 357 | 14.57 |
15 | 189 | 357 | 52.94 | 68 | 357 | 19.05 | ||
22 | 222 | 355 | 62.54 | 87 | 357 | 24.37 | ||
33 | 108 | 356 | 30.34 | 90 | 356 | 25.28 | ||
Differential | 9 | 153 | 356 | 42.98 | 167 | 357 | 46.78 | |
15 | 220 | 356 | 61.80 | 243 | 358 | 67.88 | ||
22 | 119 | 356 | 33.43 | 116 | 355 | 32.68 | ||
33 | 100 | 353 | 28.33 | 101 | 354 | 28.53 |
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. |
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Yao, M.; Zheng, S.; Hu, Y.; Zhang, Z.; Peng, J.; Zhong, J. Single-Pixel Moving Object Classification with Differential Measuring in Transform Domain and Deep Learning. Photonics 2022, 9, 202. https://doi.org/10.3390/photonics9030202
Yao M, Zheng S, Hu Y, Zhang Z, Peng J, Zhong J. Single-Pixel Moving Object Classification with Differential Measuring in Transform Domain and Deep Learning. Photonics. 2022; 9(3):202. https://doi.org/10.3390/photonics9030202
Chicago/Turabian StyleYao, Manhong, Shujun Zheng, Yuhang Hu, Zibang Zhang, Junzheng Peng, and Jingang Zhong. 2022. "Single-Pixel Moving Object Classification with Differential Measuring in Transform Domain and Deep Learning" Photonics 9, no. 3: 202. https://doi.org/10.3390/photonics9030202
APA StyleYao, M., Zheng, S., Hu, Y., Zhang, Z., Peng, J., & Zhong, J. (2022). Single-Pixel Moving Object Classification with Differential Measuring in Transform Domain and Deep Learning. Photonics, 9(3), 202. https://doi.org/10.3390/photonics9030202