Multiple CR Spatiotemporal Compressive Imaging System
Abstract
:1. Introduction
- Considering the need to balance the encoding efficiency and the simplicity of the imaging system structure, we re-discuss the mathematical model of STCI and adopt a stepwise strategy for spatiotemporal encoding. Through the preprocessing of the mask, we finally only need to introduce a single spatial light modulator (SLM) in the optical system to achieve effective spatiotemporal encoding.
- By adopting a special structural spatial mask and introducing a hyperparameter module for multi-CR reconstruction in the network, we implemented an STCI reconstruction method that can handle reconstruction with multiple spatiotemporal CRs.
- Through simulation and optical experiments, we verify that our proposed method can accurately reconstruct the motion and spatial details of high-speed motion scenes when the temporal and spatial compression ratio is 128:1. Similarly, we verify the performance of the reconstruction algorithm under nine spatiotemporal compression ratios.
2. Related Work
2.1. Compressive Imaging with Different Optical Modulation Devices
2.2. Typical Reconstruction Algorithms for Spatial or Temporal CI
3. Multiple CR Spatiotemporal Compressive Imaging (Multi-CR STCI)
3.1. Imaging Model and Spatiotemporal Mask Design
3.2. GAP for STCI
3.3. Reconstruction Algorithm
4. Simulation Experiments
4.1. Network Training
4.2. Results of STCINet_v1
4.3. Results of STCINet-v2
4.4. Temporal Reconstruction
4.5. Ablation
5. Optical Experiment
5.1. Optical Setup
5.2. Optical Results
5.3. Discussions
6. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Conflicts of Interest
References
- Gao, L.; Liang, J.; Li, C.; Wang, L.V. Single-shot compressed ultrafast photography at one hundred billion frames per second. Nature 2014, 516, 74–77. [Google Scholar] [CrossRef]
- El-Desouki, M.; Deen, M.J.; Fang, Q.; Liu, L.; Tse, F.; Armstrong, D. CMOS image sensors for high speed applications. Sensors 2009, 9, 430–444. [Google Scholar] [CrossRef] [PubMed]
- Donoho, D.L. Compressed sensing. IEEE Trans. Inf. Theory 2006, 52, 1289–1306. [Google Scholar] [CrossRef]
- Ke, J.; Lam, E.Y. Object reconstruction in block-based compressive imaging. Opt. Express 2012, 20, 22102–22117. [Google Scholar] [CrossRef] [PubMed]
- Zhou, Q.; Ke, J.; Lam, E.Y. Dual-waveband temporal compressive imaging. In Proceedings of the Computational Optical Sensing and Imaging, Munich, Germany, 23–27 June 2019; Optica Publishing Group: Washington, DC, USA, 2019; p. CTu2A.8. [Google Scholar]
- Cao, X.; Yue, T.; Lin, X.; Lin, S.; Yuan, X.; Dai, Q.; Carin, L.; Brady, D.J. Computational snapshot multispectral cameras: Toward dynamic capture of the spectral world. IEEE Signal Process. Mag. 2016, 33, 95–108. [Google Scholar] [CrossRef]
- Dong, D.W.; Atick, J.J. Statistics of natural time-varying images. Netw. Comput. Neural Syst. 1995, 6, 345. [Google Scholar] [CrossRef]
- Treeaporn, V.; Ashok, A.; Neifeld, M.A. Space–time compressive imaging. Appl. Opt. 2012, 51, A67–A79. [Google Scholar] [CrossRef]
- Harmany, Z.T.; Marcia, R.F.; Willett, R.M. Spatio-temporal compressed sensing with coded apertures and keyed exposures. arXiv 2011, arXiv:1111.7247. [Google Scholar]
- Ke, J.; Zhang, L.; Lam, E.Y. Temporal compressed measurements for block-wise compressive imaging. In Proceedings of the Mathematics in Imaging, San Francisco, CA, USA, 2–7 February 2019; Optical Society of America: Washington, DC, USA, 2019; p. JW4B.1. [Google Scholar]
- Gan, L. Block compressed sensing of natural images. In Proceedings of the 2007 15th International Conference on Digital Signal Processing, Cardiff, UK, 1–4 July 2007; pp. 403–406. [Google Scholar]
- Tsai, T.H.; Llull, P.; Yuan, X.; Carin, L.; Brady, D.J. Spectral-temporal compressive imaging. Opt. Lett. 2015, 40, 4054–4057. [Google Scholar] [CrossRef]
- Zhang, B.; Yuan, X.; Deng, C.; Zhang, Z.; Suo, J.; Dai, Q. End-to-end snapshot compressed super-resolution imaging with deep optics. Optica 2022, 9, 451–454. [Google Scholar] [CrossRef]
- Llull, P.; Liao, X.; Yuan, X.; Yang, J.; Kittle, D.; Carin, L.; Sapiro, G.; Brady, D.J. Coded aperture compressive temporal imaging. Opt. Express 2013, 21, 10526–10545. [Google Scholar] [CrossRef] [PubMed]
- Reddy, D.; Veeraraghavan, A.; Chellappa, R. P2C2: Programmable pixel compressive camera for high speed imaging. In Proceedings of the CVPR 2011, Colorado Springs, CO, USA, 20–25 June 2011; pp. 329–336. [Google Scholar]
- Bioucas-Dias, J.M.; Figueiredo, M.A. A new TwIST: Two-step iterative shrinkage/thresholding algorithms for image restoration. IEEE Trans. Image Process. 2007, 16, 2992–3004. [Google Scholar] [CrossRef] [PubMed]
- Ma, J.; Liu, X.Y.; Shou, Z.; Yuan, X. Deep tensor admm-net for snapshot compressive imaging. In Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Republic of Korea, 27 October–2 November 2019; pp. 10223–10232. [Google Scholar]
- Zhang, J.; Ghanem, B. ISTA-Net: Interpretable optimization-inspired deep network for image compressive sensing. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18–23 June 2018; pp. 1828–1837. [Google Scholar]
- Cui, C.; Ke, J. Spatial compressive imaging deep learning framework using joint input of multi-frame measurements and degraded maps. Opt. Express 2022, 30, 1235–1248. [Google Scholar] [CrossRef]
- Zhang, L.; Lam, E.Y.; Ke, J. Temporal compressive imaging reconstruction based on a 3D-CNN network. Opt. Express 2022, 30, 3577–3591. [Google Scholar] [CrossRef]
- Arce, G.R.; Brady, D.J.; Carin, L.; Arguello, H.; Kittle, D.S. Compressive coded aperture spectral imaging: An introduction. IEEE Signal Process. Mag. 2013, 31, 105–115. [Google Scholar] [CrossRef]
- Babbitt, W.R.; Barber, Z.W.; Renner, C. Compressive laser ranging. Opt. Lett. 2011, 36, 4794–4796. [Google Scholar] [CrossRef]
- Mengu, D.; Tabassum, A.; Jarrahi, M.; Ozcan, A. Snapshot multispectral imaging using a diffractive optical network. Light Sci. Appl. 2023, 12, 86. [Google Scholar] [CrossRef]
- Hu, X.; Xu, W.; Fan, Q.; Yue, T.; Yan, F.; Lu, Y.; Xu, T. Metasurface-based computational imaging: A review. Adv. Photonics 2024, 6, 014002. [Google Scholar] [CrossRef]
- Wang, X.; Xu, T.; Zhang, Y.; Xu, C.; Fan, A.; Yu, Y. A multi-channel spectral coding method for the coded aperture tunable filter spectral imager. In Proceedings of the Optics, Photonics and Digital Technologies for Imaging Applications VI. SPIE, Online, 6–10 April 2020; Volume 11353, pp. 271–279. [Google Scholar]
- Yuan, X. Generalized alternating projection based total variation minimization for compressive sensing. In Proceedings of the 2016 IEEE International Conference on Image Processing (ICIP), Phoenix, AZ, USA, 25–28 September 2016; pp. 2539–2543. [Google Scholar] [CrossRef]
- Liu, Y.; Yuan, X.; Suo, J.; Brady, D.J.; Dai, Q. Rank Minimization for Snapshot Compressive Imaging. IEEE Trans. Pattern Anal. Mach. Intell. 2019, 41, 2990–3006. [Google Scholar] [CrossRef]
- Kulkarni, K.; Lohit, S.; Turaga, P.; Kerviche, R.; Ashok, A. Reconnet: Non-iterative reconstruction of images from compressively sensed measurements. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, 27–30 June 2016; pp. 449–458. [Google Scholar]
- Cheng, Z.; Lu, R.; Wang, Z.; Zhang, H.; Chen, B.; Meng, Z.; Yuan, X. BIRNAT: Bidirectional Recurrent Neural Networks with Adversarial Training for Video Snapshot Compressive Imaging. In Proceedings of the 16th European Conference, Glasgow, UK, 23–28 August 2020; pp. 258–275. [Google Scholar] [CrossRef]
- Yuan, X.; Liu, Y.; Suo, J.; Dai, Q. Plug-and-Play Algorithms for Large-Scale Snapshot Compressive Imaging. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 14–19 June 2020. [Google Scholar]
- Liao, X.; Li, H.; Carin, L. Generalized alternating projection for weighted-2,1 minimization with applications to model-based compressive sensing. Siam J. Imaging Sci. 2014, 7, 797–823. [Google Scholar] [CrossRef]
- Zhang, K.; Gool, L.V.; Timofte, R. Deep Unfolding Network for Image Super-Resolution. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, WA, USA, 13–19 June 2020. [Google Scholar]
- Chen, Y.; Dai, X.; Liu, M.; Chen, D.; Yuan, L.; Liu, Z. Dynamic convolution: Attention over convolution kernels. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA, 13–19 June 2020; pp. 11030–11039. [Google Scholar]
- Pont-Tuset, J.; Perazzi, F.; Caelles, S.; Arbeláez, P.; Sorkine-Hornung, A.; Van Gool, L. The 2017 davis challenge on video object segmentation. arXiv 2017, arXiv:1704.00675. [Google Scholar]
- Mercat, A.; Viitanen, M.; Vanne, J. UVG dataset: 50/120fps 4K sequences for video codec analysis and development. In Proceedings of the 11th ACM Multimedia Systems Conference, Istanbul, Turkey, 8–11 June 2020; pp. 297–302. [Google Scholar]
2/1/2:1 | 2/2/8:1 | 2/4/32:1 | 4/1/4:1 | 4/2/16:1 | 4/4/64:1 | 8/1/8:1 | 8/2/32:1 | 8/4/128:1 | |
---|---|---|---|---|---|---|---|---|---|
Subway | 46.54 | 38.75 | 31.63 | 43.63 | 36.74 | 30.68 | 39.75 | 33.53 | 28.33/28.56 |
Aerobatics | 36.79 | 34.22 | 30.97 | 35.25 | 33.04 | 30.20 | 33.69 | 31.38 | 28.48/28.79 |
Plane | 42.26 | 34.38 | 29.10 | 40.82 | 34.30 | 29.29 | 38.89 | 34.15 | 29.98/30.16 |
Chameleon | 42.72 | 34.45 | 28.77 | 39.20 | 31.99 | 27.96 | 35.05 | 29.19 | 25.82/26.09 |
Car-race | 41.15 | 34.54 | 27.87 | 39.72 | 33.72 | 28.73 | 38.56 | 33.37 | 27.91/28.40 |
skiing | 44.54 | 39.09 | 35.25 | 41.99 | 37.57 | 39.12 | 35.84 | 29.89 | 33.44/33.69 |
Avg. | 42.33 | 35.91 | 30.60 | 40.10 | 34.56 | 31.00 | 36.96 | 31.92 | 28.99/29.28 |
2/1/2:1 | 2/2/8:1 | 2/4/32:1 | 4/1/4:1 | 4/2/16:1 | 4/4/64:1 | 8/1/8:1 | 8/2/32:1 | 8/4/128:1 | |
---|---|---|---|---|---|---|---|---|---|
Beauty | 91.94 | 89.34 | 81.63 | 90.15 | 86.41 | 77.88 | 86.81 | 80.96 | 71.56 |
Bosphours | 99.93 | 99.90 | 89.33 | 99.92 | 97.69 | 79.31 | 99.41 | 89.43 | 66.15 |
Honeybee | 91.94 | 89.34 | 81.63 | 90.15 | 86.41 | 77.88 | 86.81 | 80.96 | 78.41 |
Avg. | 94.60 | 92.86 | 84.19 | 93.40 | 90.17 | 78.35 | 91.01 | 83.78 | 72.04 |
Algorithms | Average PSNR | Running Time | Memory |
---|---|---|---|
GAP-TV | 32.01 | 39.5 | - |
PnP-FFDNet | 35.93 | 29.8 | 9017 |
BIRNAT | 37.9 | 3.8 | >24,000 |
Ours | 37.14 | 2.9 | 3199 |
2/1/2:1 | 2/2/8:1 | 2/4/32:1 | 4/1/4:1 | 4/2/16:1 | 4/4/64:1 | 8/1/8:1 | 8/2/32:1 | 8/4/128:1 | Avg. | |
---|---|---|---|---|---|---|---|---|---|---|
STCINet | 42.33 | 35.91 | 30.60 | 40.10 | 34.56 | 31.00 | 36.96 | 31.92 | 28.99 | 34.68 |
w/o | 38.67 | 34.72 | 30.66 | 37.41 | 33.53 | 30.07 | 35.39 | 32.03 | 28.86 | 33.48 |
w/o DCU | 38.41 | 34.28 | 30.56 | 36.89 | 33.19 | 29.87 | 34.94 | 31.75 | 28.70 | 33.29 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2025 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
Hao, X.; Zhao, D.; Ke, J. Multiple CR Spatiotemporal Compressive Imaging System. Sensors 2025, 25, 1334. https://doi.org/10.3390/s25051334
Hao X, Zhao D, Ke J. Multiple CR Spatiotemporal Compressive Imaging System. Sensors. 2025; 25(5):1334. https://doi.org/10.3390/s25051334
Chicago/Turabian StyleHao, Xiaowen, Dingaoyu Zhao, and Jun Ke. 2025. "Multiple CR Spatiotemporal Compressive Imaging System" Sensors 25, no. 5: 1334. https://doi.org/10.3390/s25051334
APA StyleHao, X., Zhao, D., & Ke, J. (2025). Multiple CR Spatiotemporal Compressive Imaging System. Sensors, 25(5), 1334. https://doi.org/10.3390/s25051334