skip to main content
10.1145/3511176.3511203acmotherconferencesArticle/Chapter ViewAbstractPublication PagesicvipConference Proceedingsconference-collections
research-article

Multi-rate Video Compressive Sensing for Fixed Scene Measurement

Published: 12 March 2022 Publication History

Abstract

We propose a simple and efficient framework for video compressive sensing (CS) at fixed scene. In recent years, deep learning has been widely used in reconstructing images and videos for CS. Although they have made a difference in reconstruction quality, current video CS research deals with universal video dataset, regardless of real scene. However, CS in reality mainly serve for a fixed scene. In this paper, we focus on this kind of situation and propose an efficient method to sense the scene with few measurements and reconstruction at a high quality. Technically, we firstly employ an extremely low measurement rate to determine the region of interest (ROI) and then apply more measurements to ROI. Then, we combine the ROI area reconstruction and use temporal information to make up for the background. Experiments have shown that our method can obtain over 30 dB at reconstruction videos with less than 3% measurement rate at fixed scene video dataset.

References

[1]
E. J. Candes, T. Tao, 2005. Decoding by linear programming. IEEE transactions on information theory, 51(12), pp.4203-4215. https://doi.org/10.1109/TIT.2005.858979
[2]
R. G. Baraniuk, 2007. Compressive sensing [lecture notes]. IEEE signal processing magazine, 24(4), pp.118-121. https://doi.org/10.1109/MSP.2007.4286571
[3]
A. Mousavi, A.B. Patel and R. G. Baraniuk, 2015. A deep learning approach to structured signal recovery. IEEE 53rd annual Allerton conference on communication, control, and computing (Allerton). https://doi.org/10.1109/ALLERTON.2015.7447163
[4]
K Kulkarni, S Lohit, P Turaga, R. Kerviche, A. Ashok, 2016. Reconnet: Non-iterative reconstruction of images from compressively sensed measurements. IEEE Conference on Computer Vision and Pattern Recognition, 449-458. https://doi.org/10.1109/CVPR.2016.55
[5]
Z. Zhao, X. Xie, C. Wang, S. Mao, W. Liu, G. Shi, 2019. ROI-CSNet: Compressive sensing network for ROI-aware image recovery. Signal Processing: Image Communication, 78, pp.113-124. https://doi.org/10.1016/j.image.2019.06.006
[6]
C. Dong, C.C. Loy, K. He, X. Tang, 2015, Image Super-Resolution Using Deep Convolutional Networks. IEEE Transactions on Pattern Analysis and Machine Intelligence. 38, 2, (Feb. 1 2016), 295-307. https://doi.org/10.1109/TPAMI.2015.2439281
[7]
H. Yao, F. Dai, S. Zhang, Y. Zhang, Q. Tian, C. Xu, 2019. DR2-Net: Deep residual reconstruction network for image compressive sensing. Neurocomputing 359, 483-493. https://doi.org/10.1016/j.neucom.2019.05.006
[8]
A. Mousavi, G. Dasarathy, R.G. Baraniuk, 2017, DeepCodec: Adaptive sensing and recovery via deep convolutional neural networks. 2017 55th Annual Allerton Conference on Communication, Control, and Computing (Allerton). 744-744. https://doi.org/10.1109/ALLERTON.2017.8262812
[9]
X. Xie, Y. Wang, G. Shi, C. Wang, J. Du, X. Han, 2017, Adaptive Measurement Network for CS Image Reconstruction. CCF Chinese Conference on Computer Vision, 772. https://doi.org/10.1007/978-981-10-7302-1_34
[10]
S. Lohit, K. Kulkarni, R. Kerviche, P. Turaga, A. Ashok, 2018, Convolutional Neural Networks for Noniterative Reconstruction of Compressively Sensed Images. IEEE Transactions on Computational Imaging, 4, 3 (Sept. 2018) 326-340. https://doi.org/10.1109/TCI.2018.2846413
[11]
X. Xie, C. Wang, J. Du, G. Shi, 2018, Full Image Recover for Block-Based Compressive Sensing. 2018 IEEE International Conference on Multimedia and Expo (ICME), 1-6. https://doi.org/10.1109/ICME.2018.8486521
[12]
J. Du, X. Xie, C. Wang, G. Shi, X. Xu, Y. Wang, 2019. Fully convolutional measurement network for compressive sensing image reconstruction. 328, 7 (February 2019), 105-112. https://doi.org/10.1016/j.neucom.2018.04.084
[13]
J. Du, X. Xie, C. Wang, G. Shi, 2018, Perceptual Compressive Sensing. Chinese Conference on Pattern Recognition and Computer Vision (PRCV), 11258, 268-279. https://doi.org/10.1007/978-3-030-03338-5_23
[14]
J. Song, B. Chen, J. Zhang, 2021. Memory-Augmented Deep Unfolding Network for Compressive Sensing. Proceedings of the 29th ACM International Conference on Multimedia (October 2021) 4249-4258. https://doi.org/10.1145/3474085.3475562
[15]
B. Sun, J. Zhang, 2021, Invertible image compressive sensing. Chinese Conference on Pattern Recognition and Computer Vision (PRCV), Springer, 548-560. https://doi.org/10.1007/978-3-030-88013-2_45
[16]
Z. Zhao, X. Xie, C. Wang, W. Liu, G. Shi, J. Du, 2019. Visualizing and understanding of learned compressive sensing with residual network. Neurocomputing. 359, 24 (September 2019), 185-198. https://doi.org/10.1016/j.neucom.2019.05.043
[17]
K. Xu, F. Ren, 2018, CSVideoNet: A Real-Time End-to-End Learning Framework for High-Frame-Rate Video Compressive Sensing. 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), 1680-1688. https://doi.org/10.1109/WACV.2018.00187
[18]
M. Iliadis, L. Spinoulas, A.K. Katsaggelos, 2018, Deep fully-connected networks for video compressive sensing. Digital Signal Processing. 72 (January 2018) 9-18. https://doi.org/10.1016/j.dsp.2017.09.010
[19]
D. Zhao, J. Ke, 2021. Two-step spatial-temporal compressive sensing imaging. Advanced Optical Imaging Technologies IV. 11896. SPIE, 87-91. https://doi.org/10.1117/12.2602717
[20]
R. Timofte, E. Agustsson, L. Van Gool, 2017, NTIRE 2017 Challenge on Single Image Super-Resolution: Methods and Results. 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2160-7516. https://doi.org/10.1109/CVPRW.2017.149

Cited By

View all
  • (2024)Robust Mixed-Rate Region-of-Interest-Aware Video Compressive Sensing for Transmission Line Surveillance VideoInformation10.3390/info1509055515:9(555)Online publication date: 10-Sep-2024
  • (2024)Compressive Sensing in Image/Video Compression: Sampling, Coding, Reconstruction, and Codec OptimizationInformation10.3390/info1502007515:2(75)Online publication date: 26-Jan-2024
  • (2024)aVCSR: Adaptive Video Compressive Sensing Using Region-of-Interest Detection in the Compressed DomainIEEE MultiMedia10.1109/MMUL.2023.334206231:1(19-32)Online publication date: Jan-2024

Recommendations

Comments

Information & Contributors

Information

Published In

cover image ACM Other conferences
ICVIP '21: Proceedings of the 2021 5th International Conference on Video and Image Processing
December 2021
219 pages
ISBN:9781450385893
DOI:10.1145/3511176
Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 12 March 2022

Permissions

Request permissions for this article.

Check for updates

Author Tags

  1. compressive sensing
  2. convolutional neural network
  3. deep learning
  4. low-level computer vision
  5. video reconstruction

Qualifiers

  • Research-article
  • Research
  • Refereed limited

Funding Sources

Conference

ICVIP 2021

Contributors

Other Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

  • Downloads (Last 12 months)8
  • Downloads (Last 6 weeks)0
Reflects downloads up to 16 Feb 2025

Other Metrics

Citations

Cited By

View all
  • (2024)Robust Mixed-Rate Region-of-Interest-Aware Video Compressive Sensing for Transmission Line Surveillance VideoInformation10.3390/info1509055515:9(555)Online publication date: 10-Sep-2024
  • (2024)Compressive Sensing in Image/Video Compression: Sampling, Coding, Reconstruction, and Codec OptimizationInformation10.3390/info1502007515:2(75)Online publication date: 26-Jan-2024
  • (2024)aVCSR: Adaptive Video Compressive Sensing Using Region-of-Interest Detection in the Compressed DomainIEEE MultiMedia10.1109/MMUL.2023.334206231:1(19-32)Online publication date: Jan-2024

View Options

Login options

View options

PDF

View or Download as a PDF file.

PDF

eReader

View online with eReader.

eReader

HTML Format

View this article in HTML Format.

HTML Format

Figures

Tables

Media

Share

Share

Share this Publication link

Share on social media