基于帧间组稀疏的两阶段递归增强视频压缩感知重构网络
Two-Stage Recursive Enhancement Reconstruction Based on Video Inter-frame Group Sparse Representation in Compressed Video Sensing
查看参考文献24篇
|
文摘
|
基于迭代优化的传统视频压缩感知重构算法运行时间长,参数的自适应性较低,限制了其实用性和泛化能力.利用神经网络强大的计算能力和运行速度快、参数可学习的优点,本文首先提出了帧间组稀疏网络(VGSR-Net),用神经网络将图像块组映射到更高维的稀疏表示域中,并利用可学习的阈值提取帧间相关特征.在此基础上,提出了两阶段混合递归增强重构网络(2sRER-VGSR-Net).首先,利用VGSR-Net对初始重构结果进行初步增强;然后,引入STMCNet实现运动估计,并利用残差重构网络进一步重构当前帧丢失的信息,得到更高质量的重构结果.在第二阶段重构过程中采用混合递归结构,充分利用已有的高质量重构帧信息.仿真结果表明,所提算法与现有最优迭代优化重构算法SSIMInterF- GSR相比重构性能提升了1.99dB;和基于深度学习的重构网络CSVideoNet相比,性能提升了4.60dB. |
|
其他语种文摘
|
The traditional iterative optimized based video compression sensing algorithms are limited by long running time and low adaptability of parameters, resulting in low practicability and generalization. Taking advantage of the powerful computing power, fast speed and learnable parameters of neural networks, this paper first proposes a group sparse representation network (VGSR-Net),which maps the image block group to a higher-dimensional sparse domain through convolution, and uses a learnable threshold to denoise and extract inter-frame correlation. On this basis,a two-stage recursive enhance reconstruction network(2sRER-VGSR-Net) is proposed. First,we perform VGSR-Net to preliminarily enhance the initial reconstruction and then introduce STMC-Net as motion estimation, and the compensated frames are fed into the residual reconstruction network to further extract the missing detail and enhance the current frame. The second stage of reconstruction adopts a hybrid recursive structure with the aim of making full use of the existing better quality reconstructed frames. The simulation results show that the proposed algorithm improves the PSNR(Peak Signal to Noise Ratio) by 1.99dB compared with the existing state-of-art traditional compressed video sensing reconstruction algorithms SSIM-InterF-GSR,while improves the PSNR by 4.60dB with the comparation of the network-based algorithm CSVideoNet. |
|
来源
|
电子学报
,2021,49(3):435-442 【核心库】
|
|
DOI
|
10.12263/dzxb.20200272
|
|
关键词
|
视频压缩感知
;
深度学习
;
帧间组稀疏表示
;
混合递归网络
;
运动估计
;
增强重构
|
|
地址
|
华南理工大学电子与信息学院, 广东, 广州, 510640
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
0372-2112 |
|
学科
|
电子技术、通信技术 |
|
基金
|
广东省自然科学基金-重点
;
广东省自然科学基金
|
|
文献收藏号
|
CSCD:6933247
|
参考文献 共
24
共2页
|
|
1.
Donoho D L. Compressed sensing.
IEEE Transactions on Information Theory,2006,52(4):1289-1306
|
CSCD被引
3003
次
|
|
|
|
|
2.
Gan L. Block compressed sensing of natural images.
15th International Conference on Digital Signal Processing,2007:403-406
|
CSCD被引
10
次
|
|
|
|
|
3.
Mun S. Block compressed sensing of images using directional transforms.
16th IEEE International Conference on Image Processing (ICIP),2009:3021-3024
|
CSCD被引
1
次
|
|
|
|
|
4.
Chen R. Compressed video sensing with multi-hypothesis prediction.
International Conference on Emerging Internetworking,Data & Web Technologies,2017:489-496
|
CSCD被引
2
次
|
|
|
|
|
5.
Zhang J. Group-based sparse representation for image restoration.
IEEE Transactions on Image Processing,2014,23(8):3336-3351
|
CSCD被引
90
次
|
|
|
|
|
6.
Kang L. Distributed compressive video sensing.
International Conference on Acoustics,Speech and Signal Processing,2009:1169-1172
|
CSCD被引
1
次
|
|
|
|
|
7.
Tramel E W. Video Compressed Sensing with Multihypothesis.
Data Compression Conference (DCC),2011:193-202
|
CSCD被引
1
次
|
|
|
|
|
8.
Zhao C. Video compressive sensing reconstruction via reweighted residual sparsity.
IEEE Transactions on Circuits and Systems for Video Technology,2017,27(6):1182-1195
|
CSCD被引
18
次
|
|
|
|
|
9.
和志杰. 视频压缩感知中基于结构相似的帧间组稀疏表示重构算法研究.
电子学报,2018,46(3):544-553
|
CSCD被引
18
次
|
|
|
|
|
10.
杨春玲. CVS中基于多维度参考帧的双稀疏重构算法.
华南理工大学学报(自然科学版),2018,46(8):1-10
|
CSCD被引
3
次
|
|
|
|
|
11.
汤瑞东. 视频压缩感知多假设局部增强重构算法.
自动化学报,2019
|
CSCD被引
1
次
|
|
|
|
|
12.
Kulkarni K. Reconnet: Non-iterative reconstruction of images from compressively sensed measurements.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR),2016:449-458
|
CSCD被引
2
次
|
|
|
|
|
13.
Shi W. Deep networks for compressed image sensing.
IEEE International Conference on Multimedia and Expo (ICME),2017:877-882
|
CSCD被引
1
次
|
|
|
|
|
14.
练秋生. 基于多尺度残差网络的压缩感知重构算法.
自动化学报,2019,45(11):2082-2091
|
CSCD被引
13
次
|
|
|
|
|
15.
Zhang J. ISTA-Net: Interpretable optimizationinspired deep network for image compressive sensing.
IEEE/CVF Conference on Computer Vision and Pattern Recognition,2018:1828-1837
|
CSCD被引
2
次
|
|
|
|
|
16.
Xu K. 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),2018:1680-1688
|
CSCD被引
2
次
|
|
|
|
|
17.
Sajjadi M S M. Frame-recurrent video super-resolution.
2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR),2018:6626-6634
|
CSCD被引
1
次
|
|
|
|
|
18.
Gu D. Continuous bidirectional optical flow for video frame sequence interpolation.
2019 IEEE International Conference on Multimedia and Expo (ICME),2019:1768-1773
|
CSCD被引
1
次
|
|
|
|
|
19.
Kim T H. Spatiotemporal transformer network for video restoration.
The European Conference on Computer Vision (ECCV),2018:106-122
|
CSCD被引
1
次
|
|
|
|
|
20.
Yang R. Multi-frame quality enhancement for compressed video.
Conference on Computer Vision and Pattern Recognition (CVPR),2018:6664-6673
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问