电子学报2023，Vol.51Issue(11)：3320-3330,11.DOI:10.12263/DZXB.20220958
基于MAP的多信息流梯度更新与聚合视频压缩感知重构算法
MAP-Based Multi-Information Flow Gradient Update and Aggregation for Video Compressed Sensing Reconstruction
摘要
Abstract
Due to the lack of guidance from the parallel update theoretical solver framework,existing deep learning-based distributed compressed video sensing(DCVS)algorithms alternately use measurement values and reference frames to optimize the reconstructed non-key frame,resulting in the inability to fully combine the two types of information and limit-ing the quality of reconstruction.In order to solve this problem,this paper firstly uses Bayesian theory and maximum a pos-teriori estimation(MAP)to derive the optimization equation of non-key frame reconstruction in DCVS,and then derives the solution framework of the optimization equation based on the proximal gradient algorithm,including multi-information flow gradient update and aggregation equation.Based on it,this paper designs a multi-information flow gradient update and aggregation neural network module(MIGA),and constructs a deep multi-information flow gradient update and aggregation network(DMIGAN)for DCVS non-key frame reconstruction.MIGA uses the measurement values and multiple reference frames to update the current non-key frame by parallel gradients,and then performs information interaction and fusion,so as to fully combine multiple information flows to update and reconstruct the frame.In this paper,the MIGA and the denois-ing sub-network are cascaded to simulate a single iteration of the proximal gradient algorithm as the basic phase.The deep reconstruction network DMIGAN is constructed by cascading multiple phases to realize the deep optimization process of frame reconstruction.Experiments show that,compared with the representative traditional iterative optimization algorithm structural similarity based inter-frame group sparse representation(SSIM-InterF-GSR),the performance of DMIGAN is im-proved by 8.8 dB and 7.36 dB at low sampling rate and high sampling rate respectively;and compared with the representa-tive deep learning reconstruction algorithm VCSNet-2,the performance is improved by 7.09 dB and 8.78 dB at low sam-pling rate and high sampling rate,respectively.关键词
分布式视频压缩感知/最大后验概率估计/多信息流梯度更新/信息聚合/迭代优化/光流估计Key words
distributed compressed video sensing/maximum a posteriori estimation/multi-information flow gradi-ent update/information aggregation/iterative optimization/optical flow estimation分类
信息技术与安全科学引用本文复制引用
杨鑫,杨春玲..基于MAP的多信息流梯度更新与聚合视频压缩感知重构算法[J].电子学报,2023,51(11):3320-3330,11.基金项目
广东省自然科学基金(No.2019A1515011949)Natural Science Foundation of Guangdong Province(No.2019A1515011949) （No.2019A1515011949）
