Laser illumination compressed sensing imaging based on deep learning

In order to compensate for the low spatial resolution of laser illumination imaging system due to the single photon detector with small number of pixels. In order to solve this problem, we demonstrated a laser illumination imaging system with compressed coded and introduced the application of deep learning in compressed sensing (CS) image reconstruction based on residual network. Specifically, by considering the priori information of sparsity, the better imaging results with much higher resolution could be obtained with a small amount of observation data. The digital micro-mirror device (DMD) is used to achieve sparse coding in this work. We designed to use two detectors to collect information in two reflection directions of DMD, which can reduce samples by 50%. In addition, considering that the time complexity of traditional CS reconstruction methods is too high, so we introduced CS reconstruction method based on residual network into our work, and did the simulation experiments with our data. According to the experimental results, our method performed better at the perspective of image quality evaluation index PSNR and consumption time in reconstruction process.

[1]  David B. Thomas,et al.  Redundancy-Reduced MobileNet Acceleration on Reconfigurable Logic for ImageNet Classification , 2018, ARC.

[2]  Pavan K. Turaga,et al.  ReconNet: Non-Iterative Reconstruction of Images from Compressively Sensed Measurements , 2016, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[3]  Timothy Lillicrap,et al.  Deep Compressed Sensing , 2019, ICML.

[4]  Jianjun Wang,et al.  Tensor restricted isometry property analysis for a large class of random measurement ensembles , 2019, Science China Information Sciences.

[5]  Trac D. Tran,et al.  Iterative Convex Refinement for Sparse Recovery , 2015, IEEE Signal Processing Letters.

[6]  Michael Elad,et al.  A Deep Learning Approach to Block-based Compressed Sensing of Images , 2016, ArXiv.

[7]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[8]  Naima Kaabouch,et al.  Compressive sensing: Performance comparison of sparse recovery algorithms , 2018, 2017 IEEE 7th Annual Computing and Communication Workshop and Conference (CCWC).

[9]  Yichen Wei,et al.  Relation Networks for Object Detection , 2017, 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.

[10]  Fei-Fei Li,et al.  ImageNet: A large-scale hierarchical image database , 2009, 2009 IEEE Conference on Computer Vision and Pattern Recognition.

[11]  Amir H. Banihashemi,et al.  Iterative Reweighted $\ell_{2}/\ell_{1}$ Recovery Algorithms for Compressed Sensing of Block Sparse Signals , 2015, IEEE Transactions on Signal Processing.

[12]  Christian W. Smith,et al.  A data-driven approach to sampling matrix selection for compressive sensing , 2019, Computational Imaging V.

[13]  Yun Fu,et al.  Image Super-Resolution Using Very Deep Residual Channel Attention Networks , 2018, ECCV.

[14]  Trevor Darrell,et al.  Caffe: Convolutional Architecture for Fast Feature Embedding , 2014, ACM Multimedia.

[15]  Richard G Baraniuk,et al.  More Is Less: Signal Processing and the Data Deluge , 2011, Science.

[16]  慧 廣瀬.  A Mathematical Introduction to Compressive Sensing , 2015 .

[17]  H. Vincent Poor,et al.  Universal compressed sensing , 2014, 2016 IEEE International Symposium on Information Theory (ISIT).

[18]  Xun Xu,et al.  Fully-Convolutional Measurement Network for Compressive Sensing Image Reconstruction , 2017, Neurocomputing.