Key Laboratory of Biomimetic Robots and Systems, School of Optics and Photonics, Beijing Institute of Technology, Beijing 100081, China.
Sensors (Basel). 2019 Sep 27;19(19):4190. doi: 10.3390/s19194190.
Fourier single pixel imaging (FSPI) is well known for reconstructing high quality images but only at the cost of long imaging time. For real-time applications, FSPI relies on under-sampled reconstructions, failing to provide high quality images. In order to improve imaging quality of real-time FSPI, a fast image reconstruction framework based on deep learning (DL) is proposed. More specifically, a deep convolutional autoencoder network with symmetric skip connection architecture for real time 96 × 96 imaging at very low sampling rates (5-8%) is employed. The network is trained on a large image set and is able to reconstruct diverse images unseen during training. The promising experimental results show that the proposed FSPI coupled with DL (termed DL-FSPI) outperforms conventional FSPI in terms of image quality at very low sampling rates.
傅里叶单像素成像（FSPI）以重建高质量图像而闻名，但这是以较长的成像时间为代价的。对于实时应用，FSPI 依赖于欠采样重建，无法提供高质量的图像。为了提高实时 FSPI 的成像质量，提出了一种基于深度学习（DL）的快速图像重建框架。更具体地说，使用了具有对称跳过连接结构的深度卷积自动编码器网络，用于在非常低的采样率（5-8%）下实时进行 96×96 成像。该网络在一个大型图像集中进行训练，能够重建训练过程中未见过的各种图像。有前景的实验结果表明，所提出的与 DL 结合的 FSPI（称为 DL-FSPI）在非常低的采样率下的图像质量方面优于传统的 FSPI。
