Ghost Imaging Based on Deep Learning

He, Yuchen; Gao, Wang; Dong, Guoxiang; Zhu, Shitao; Chen, Hui; Zhang, Anxue; Wang, Chao

doi:10.1038/s41598-018-24731-2

Cited by 128 publications

(52 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, various methods have been proposed to reduce the signal acquisitions and improve the imaging performance [21][22][23][24][25][26][27]. One of the widely used methods is to use orthonormal patterns (basis) to reduce the sampling ratio (SR) and illumination patterns.…”

Section: Introductionmentioning

confidence: 99%

“…By using a "Cake-Cutting" Hadamard basis optimization technique, a super sub-Nyquist sampling is realized and the acquisition time is significantly decreased. Another lately reported method is to use deep learning (DL) to decrease the SR [24][25][26][27]. In [24][25][26], three deep-learning-based methods are developed to lower the SR of CGI, where the input image is obtained by conventional GI.…”

Section: Introductionmentioning

confidence: 99%

“…Another lately reported method is to use deep learning (DL) to decrease the SR [24][25][26][27]. In [24][25][26], three deep-learning-based methods are developed to lower the SR of CGI, where the input image is obtained by conventional GI. Most recently, Wang et al demonstrated a neural network for CGI which reconstructs target images directly from the one-dimensional (1-D) bucket signals without the need of the illumination patterns [27].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Sub-Nyquist computational ghost imaging with deep learning

Wang

Zhao

et al. 2020

Opt. Express

View full text Add to dashboard Cite

We propose a deep learning computational ghost imaging (CGI) scheme to achieve sub-Nyquist and high-quality image reconstruction. Unlike the second-order-correlation CGI and compressive-sensing CGI, which use lots of illumination patterns and a one-dimensional (1-D) light intensity sequence (LIS) for image reconstruction, a deep neural network (DAttNet) is proposed to restore the target image only using the 1-D LIS. The DAttNet is trained with simulation data and retrieves the target image from experimental data. The experimental results indicate that the proposed scheme can provide high-quality images with a sub-Nyquist sampling ratio and performs better than the conventional and compressive-sensing CGI methods in sub-Nyquist sampling ratio conditions (e.g., 5.45%). The proposed scheme has potential practical applications in underwater, real-time and dynamic CGI.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Sub-Nyquist computational ghost imaging with deep learning

Wang

Zhao

et al. 2020

Opt. Express

View full text Add to dashboard Cite

show abstract

“…Deep learning (DL) has greatly inspired the research in object detection, image classification, signal processing, and among many others. For the inverse problem community, learning-based methods have been successfully employed in multiple scattering media imaging [24], holographic image reconstruction [25], lensless computational imaging [26], computational ghost imaging [27,28] and so forth, but they usually take a lot of effort to collect data set, which is not easily affordable. To reduce the cost of training, some researchers have proposed training imaging network with simulation data set.…”

Section: Introductionmentioning

confidence: 99%

Fast Terahertz Coded-Aperture Imaging Based on Convolutional Neural Network

et al. 2020

View full text Add to dashboard Cite

Terahertz coded-aperture imaging (TCAI) has many advantages such as forward-looking imaging, staring imaging and low cost and so forth. However, it is difficult to resolve the target under low signal-to-noise ratio (SNR) and the imaging process is time-consuming. Here, we provide an efficient solution to tackle this problem. A convolution neural network (CNN) is leveraged to develop an off-line end to end imaging network whose structure is highly parallel and free of iterations. And it can just act as a general and powerful mapping function. Once the network is well trained and adopted for TCAI signal processing, the target of interest can be recovered immediately from echo signal. Also, the method to generate training data is shown, and we find that the imaging network trained with simulation data is of good robustness against noise and model errors. The feasibility of the proposed approach is verified by simulation experiments and the results show that it has a competitive performance with the state-of-the-art algorithms.

show abstract

“…relying on basic correlation and probabilistic methods for target detection 14,15 . Recently, there have been some interesting studies that explore the potential of DL for GI [16][17][18][19][20] . For GI, the most relevant deep neural network model is the denoising autoencoder 21 .…”

mentioning

confidence: 99%

DeepGhost: real-time computational ghost imaging via deep learning

Rizvi

Cao

Zhang

et al. 2020

Sci Rep

View full text Add to dashboard Cite

the potential of random pattern based computational ghost imaging (cGi) for real-time applications has been offset by its long image reconstruction time and inefficient reconstruction of complex diverse scenes. to overcome these problems, we propose a fast image reconstruction framework for cGi, called "DeepGhost", using deep convolutional autoencoder network to achieve real-time imaging at very low sampling rates (10-20%). By transferring prior-knowledge from STL-10 dataset to physical-data driven network, the proposed framework can reconstruct complex unseen targets with high accuracy. The experimental results show that the proposed method outperforms existing deep learning and state-of-the-art compressed sensing methods used for ghost imaging under similar conditions. the proposed method employs deep architecture with fast computation, and tackles the shortcomings of existing schemes i.e., inappropriate architecture, training on limited data under controlled settings, and employing shallow network for fast computation. Computational ghost imaging 1 acquires spatial information about an unknown target by illuminating it with a series of random binary patterns generated by a spatial light modulator (SLM). For each projected pattern, the light intensity back-reflected from the target plane is recorded by an ordinary photodiode. By correlating intensity measurements with corresponding projected patterns, the target image is reconstructed. One downside of CGI is the requirement of a large number of measurements to produce a good-quality image, which increases its imaging time. Despite the emergence of basis scan schemes 2 , CGI (using random patterns) is still employed in many applications due to its simplicity, inherent encryption of patterns 3 , and ease of deployment 4. Therefore, it is important to improve the efficiency of CGI by integrating it with some optimization technique to avoid complex (hardware based) methods 5 that fail to reap the benefits of reduced cost and simplicity in ghost imaging (GI). Owing to its advantages of low cost, robustness against noise and scattering, and ability to operate over long spectral range, CGI is widely used in many applications 6-8. In order to make CGI practical, more specifically for real-time imaging, it is important to reduce its imaging time. The imaging time of CGI can be subcategorized as data acquisition time and image reconstruction time. The data acquisition time of CGI depends on the required number of measurements and mainly on the projection rate of SLM. Recent advances in SLM technology make it easy to reduce data acquisition time by employing commercially available high-resolution digital micromirror devices (DMDs) operating at ~ 20 kHz. The acquisition time can also be reduced by employing some simple yet novel solutions 9,10. Therefore, the image reconstruction time remains the main bottleneck towards achieving high speed imaging in CGI. This image reconstruction time can be reduced by employing an efficient image reconstruction framework. Recently, comp...

show abstract

Ghost Imaging Based on Deep Learning

Cited by 128 publications

References 41 publications

Sub-Nyquist computational ghost imaging with deep learning

Sub-Nyquist computational ghost imaging with deep learning

Fast Terahertz Coded-Aperture Imaging Based on Convolutional Neural Network

DeepGhost: real-time computational ghost imaging via deep learning

Contact Info

Product

Resources

About