U-net like deep autoencoders for deblurring atmospheric turbulence

Chen, Gongping; Gao, Zhisheng; Wang, Qiaolu; Luo, Qingqing

doi:10.1117/1.jei.28.5.053024

Cited by 18 publications

(26 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The architecture from Chen et al 9 is the only architecture in this work that was initially designed to perform turbulence mitigation. It consists of three networks, the first of which is a Convolutional Autoencoder (CAE).…”

Section: Cae-unet-caementioning

confidence: 99%

“…Such an application of DL to turbulence mitigation has been considered before [9][10][11][12] ; however, this paper aims to assess the capabilities of several DL architectures that were not originally designed for turbulence mitigation. The motivation for this assessment is to evaluate which network will best adapt to the problem of turbulence mitigation.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of deep learning architectures for turbulence mitigation in long-range imagery

Vint

Caterina

Soraghan

et al. 2020

Artificial Intelligence and Machine Learning in Defense Applications II

View full text Add to dashboard Cite

In long range imagery, the atmosphere along the line of sight can result in unwanted visual effects. Random variations in the refractive index of the air causes light to shift and distort. When captured by a camera, this randomly induced variation results in blurred and spatially distorted images. The removal of such effects is greatly desired. Many traditional methods are able to reduce the effects of turbulence within images, however they require complex optimisation procedures or have large computational complexity. The use of deep learning for image processing has now become commonplace, with neural networks being able to outperform traditional methods in many fields. This paper presents an evaluation of various deep learning architectures on the task of turbulence mitigation. The core disadvantage of deep learning is the dependence on a large quantity of relevant data. For the task of turbulence mitigation, real life data is difficult to obtain, as a clean undistorted image is not always obtainable. Turbulent images were therefore generated with the use of a turbulence simulator. This was able to accurately represent atmospheric conditions and apply the resulting spatial distortions onto clean images. This paper provides a comparison between current state of the art image reconstruction convolutional neural networks. Each network is trained on simulated turbulence data. They are then assessed on a series of test images. It is shown that the networks are unable to provide high quality output images. However, they are shown to be able to reduce the effects of spatial warping within the test images. This paper provides critical analysis into the effectiveness of the application of deep learning. It is shown that deep learning has potential in this field, and can be used to make further improvements in the future.

show abstract

Section: Cae-unet-caementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Analysis of deep learning architectures for turbulence mitigation in long-range imagery

Vint

Caterina

Soraghan

et al. 2020

Artificial Intelligence and Machine Learning in Defense Applications II

View full text Add to dashboard Cite

show abstract

“…The significant improvement in deep learning and the implementation of CNN has been quite promising. [19][20][21] A major problem with deep learning is that a huge amount of data is required to train successful models. The CNN algorithm has made some improvements in the detection of facial expressions, but there are still some detachments in place, including too long training times and low recognizing rates in the complex environment.…”

Section: Introductionmentioning

confidence: 99%

Real-time emotion recognition using end-to-end attention-based fusion network

et al. 2023

View full text Add to dashboard Cite

.Real-time emotion detection based on facial expression is an innovative research field that has been applied in several areas, such as health, human–machine vision, and autonomous safety. Researchers in object detection are involved in developing methods to interpret, code facial expressions, and extract these features to be better predicted by machines. Furthermore, the success of deep learning with different architectures is exploited to achieve better performance. But these methods drastically fail in excessive sweating in different health conditions. We aim to create a dataset in different health conditions and detect facial emotion using the encoder and decoder-based deep learning methodology. The proposed architecture and the dataset present the progress made by comparing the other proposed methods and the quantitative and qualitative results obtained. The major benefit of our study is to enhance the emotion detection efficiency with other proposed methods and real-time applications for different health conditions. We propose the application of feature extraction of facial expressions with an end-to-end attention module-based fusion network for detecting different facial emotions (happy, angry, neutral, surprised, etc.) with an accuracy of 99.68%. The proposed system depends upon the human face; as we know, the face reflects human brain activities or emotions.

show abstract

“…The encoder-decoder framework allows the network to learn the latent space representation of the data. Such networks have been shown to work with image noise for tasks such as image deblurring [21] and super-resolution [22]. Hence, such a network was chosen for the present study to aid in dealing with speckle noise typically present in SAR images.…”

Section: Introductionmentioning

confidence: 99%

RUF: Effective Sea Ice Floe Segmentation Using End-to-End RES-UNET-CRF with Dual Loss

et al. 2021

View full text Add to dashboard Cite

Sea ice observations through satellite imaging have led to advancements in environmental research, ship navigation, and ice hazard forecasting in cold regions. Machine learning and, recently, deep learning techniques are being explored by various researchers to process vast amounts of Synthetic Aperture Radar (SAR) data for detecting potential hazards in navigational routes. Detection of hazards such as sea ice floes in Marginal Ice Zones (MIZs) is quite challenging as the floes are often embedded in a multiscale ice cover composed of ice filaments and eddies in addition to floes. This study proposes a segmentation model tailored for detecting ice floes in SAR images. The model exploits the advantages of both convolutional neural networks and convolutional conditional random field (Conv-CRF) in a combined manner. The residual UNET (RES-UNET) computes expressive features to generate coarse segmentation maps while the Conv-CRF exploits the spatial co-occurrence pairwise potentials along with the RES-UNET unary/segmentation maps to generate final predictions. The whole pipeline is trained end-to-end using a dual loss function. This dual loss function is composed of a weighted average of binary cross entropy and soft dice loss. The comparison of experimental results with the conventional segmentation networks such as UNET, DeepLabV3, and FCN-8 demonstrates the effectiveness of the proposed architecture.

show abstract

U-net like deep autoencoders for deblurring atmospheric turbulence

Cited by 18 publications

References 57 publications

Analysis of deep learning architectures for turbulence mitigation in long-range imagery

Analysis of deep learning architectures for turbulence mitigation in long-range imagery

Real-time emotion recognition using end-to-end attention-based fusion network

RUF: Effective Sea Ice Floe Segmentation Using End-to-End RES-UNET-CRF with Dual Loss

Contact Info

Product

Resources

About