Rethinking Atmospheric Turbulence Mitigation

Chimitt, Nicholas; Mao, Zhiyuan; Hong, Guanzhe; Chan, Stanley H.

doi:10.48550/arxiv.1905.07498

Cited by 3 publications

(2 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Whilst the theoretical OTF can provide an indication of a turbulent volume, the most accurate method of depicting the path of light is by implementing a propagation simulation [12]. These methods model the atmosphere using a series of complex planes called phase screens, which represent how the light wave changes path as it travels [13], [14]. Although the propagation of a single light wave can be achieved with minimal computation, the aggregate time required to perform a propagation for each pixel in an image can result in a computationally expensive simulation.…”

Section: Related Workmentioning

confidence: 99%

Simulation of Anisoplanatic Turbulence for Images and Videos

Vint,

Di Caterina,

Kirkland

et al. 2023

2023 Sensor Signal Processing for Defence Conference (SSPD)

View full text Add to dashboard Cite

Turbulence is a common phenomenon in the atmosphere and can generate a variety of distortions in an image. This can cause further image processing tasks to struggle due to lack of detail in the resulting turbulence affected imagery. It is therefore useful to attempt to remove such distortions as a post processing step. However, the development of such algorithms is difficult due to the complex nature of turbulence data acquisition. To alleviate these issues, this paper presents the development of a turbulence simulator that is capable of imparting the effects of a turbulent atmosphere onto clean images and videos. This work also provides a large, publicly available dataset that can be used as a benchmark. The simulator and dataset will be valuable resources in the field of turbulence mitigation. Indeed, the simulator allows researchers to simulate specific turbulent conditions for any application as required; while the dataset provides the ability to make use of turbulent data without the expensive time commitment of simulation.

show abstract

Section: Related Workmentioning

confidence: 99%

Simulation of Anisoplanatic Turbulence for Images and Videos

Vint,

Di Caterina,

Kirkland

et al. 2023

2023 Sensor Signal Processing for Defence Conference (SSPD)

View full text Add to dashboard Cite

show abstract

“…Most image processing techniques are designed for mitigating atmospheric turbulence effects in videos. They [21,23,19] often proceeds by combining the complementary clear regions across frames by the lucky fusion process and further performing deconvolution on this fused frame to get the restored output. With the success of deep networks in fast and accurate image reconstruction, a few deep learning techniques have also been proposed for atmospheric turbulence mitigation [7,3,24,25].…”

Section: Introductionmentioning

confidence: 99%

A Comparison of Different Atmospheric Turbulence Simulation Methods for Image Restoration

Gopalakrishnan

Mei

Patel

2022

2022 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

Atmospheric turbulence deteriorates the quality of images captured by long-range imaging systems by introducing blur and geometric distortions to the captured scene. This leads to a drastic drop in performance when computer vision algorithms like object/face recognition and detection are performed on these images. In recent years, various deep learning-based atmospheric turbulence mitigation methods have been proposed in the literature. These methods are often trained using synthetically generated images and tested on real-world images. Hence, the performance of these restoration methods depends on the type of simulation used for training the network. In this paper, we systematically evaluate the effectiveness of various turbulence simulation methods on image restoration. In particular, we evaluate the performance of two stateor-the-art restoration networks using six simulations method on a real-world LRFID dataset consisting of face images degraded by turbulence. This paper will provide guidance to the researchers and practitioners working in this field to choose the suitable data generation models for training deep models for turbulence mitigation. The implementation codes for the simulation methods, source codes for the networks and the pre-trained models are available at https://github.com/Nithin-GK/Turbulence-Simulations

show abstract

Estimation of modified Zernike coefficients from turbulence-degraded multispectral imagery using deep learning

Siddik,

Sandoval,

Voelz

et al. 2024

Appl. Opt.

View full text Add to dashboard Cite

We investigate how wavelength diversity affects the performance of a deep-learning model that predicts the modified Zernike coefficients of turbulence-induced wavefront error from multispectral images. The ability to perform accurate predictions of the coefficients from images collected in turbulent conditions has potential applications in image restoration. The source images for this work were a point object and extended objects taken from a character-based dataset, and a wavelength-dependent simulation was developed that applies the effects of isoplanatic atmospheric turbulence to the images. The simulation utilizes a phase screen resampling technique to emulate the simultaneous collection of each band of a multispectral image through the same turbulence realization. Simulated image data were generated for the point and extended objects at various turbulence levels, and a deep neural network architecture based on AlexNet was used to predict the modified Zernike coefficients. Mean squared error results demonstrate a significant improvement in predicting modified Zernike coefficients for both the point object and extended objects as the number of spectral bands is increased. However, the improvement with the number of bands was limited when using extended objects with additive noise.

show abstract

Rethinking Atmospheric Turbulence Mitigation

Cited by 3 publications

References 19 publications

Simulation of Anisoplanatic Turbulence for Images and Videos

Simulation of Anisoplanatic Turbulence for Images and Videos

A Comparison of Different Atmospheric Turbulence Simulation Methods for Image Restoration

Estimation of modified Zernike coefficients from turbulence-degraded multispectral imagery using deep learning

Contact Info

Product

Resources

About