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

Vint, David and Di Caterina, Gaetano and Soraghan, John and Lamb, Robert and Humphreys, David; Dijk, Judith, ed. (2020) Analysis of deep learning architectures for turbulence mitigation in long-range imagery. In: Artificial Intelligence and Machine Learning in Defense Applications II. SPIE, Bellingham, WA.. (

[thumbnail of Vint-etal-SPIE-2020-Analysis-of-deep-learning-architectures-for-turbulence]
Text. Filename: Vint_etal_SPIE_2020_Analysis_of_deep_learning_architectures_for_turbulence.pdf
Accepted Author Manuscript

Download (1MB)| Preview


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.