Atmospheric turbulence mitigation for sequences with moving objects using recursive image fusion

TL;DR

This paper introduces a recursive image fusion method using DT-CWT to mitigate atmospheric distortion in sequences with moving objects, improving image clarity and detail behind the distortion layer.

Contribution

It presents a novel fusion approach based on DT-CWT and improved GMM and Kalman filtering for effective atmospheric distortion mitigation in videos with moving objects.

Findings

Enhanced video quality over existing methods

Effective distortion reduction while preserving details

Competitive processing speed

Abstract

This paper describes a new method for mitigating the effects of atmospheric distortion on observed sequences that include large moving objects. In order to provide accurate detail from objects behind the distorting layer, we solve the space-variant distortion problem using recursive image fusion based on the Dual Tree Complex Wavelet Transform (DT-CWT). The moving objects are detected and tracked using the improved Gaussian mixture models (GMM) and Kalman filtering. New fusion rules are introduced which work on the magnitudes and angles of the DT-CWT coefficients independently to achieve a sharp image and to reduce atmospheric distortion, respectively. The subjective results show that the proposed method achieves better video quality than other existing methods with competitive speed.