Model-free prediction of atmospheric warp based on artificial neural network
- 16 October 2014
- journal article
- Published by Optica Publishing Group in Applied Optics
- Vol. 53 (30) , 7087-7094
Abstract
This paper presents the application of artificial neural network for predicting the warping of images of remote objects or scenes ahead of time. The algorithm is based on estimating the pattern of warping of previously captured short-exposure frames through a generalized regression neural network (GRNN) and then predicting the warping of the upcoming frame. A high-accuracy optical flow technique is employed to estimate the dense motion fields of the captured frames, which are considered as training data for the GRNN. The proposed approach is independent of the pixel-oscillatory model unlike the state-of-the-art Kalman filter (KF) approach. Simulation experiments on synthetic and real-world turbulence degraded videos show that the proposed GRNN-based approach performs better than the KF approach in atmospheric warp prediction.Keywords
This publication has 17 references indexed in Scilit:
- A Linear Systems Approach to Imaging Through TurbulenceJournal of Mathematical Imaging and Vision, 2013
- High Precision Restoration Method for Non-uniformly Warped Images2013
- Atmospheric-Turbulence-Degraded Astronomical Image Restoration by Minimizing Second-Order Central MomentIEEE Geoscience and Remote Sensing Letters, 2012
- Non rigid geometric distortions correction - Application to atmospheric turbulence stabilizationInverse Problems and Imaging, 2012
- Near Real-Time Restoration of Non-Uniformly Warped Images from a Dynamic Scenery2011
- Image reconstruction from videos distorted by atmospheric turbulence2010
- Statistical Turbulence Approach to the Covariance Matrices in the Shiftmap Prediction Using Kalman Filter2009
- Blind deconvolution algorithms for the restoration of atmospherically degraded imagery: a comparative analysis2008
- Atmospheric Turbulence-Degraded Image Restoration Using Principal Components AnalysisIEEE Geoscience and Remote Sensing Letters, 2007
- Atmospheric turbulence visualization with wide-area motion-blur restorationJournal of the Optical Society of America A, 1999