Fourier Based Pre-Processing For Seeing Through Water

Ajit Rajwade

Abstract:

Consider a scene submerged underneath a fluctuating
water surface. Images of such a scene, when acquired from
a camera in the air, exhibit significant spatial distortions.
In this paper, we present a novel, computationally efficient
pre-processing algorithm to correct a significant amount
(≈ 50%) of apparent distortion present in video sequences
of such a scene. We demonstrate that when the partially
restored video output from this stage is given as input to
other methods, it significantly improves their performance.
This algorithm involves (i) tracking a small number N of
salient feature points across the T frames to yield pointtrajectories {qi , {(xit, yit)}
T
t=1}
N
i=1, and (ii) using the
point-trajectories to infer the deformations at other nontracked points in every frame. A Fourier decomposition
of the N trajectories, followed by a novel Fourier phaseinterpolation step, is used to infer deformations at all other
points. Our method exploits the inherent spatio-temporal
characteristics of the fluctuating water surface to correct
non-rigid deformations to a very large extent.
The source code, datasets and supplemental material can
be accessed at [1], [2].