ONLINE SUNFLICKER REMOVAL USING DYNAMIC TEXTURE

PREDICTION

A. S. M. Shihavuddin, Nuno Gracias and Rafael Garcia

Computer Vision and Robotics Group, Universitat de Girona, Girona, Spain

Keywords:

Sunﬂicker, Dynamic Texture, Illumination Field, Shallow Underwater Images.

Abstract:

An underwater vision system operating in shallow water faces unique challenges, which often degrade the

quality of the acquired data. One of these challenges is the sunﬂicker effect, created from refracted sunlight

casting fast moving patterns on the seaﬂoor. Surprisingly few previous works exist to address this topic. The

best performing available method mitigates the sunﬂickering effect using ofﬂine motion compensated ﬁltering.

In the present work, we propose an online sunﬂicker removal method targeted at producing better registration

accuracy. The illumination ﬁeld of the sunﬂicker effect is considered as a dynamic texture, since it produces

repetitive dynamic patterns. With that assumption, the dynamic model of the sunﬂicker is learned from the

registered illumination ﬁelds of the previous frames and is used for predicting that of the next coming frame.

Such prediction allows for removing the sunﬂicker patterns from the new frame and successfully register it

against previous frames. Comparative results are presented using challenging test sequences which illustrate

the better performance of the approach against the closest related method in the literature.

1 INTRODUCTION

In the ﬁeld of underwater image sensing, new and

complex challenges need to be addressed like light

scattering, sunﬂicker effects, color shifts, shape dis-

tortion, visibility degradation, blurring effects and

many others. The research work presented in this pa-

per deals with the presence of strong light ﬂuctuations

due to refraction, commonly found in shallow under-

water imaging. Refracted sunlight generates dynamic

patterns, which degrade the image quality and the in-

formation content of the acquired data. The sunﬂick-

ering effect creates a difﬁcult challenge to the scien-

tists to understand and to interpret the benthos. Devel-

opment of an online method to completely or partially

eliminate this effect is a prerequisite to ensure optimal

performance of underwater imaging algorithms.

2 RELATED WORK

Motivated by the work by on effective shadow re-

moval method (Weiss, 2001) in land scenes and the

work on shadow elimination (Matsushita et al., 2002)

on video surveillance, Schechner and Karpel devel-

oped an approach (Schechner and Karpel, 2004a) to

solve the sunﬂicker removal problem based on the

observation that the spatial intensity gradients of the

caustics tend to be sparse. Under that assumption,

doing the temporal median over the gradients of a

small number of images, a gradient ﬁeld was ob-

tained where the illumination effect was greatly re-

duced. The ﬂicker free image was obtained by inte-

grating the median gradient ﬁeld. This sunﬂicker re-

moval method (Schechner and Karpel, 2004a) did not

take into consideration the camera motion for which

registration inaccuracies are likely to appear. Us-

ing the method by Sarel and Irani (Sarel and Irani,

2004; Ukrainitz and Irani, 2006) two transparent over-

lapped video can be separated using the information

exchange theory, if one of the video mentioned con-

tains a repetitive dynamic sequence. This method

(Sarel and Irani, 2004) claims to work for the repeti-

tive dynamic sequence with variation in each repeated

cycle, though the variation amount in the repetitive

dynamic sequence is not quantitatively deﬁned. On

the other hand, a large number of frames would be

required to grab a complete cycle of a repetitive dy-

namic sequence, making it impractical for moving

cameras. An interesting approach to this problem

can be to use polarization information (Schechner and

Karpel, 2004b), to improve visibility underwater and

in deep space. The refracted sunlight underwater has

unique polarization characteristics. The exploitation

161

S. M. Shihavuddin A., Gracias N. and Garcia R..

ONLINE SUNFLICKER REMOVAL USING DYNAMIC TEXTURE PREDICTION.

DOI: 10.5220/0003811901610167

In Proceedings of the International Conference on Computer Vision Theory and Applications (VISAPP-2012), pages 161-167

ISBN: 978-989-8565-03-7

 2012 SCITEPRESS (Science and Technology Publications, Lda.)

of such characteristics is possible, but requires spe-

cial cameras with polarized ﬁlters or imaging sensors,

which are not commonly deployed. Another way of

looking in to the same problem can be to recover the

low rank matrix (Cand

es et al., 2009) which presents

the illumination ﬁeld. But this method only works

when there is no camera motion which in our case is

impractical.

The work by Gracias et al. (Gracias et al., 2008)

can be considered as the state of art among the meth-

ods that have addressed the removal of sunﬂicker in

shallow underwater images. This motion compen-

sated ﬁltering approach accounted for the basic re-

quirement that the camera should be allowed to move

during acquisition, thus being more adequate to real

optical survey work. The method is based on the as-

sumption that video sequences allow several observa-

tions of the same area of the seaﬂoor, over time. If the

assumption is valid, it is possible to compute the im-

age difference between a given reference frame and

the temporal median of a registered set of neighbor-

ing images. The most important observation is that

this difference will have two components with sepa-

rable spectral content. One is related to the illumi-

nation ﬁeld (which has lower spatial frequencies) and

the other to the registration inaccuracies (mainly hav-

ing higher frequencies). The illumination ﬁeld can be

approximately recovered by using low–pass ﬁltering.

The main limitation is that the median image for each

frame is obtained from both past and future frames,

thus making it non causal.

3 APPROACH

The presented method uses dynamic texture modeling

and synthesizing (Doretto et al., 2003), using princi-

pal component analysis, to predict the sunﬂicker pat-

tern of the next frame from the previous few frames.

The prediction is then used to coarsely remove the il-

lumination ﬁeld from the current working frame. The

presented approach attains higher registration per-

formance even under heavy illumination ﬂuctuation.

Also this method is strictly causal (i.e. does not rely

on future observations), fulﬁlling the important con-

dition of online operation required for visual-based

robot navigation.

3.1 Dynamic Texture Modeling and

Synthesizing

The Open Loop Linear Dynamic system (OLLDS)

model (Doretto et al., 2003) is used to learn the dy-

namic model of sunﬂicker illumination pattern and to

synthesize it for unknown cases. Once modeling is

done, the OLLDS can potentially be used for extrap-

olating synthetic sequences of any duration at negli-

gible computational cost. The underlying assumption

in this approach is that, the individual images are real-

izations of the output of a dynamical system driven by

an independent and identically distributed (IID) pro-

cess.

For learning the model parameters, the OLLDS

model uses one of two criteria: total likelihood or pre-

diction error. Under the hypothesis of second-order

stationarity, a closed-form sub-optimal solution of the

learning problem can be obtained as follows (Doretto

et al., 2003).

1. A linear dynamic texture is modeled as an auto-

regressive moving average process (ARMA) with un-

known input distribution, in the form,

x(t + 1) = Ax(t) + Bv(t) v(t) ≈ N(0, Q) x(0) = x

y(t) = Cx(t)+ w(t) w(t) ≈ N(0, R)

where y(t) belongs to R

is the observation vector; x(t)

belonging to R

, is the hidden state vector (r is much

smaller than n); A is the system matrix; C is the output

matrix and v(t), w(t) are Gaussian white noises. Here

y(t) presents the noisy output, in this case the image

sequences.

2. Taking the SVD of y(t), C can be found.

= UΣV

C(τ) = U X(τ) = ΣV

3. A can be determined uniquely by,

A(τ) = ΣV

V (V

V )

−1

Where



0 0

τ−1





τ−1

0 0



Also, Q and B can be found by

Q(τ) =

1 − τ

τ−1

∑

i=1

v(i)v

(i)

= Q

3.2 Motion Compensated Filtering

Let us consider a set of registered images. We refer

to a given image by the discrete parameter i which

indexes the images temporally. The radiance L of a

given pixel with coordinates (x, y) can be modelled

(x, y) = E

(x, y) · R

(x, y)

VISAPP 2012 - International Conference on Computer Vision Theory and Applications

162

where E

is the irradiance of the sunlight over the 3D

scene at the location deﬁned by pixel (x, y) at time i,

after absorption in the water. R(x, y) is the bidirec-

tional reﬂectance distribution function. For underwa-

ter natural scenes, where diffuse reﬂectance models

are applicable, R is assumed independent of both light

and view directions.

Converting the expression for L

to a logarithmic

scale allows the use of linear ﬁltering over the illumi-

nation and reﬂectance.

(x, y) = e

(x, y) + r

(x, y)

For approximately constant water depth, and for

realistic ﬁnite cases, the median converges signiﬁ-

cantly faster to average value of l

than the sample

mean.

med

(x, y) = med

[i0,i1]

(x, y) ≈ e + r

med

(x, y)

Here r

med

(x, y) stands for an approximation to the

median of reﬂectance. The difference d

(x, y) of a

given image l

(x, y) with the median radiance l

med

(x,

y) is used to recover the approximate background im-

age.

(x, y) = l

(x, y) − I

med

(x, y)

≈ (e

(x, y) − e) + (r

(x, y) − r

med

(x, y))

This difference d

(x,y) has two main components.

The ﬁrst component relates to the instant ﬂuctuation

of the illumination ﬁeld and has lower spatial frequen-

cies. This component will have positive values in the

over-illuminated areas where there is convergence of

the refracted sunlight and will have negative values

in the areas where the sunlight is diverted away. The

second component relates to inaccuracies in the image

registration and has higher spatial frequencies. Af-

ter applying a low pass ﬁlter on the difference image,

the low frequency components which resembles the

illumination ﬁeld is kept in the output. This approx-

imated illumination ﬁeld is later used to correct the

main input image and recover a ﬂicker–free image.

4 PROPOSED ALGORITHM

In the online sunﬂicker removal method proposed in

this work, the approximate illumination ﬁeld of the

current frame is found from the dynamic texture pre-

diction step. The homography is mainly calculated

between the temporary recovered current image (us-

ing the approximate illumination of the current frame)

and the last recovered image. Finally, the new image

can be recovered by using a median image calculated

from the current and previous few images warped

with respect to the current image using the calculated

homography. The median image and the current im-

ages can be used to ﬁnd the difference image for the

current frame. The difference images after being ﬁl-

tered through a low pass ﬁlter only holds the low fre-

quency components which represents the correct illu-

mination ﬁeld. Using this correct illumination ﬁeld

the working image is recovered from the sunﬂicker

effect. The steps are demonstrated as in ﬁg. 1

Figure 1: Step by step ﬂow diagram of the proposed online

method for sunﬂicker removal. From left to right, (1)warp-

ing previous illumination ﬁeld to the current frame, (2)pre-

dicting the current illumination ﬁeld, (3)coarsely recover-

ing the current image, (4)ﬁnding homography between the

current and the previous frame and (5)removing sunﬂicker

pattern from the image using the calculated homography.

The proposed approach considers the following

mentioned assumption to be valid

• Illumination ﬁeld is a dynamic texture

• Camera movement in the video sequence is smooth

• Bottom of the sea is approximately ﬂat

The main algorithm contains several steps which

are presented next, using the following nomenclature:

• I

0,k

- Original input image obtained at time instant k

• I

R,k

- Recovered image obtained from I

0,k

after sun-

ﬂicker removal

• H

- low pass ﬁltered version of the difference image

at time k, which is used as estimate of the illumination

ﬁeld at time k

• I

M,k

- Median image obtained from N frames after be-

ing warped into the frame of image I

0,k

• N - the number of images present in the learning se-

quence.

• M

k,k−1

- Homography relating the image frames at time

k and k − 1.

The algorithm comprises the following steps:

1. Apply the motion compensated ﬁltering

method (Gracias et al., 2008) to register and recover

ONLINE SUNFLICKER REMOVAL USING DYNAMIC TEXTURE PREDICTION

163

ﬁrst few images from the sun ﬂickering effects. In our

implemented system, we used ﬁrst the 25 frames for

this step.

2. Get the new image in the sequence I

0,k

assum-

ing that the previous images I

0,k−1

, . . . , I

0,k−N

have

been recovered after sunﬂicker removal (I

R,k−1

, . . . ,

R,k−N

). Advance time k (i.e. all previous data struc-

tures that had index k now have index k − 1).

3. Predict the ﬂicker pattern by

• Warping all the ﬁltered version of the difference im-

ages, H

k−1

, . . . , H

k−N

with respect to the current frame

0,k

to be recovered , assuming that M

k,k−1

≈ M

k−1,k−2

All other previous homographies were obtained from

actual image matches and thus known previously.

• Learning the sunﬂicker pattern from the registered ﬁl-

tered difference images. After registration, the motion

of the camera is being compensated. In the learning

phase, all the difference images of the previous frames

H (H

k−1

, . . . , H

k−N

) are converted into a column ma-

trix. Using the array of all the registered H (H

k−1

, . . . ,

k−N

) a large matrix called W

t−1

is created having P

rows and N columns. P is the number of pixels per

frame and N is the total number of frames in the learn-

ing sequence.

• Predicting the

using the learned model. For learn-

ing, open loop linear dynamic model (Doretto et al.,

2003) is being used. In this step the last frame H

k−1

of the learned sequence is considered as the ﬁrst frame

for the synthesize part.

4. Create the correction factor

using the pre-

dicted low pass ﬁltered version of the difference im-

age

and the approximate difference image

d,k

. To

ﬁnd the approximate difference image, the previously

recovered image I

R,K−1

is warped into the current

frame I

0,k

position using the last homography. Using

the warped portion of the previous recovered image

and the rest from current original image, a approxi-

mate median image is created, which is fused into the

system to ﬁnd the approximate difference image,

d,k

of the current frame. Using this approximated differ-

ence image

d,k

and the predicted

, the correction

factor

is found.

5. Apply predicted correction factor to I

0,k

. Us-

ing the correction factor

found in the last step, the

current image is approximately recovered from sun-

ﬂicker effect. This recovered image is denoted by

R,k

6. Perform image registration between

R,k

and

R,k−1

. From this obtain the real M

k,k−1

7. Update I

M,k

. Using the motion compensated

ﬁltering method (Gracias et al., 2008) create a median

image for the current frame using the last few original

frames. In this case, use the

R,k

to do the registration

during ﬁnding the current median image, I

M,k

8. Obtain ﬁnal I

R,k

. Using I

M,k

ﬁnd the real differ-

ence image for the current frame, I

d,k

and the correct

sunﬂicker pattern H

and later the correct recover im-

age I

R,k

removing the sunlight properly.

9. Go to step 2 and do the same for the next frames

The image registration is performed using the

classic approach of robust model based estimation

using Harris corner detection (Harris and Stephens,

1988) and normalized cross–correlation (Zhao et al.,

2006). This method proved more resilient to strong

illumination differences when compared with the re-

sult doing the same with SIFT (Lowe, 2004). Further-

more, the operation is considerably faster since the

search areas are small.

We assume the knowledge of the gamma values

for each color channel. For unknown gamma val-

ues one can apply blind gamma estimation. An ef-

ﬁcient method is described in (Farid, 2001; Farid and

Popescu, 2001), which exploits the fact that gamma

correction introduces speciﬁc higher-order correla-

tions in the frequency domain. Having the gamma

values we transform the intensities to linear scale.

After the deﬂickering the ﬁnal output images are

transformed into the sRGB space with the prescribed

gamma value.

The steps above are applied over each color chan-

nel independently. Strong caustics lead to overex-

posure and intensity clipping in one or more of the

color channels, resulting in chromaticity changes in

the original images. These clippings typically affect

different regions of the images over time, given the

non-stationary nature of the caustics. The median is

not affected by such transient clippings, whereas the

average is. The low pass ﬁltering is performed using

a fourth order Butterworth ﬁlter (Kovesi, 2009), with

a manually adjusted cutoff frequency.

Due to the camera motion, the stack of warped dif-

ference images described in step 3, may not cover the

entire area of the current frame. If one considers the

whole area of the current frame, this creates a condi-

tion of missing data in the W matrix for PCA. To cir-

cumvent this condition, only the maximum sized area

of the current frame which is present in each warped

frame at current frame location, is considered.

5 SELECTED RESULTS

The performance evaluation of the proposed system

was done comparing with the previously available of-

ﬂine method (Gracias et al., 2008) by evaluating both

on several test datasets of shallow water video se-

quences having distinct refracted sunlight conditions.

The main evaluation criterion is the number of inliers

found per time–consecutive image pair in each reg-

istration step. This criterion was found to be a good

VISAPP 2012 - International Conference on Computer Vision Theory and Applications

164

indicator the image de–ﬂickering performance. The

better the sunﬂicker removal is achieved, the larger

the number of found inliers per time–consecutive im-

age pair, considering all the other inﬂuencing factors

constant.

5.1 Grounding Sequence

The ﬁrst test sequence was obtained from a ship

grounding survey and contains illumination patterns

of relatively low spatial frequency. Fig. 2 shows an

example of how in each step the image is coarsely re-

covered, registered and ﬁnally cleaned. The top left

and bottom left parts of the image 2 show the original

input image and real illumination ﬁeld accordingly.

Using this initial estimate, the warped illumination

ﬁeld is learnt and predicted for the current frame; the

new image is temporarily cleaned with the prediction

of illumination ﬁeld and registered with respect to the

last recovered image. In the bottom middle of Fig. 2,

the predicted illumination ﬁeld is shown and the upper

middle part of the Fig. 2 represents the intermediate

condition of the illumination ﬁeld. The prediction il-

lumination ﬁelds approximates the real illumination

ﬁeld with some spatial displacements and intensity

variation. On the top right of Fig 2 shows the ﬁnal

recovered image and the bottom right of Fig 2 shows

the ﬁnal median image. Some examples of the ﬁnally

recovered images for difference video sequences are

given in Figs. 3(b), 3(d) and 3(f).

Figure 2: Step by step results for the grounding sequence.

The top left is the original input image and bottom left is

the original illumination ﬁeld in the input image. In the

top middle, the image is of the temporary recovered im-

age,

R,k

and the bottom middle is the predicted illumina-

tion ﬁeld. This was done using the predicted illumination

ﬁeld as shown in the bottom middle. On the top right is the

ﬁnally recovered image,

R,k

and on the bottom right is the

ﬁnal median image.

In Fig. 4 the proposed online method and the ex-

isting ofﬂine method (Gracias et al., 2008) are being

compared in terms of the number of inliers during the

registration step. From the graph, it can be seen that

the new method is outperforming the old method in

(a) Original Image (b) Recovered Image

(e) Original Image (f) Recovered Image

Figure 3: Illustration of the online sunﬂicker removal per-

formance.

almost all the frames. Quantitatively, matching per-

formance is improved by 46% based on the inliers de-

tected in every pair of frames. Without prediction, the

registration or the number of found inliers are vary-

ing very rapidly because of complete dependency on

the camera motion. In the case of prediction, it in-

cludes the displacement errors creating a generalized

solution which provides approximately constant out-

comes.

Figure 4: Comparison between proposed method and the

ofﬂine method for grounding sequence.

5.2 Rock Sequence

The Rock sequence is more challenging than the

grounding sequence, captured in shallow waters hav-

ing a very rocky bottom. Both the methods are be-

ing tested for sunﬂicker removal keeping other pa-

ONLINE SUNFLICKER REMOVAL USING DYNAMIC TEXTURE PREDICTION

165

rameters unchanged. The proposed online method

is also performing signiﬁcantly better than the ofﬂine

method in terms of found inliers per registration steps

as shown in Fig. 5. Overall gain in the matching per-

formance in the proposed method is about 67% com-

pared with the ofﬂine method.

Figure 5: Comparison between proposed method and the

ofﬂine method for Rock sequence.

5.3 Andros Sequence

This is the most challenging sequence of the three,

captured in very shallow waters of less than 2 meters

depth under intense sunlight. In this case, the illumi-

nation patterns have simultaneously very high spatial

and temporal frequencies which leads to the method

of (Gracias et al., 2008) to fail. In such situation it is

very hard to get a good registration performance. In

the Fig. 6, the graph shows that the proposed method

performs 15% better. This performance is achieved

because of the steady motion of the camera in this par-

ticular sequence. It proves the robustness of the online

method achieving better results even in such a difﬁcult

video sequence. In case of large registration errors,

the prediction model performance degrades rapidly.

Figure 6: Comparison between proposed method and the

ofﬂine method for Andros sequence.

6 CONCLUSIONS AND FUTURE

DIRECTION

This work addresses the speciﬁc problem of sun-

ﬂicker in shallow underwater images, by presenting

a method which is suited for de–ﬂickering on the ﬂy.

In the current online method, only the previous few

frames with the current frame are used to create me-

dian image. In this case, the homography is calculated

by registering the sunﬂicker removed version (using

prediction from dynamic texture model learned from

the last few frames) of current image with the last

ﬂicker–free image. This results in higher image reg-

istration accuracy than the ofﬂine method where the

registration is carried out over the original images af-

fected by the illumination patterns. The better regis-

tration then reﬂects in better median images estima-

tion and ultimately in better sunﬂickering correction.

This research was motivated by the fact that the

ﬂicker–free images will help creating more accurate

mosaics of the sea ﬂoor. Currently the method is im-

plemented in Matlab, and the code has not been op-

timized for speed. It takes 6.39 seconds per frame,

on average, when executed on an Intel core 2 Duo 2

GHz processor. However, being an on-line approach,

the method has the potential to be implemented for

real–time operation.

An extension to the current work is to relate the

illumination frequency with the number of frames re-

quired to perform sunﬂicker removal optimally. It can

be a way to know beforehand the minimum frame rate

of the camera required to remove the sunﬂicker effect

properly. Also, for instrumented imaging platforms,

the camera motion can be estimated using a motion

sensor, such as a rate gyro or an accelerometer. This

estimate can be used during the initialization phase of

the method, or whenever the image registration is not

possible.

Another extension addresses highly slanted cam-

era conﬁguration, where the illumination patterns

present distinct spatio-temporal frequencies for dif-

ferent regions of the image. In the described method,

the cutoff frequency of the the low-pass ﬁlter is con-

stant. As future work, this cutoff frequency will be

made adaptive to the spatial location and estimated

from image data.

ACKNOWLEDGEMENTS

This work was partially funded by the Spanish

MCINN under grant CTM2010-15216, and by the

EU Project FP7-ICT-2009-248497. ASM Shihavud-

din and Nuno Gracias were supported by the MCINN

under the FI and Ramon y Cajal programs.

VISAPP 2012 - International Conference on Computer Vision Theory and Applications

166

REFERENCES

Cand

es, E. J., Li, X., Ma, Y., and Wright, J. (2009). Robust

principal component analysis? CoRR, abs/0912.3599.

Doretto, G., Chiuso, A., Wu, Y. N., and Soatto, S. (2003).

Dynamic textures. International Journal of Computer

Vision, 51:91–109.

Farid, H. (2001). Blind inverse gamma correction. Im-

age Processing, IEEE Transactions on, 10(10):1428

–1433.

Farid, H. and Popescu, A. C. (2001). Blind removal of im-

age non-linearities. Computer Vision, IEEE Interna-

tional Conference on, 1:76.

Gracias, N., Negahdaripour, S., Neumann, L., Prados, R.,

and Garcia, R. (2008). A motion compensated ﬁlter-

ing approach to remove sunlight ﬂicker in shallow wa-

ter images. In OCEANS 2008.

Harris, C. and Stephens, M. (1988). A combined corner

and edge detector. In Fourth Alvey Vision Conference,

Manchester, UK, pages 147 –151.

Kovesi, P. D. (2009). Matlab and octave functions for com-

puter vision and image processing. School of Com-

puter Science Software Engineering.

Lowe, D. G. (2004). Distinctive image features from scale-

invariant keypoints. International Journal of Com-

puter Vision, 60:91–110.

Matsushita, Y., Nishino, K., Ikeuchi, K., and Sakauchi, M.

(2002). Shadow elimination for robust video surveil-

lance. Motion and Video Computing, IEEE Workshop

on, page 15.

Sarel, B. and Irani, M. (2004). Separating transparent lay-

ers through layer information exchange. In Pajdla, T.

and Matas, J., editors, Computer Vision - ECCV 2004,

volume 3024 of Lecture Notes in Computer Science,

pages 328–341. Springer Berlin / Heidelberg.

Schechner, Y. and Karpel, N. (2004a). Attenuating natu-

ral ﬂicker patterns. In IEEE TECHNO-OCEAN, 04,

volume 3, pages 1262 –1268.

Schechner, Y. and Karpel, N. (2004b). Recovering

scenes by polarization analysis. In OCEANS ’04.

MTTS/IEEE TECHNO-OCEAN ’04, volume 3, pages

1255 –1261 Vol.3.

Ukrainitz, Y. and Irani, M. (2006). Aligning sequences

and actions by maximizing space-time correlations.

In Leonardis, A., Bischof, H., and Pinz, A., edi-

tors, Computer Vision ECCV 2006, volume 3953 of

Lecture Notes in Computer Science, pages 538–550.

Springer Berlin / Heidelberg.

Weiss, Y. (2001). Deriving intrinsic images from image se-

quences. In Computer Vision, 2001. ICCV 2001. Pro-

ceedings. Eighth IEEE International Conference on,

volume 2, pages 68 –75.

Zhao, F., Huang, Q., and Gao, W. (2006). Image matching

by normalized cross-correlation. In Acoustics, Speech

and Signal Processing, 2006. ICASSP 2006 Proceed-

ings. 2006 IEEE International Conference on, vol-

ume 2.

ONLINE SUNFLICKER REMOVAL USING DYNAMIC TEXTURE PREDICTION

167