For the shadowgraphy techniques with a single camera, it is difficult to accurately obtain the shape, size, and depth location of the droplets out of focus due to the defocus blur. This paper proposed a deep learning-based method to recover the sharp images and infer the depth information from the defocused blur droplets images. The proposed model comprising of a defocus map estimation subnetwork and a defocus deblur subnetwork is optimized with a two-stage strategy. To train the networks, the synthetic blur data generated by the Gauss kernel method are utilized as the input data, which mimic the defocused images of droplets. The proposed approach has been assessed based on synthetic images and real sphere blur images. The results demonstrate that our method has satisfactory performance both in terms of depth location estimation and droplet size measurement, e.g., the diameter relative error is less than 5% and the location error is less than 1 mm for the sphere with a diameter of more than 1 mm. Moreover, the present model also exhibits considerable generalization and robustness against the transparent ellipsoid and the random background noise. A further application of the present model to the measurement of transparent water droplets generated by an injector is also explored and illustrates the practicability of the present model in real experiments. The present study indicates that the proposed learning-based method is promising for the three-dimensional (3D) measurement of spray droplets via a combination of shadowgraphy techniques using a single camera, which will greatly reduce experimental costs and complexity.

1.
C.
Tropea
, “
Optical particle characterization in flows
,”
Annu. Rev. Fluid Mech.
43
,
399
(
2011
).
2.
D. L.
Hofeldt
and
R. K.
Hanson
, “
Instantaneous imaging of particle size and spatial distribution in two-phase flows
,”
Appl. Opt.
30
,
4936
(
1991
).
3.
H.
Zhang
,
X.
Yi
,
Y.
Du
,
R.
Zhang
,
X.
Zhang
,
F.
He
,
F.
Niu
, and
P.
Hao
, “
Dynamic behavior of water drops impacting on cylindrical superhydrophobic surfaces
,”
Phys. Fluids
31
,
032104
(
2019
).
4.
H.
Zhang
,
X.
Zhang
,
X.
Yi
,
F.
He
,
F.
Niu
, and
P.
Hao
, “
Asymmetric splash and breakup of drops impacting on cylindrical superhydrophobic surfaces
,”
Phys. Fluids
32
,
122108
(
2020
).
5.
N.
Bremond
and
E.
Villermaux
, “
Atomization by jet impact
,”
J. Fluid Mech.
549
,
273
(
2006
).
6.
G.
Vadlamudi
,
S. K.
Thirumalaikumaran
,
D.
Chakravortty
,
A.
Saha
, and
S.
Basu
, “
Penetration and aerosolization of cough droplet spray through face masks: A unique pathway of transmission of infection
,”
Phys. Fluids
34
,
052108
(
2022
).
7.
H.
Zhang
,
X.
Zhang
,
X.
Yi
,
F.
He
,
F.
Niu
, and
P.
Hao
, “
Reversed role of liquid viscosity on drop splash
,”
Phys. Fluids
33
,
052103
(
2021
).
8.
H.
Zhang
,
X.
Zhang
,
X.
Yi
,
Y.
Du
,
F.
He
,
F.
Niu
, and
P.
Hao
, “
How surface roughness promotes or suppresses drop splash
,”
Phys. Fluids
34
,
022111
(
2022
).
9.
K. S.
Kim
and
S. S.
Kim
, “
Drop sizing and depth-of-field correction in TV imaging
,”
Atomization Sprays
4
,
65
(
1994
).
10.
A.
Lecuona
,
P.
Sosa
,
P. A.
Rodríguez
, and
R. I.
Zequeira
, “
Volumetric characterization of dispersed two-phase flows by digital image analysis
,”
Meas. Sci. Technol.
11
,
1152
(
2000
).
11.
S. Y.
Lee
and
Y. D.
Kim
, “
Sizing of spray particles using image processing technique
,”
KSME Int. J.
18
,
879
(
2004
).
12.
K. U.
Koh
,
J. Y.
Kim
, and
S. Y.
Lee
, “
Determination of in-focus criteria and depth of field in image processing of spray particles
,”
Atomization Sprays
11
,
317
(
2001
).
13.
S. V.
Minov
,
F.
Cointault
,
J.
Vangeyte
,
J. G.
Pieters
, and
D.
Nuyttens
, “
Spray droplet characterization from a single nozzle by high speed image analysis using an in-focus droplet criterion
,”
Sensors (Basel)
16
,
218
(
2016
).
14.
J. B.
Blaisot
and
J.
Yon
, “
Droplet size and morphology characterization for dense sprays by image processing: Application to the diesel spray
,”
Exp. Fluids
39
,
977
(
2005
).
15.
N.
Fdida
and
J.-B.
Blaisot
, “
Drop size distribution measured by imaging: Determination of the measurement volume by the calibration of the point spread function
,”
Meas. Sci. Technol.
21
,
025501
(
2010
).
16.
M.
Legrand
,
J.
Nogueira
,
A.
Lecuona
, and
A.
Hernando
, “
Single camera volumetric shadowgraphy system for simultaneous droplet sizing and depth location, including empirical determination of the effective optical aperture
,”
Exp. Therm. Fluid Sci.
76
,
135
(
2016
).
17.
D.
Ju
,
J. S.
Shrimpton
, and
A.
Hearn
, “
A multi-thresholding algorithm for sizing out of focus particles
,”
Part. Part. Syst. Charact.
29
,
78
(
2012
).
18.
W.
Zhou
,
C.
Tropea
,
B.
Chen
,
Y.
Zhang
,
X.
Luo
, and
X.
Cai
, “
Spray drop measurements using depth from defocus
,”
Meas. Sci. Technol.
31
,
075901
(
2020
).
19.
W.
Zhou
,
Y.
Zhang
,
B.
Chen
,
C.
Tropea
,
R.
Xu
, and
X.
Cai
, “
Sensitivity analysis and measurement uncertainties of a two-camera depth from defocus imaging system
,”
Exp. Fluids
62
,
224
(
2021
).
20.
Y.
LeCun
,
Y.
Bengio
, and
G.
Hinton
, “
Deep learning
,”
Nature
521
,
436
(
2015
).
21.
J. S.
Oh
,
H.
Lee
, and
W.
Hwang
, “
Motion blur treatment utilizing deep learning for time-resolved particle image velocimetry
,”
Exp. Fluids
62
,
234
(
2021
).
22.
M.
Morimoto
,
K.
Fukami
, and
K.
Fukagata
, “
Experimental velocity data estimation for imperfect particle images using machine learning
,”
Phys. Fluids
33
,
087121
(
2021
).
23.
Z.
Wang
,
X.
Li
,
L.
Liu
,
X.
Wu
,
P.
Hao
,
X.
Zhang
, and
a.
He
, “
Deep-learning-based super-resolution reconstruction of high-speed imaging in fluids
,”
Phys. Fluids
34
,
037107
(
2022
).
24.
Y.
Ruomei
and
S.
Ling
, “
Blind image blur estimation via deep learning
,”
IEEE Trans. Image Process
25
,
1910
(
2016
).
25.
J.
Lee
,
S.
Lee
,
S.
Cho
, and
S.
Lee
, “
Deep defocus map estimation using domain adaptation
,” in
2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
,
2019
.
26.
A.
Abuolaim
and
M. S.
Brown
,
Defocus Deblurring Using Dual-Pixel Data
(
Springer International Publishing
,
Cham
,
2020
).
27.
S.
Xin
,
N.
Wadhwa
,
T.
Xue
,
J. T.
Barron
,
P. P.
Srinivasan
,
J.
Chen
,
I.
Gkioulekas
, and
R.
Garg
, “
Defocus map estimation and deblurring from a single dual-pixel image
,” in
2021 IEEE/CVF International Conference on Computer Vision (ICCV)
(
IEEE
,
2021
), p.
2208
.
28.
S.
Franchini
and
S.
Krevor
, “
Cut, overlap and locate: A deep learning approach for the 3D localization of particles in astigmatic optical setups
,”
Exp. Fluids
61
,
140
(
2020
).
29.
S.
Shao
,
K.
Mallery
, and
J.
Hong
, “
Machine learning holography for measuring 3D particle distribution
,”
Chem. Eng. Sci.
225
,
115830
(
2020
).
30.
J.
Ilonen
,
R.
Juránek
,
T.
Eerola
,
L.
Lensu
,
M.
Dubská
,
P.
Zemčík
, and
H.
Kälviäinen
, “
Comparison of bubble detectors and size distribution estimators
,”
Pattern Recognit. Lett.
101
,
60
(
2018
).
31.
I.
Poletaev
,
M. P.
Tokarev
, and
K. S.
Pervunin
, “
Bubble patterns recognition using neural networks: Application to the analysis of a two-phase bubbly jet
,”
Int. J. Multiphase Flow
126
,
103194
(
2020
).
32.
T.
Haas
,
C.
Schubert
,
M.
Eickhoff
, and
H.
Pfeifer
, “
BubCNN: Bubble detection using Faster RCNN and shape regression network
,”
Chem. Eng. Sci.
216
,
115467
(
2020
).
33.
J.
Li
,
S.
Shao
, and
J.
Hong
, “
Machine learning shadowgraph for particle size and shape characterization
,”
Meas. Sci. Technol.
32
,
015406
(
2021
).
34.
C.
Gong
,
Y.
Song
,
G.
Huang
,
W.
Chen
,
J.
Yin
, and
D.
Wang
, “
BubDepth: A neural network approach to three-dimensional reconstruction of bubble geometry from single-view images
,”
Int. J. Multiphase Flow
152
,
104100
(
2022
).
35.
A. P.
Pentland
, “
A new sense for depth of field
,”
IEEE Trans. Pattern Anal. Mach. Intell.
PAMI-9
,
523
(
1987
).
36.
H.
Ma
,
S.
Liu
,
Q.
Liao
,
J.
Zhang
, and
J. H.
Xue
, “
Defocus image deblurring network with defocus map estimation as auxiliary task
,”
IEEE Trans. Image Process.
31
,
216
(
2022
).
37.
W.
Shi
,
J.
Caballero
,
F.
Huszár
,
J.
Totz
,
A. P.
Aitken
,
R.
Bishop
,
D.
Rueckert
, and
Z.
Wang
, “
Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network
,” in
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
,
2016
.
You do not currently have access to this content.