CN111524083A - Active and passive combined underwater aerial imaging image recovery method based on structured light - Google Patents
Active and passive combined underwater aerial imaging image recovery method based on structured light Download PDFInfo
- Publication number
- CN111524083A CN111524083A CN202010379205.0A CN202010379205A CN111524083A CN 111524083 A CN111524083 A CN 111524083A CN 202010379205 A CN202010379205 A CN 202010379205A CN 111524083 A CN111524083 A CN 111524083A
- Authority
- CN
- China
- Prior art keywords
- image
- structured light
- distorted
- registration
- active
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 238000003384 imaging method Methods 0.000 title claims abstract description 26
- 238000011084 recovery Methods 0.000 title claims abstract description 13
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims abstract description 17
- 238000012937 correction Methods 0.000 claims abstract description 8
- 238000000926 separation method Methods 0.000 claims abstract description 4
- 238000005516 engineering process Methods 0.000 claims description 7
- 238000012546 transfer Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000001788 irregular Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 12
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000008569 process Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 241000135164 Timea Species 0.000 description 1
- NIXOWILDQLNWCW-UHFFFAOYSA-N acrylic acid group Chemical group C(C=C)(=O)O NIXOWILDQLNWCW-UHFFFAOYSA-N 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000012634 optical imaging Methods 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/80—Geometric correction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/14—Transformations for image registration, e.g. adjusting or mapping for alignment of images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/38—Registration of image sequences
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10016—Video; Image sequence
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an active and passive combined underwater air imaging image recovery method based on structured light, which comprises the steps of presetting a standard structured light image, and obtaining a distorted actual image and a distorted structured light image through three-channel image separation; carrying out image registration on the distorted structured light image and the standard structured light image to obtain a correction matrix; and performing secondary image registration by using the correction matrix and the distorted actual image, and outputting the image to obtain an actual target image. The method effectively eliminates image distortion and distortion caused by random fluctuation of the water surface and recovers the distorted image; the problems of large calculation amount and poor real-time performance based on an image matching restoration method are solved; the method can recover the distorted image from the single image under the condition of no other prior conditions, has strong adaptability, can recover the image with high quality in a short time, has better visual effect and higher processing speed compared with the traditional iterative registration method, and is closer to real-time processing.
Description
Technical Field
The invention relates to the technical field of underwater optical imaging, in particular to an image restoration technology based on structured light, which utilizes an active and passive combination method to effectively and quickly restore an image in real time and provides a new thought and scheme for restoring an underwater air imaging image, and specifically relates to an active and passive combination underwater air imaging image restoration method based on structured light.
Background
The underwater air imaging is an important research direction of underwater optics and ocean optics subjects, is an important means and tool for people to know the ocean, develop and utilize the ocean and protect the ocean, and has the advantages of visual detection target, high imaging resolution, high information content and the like. The technology is widely applied to the fields of underwater aerial target reconnaissance/detection/identification, marine ecological research, marine environment monitoring, lifesaving salvage and the like.
In recent years, research on underwater aerial imaging image restoration is mainly divided into two categories:
one is based on a water surface waveform estimation process to compensate and repair the distorted image. The technical scheme adopted by Arete company estimates the water surface waveform by Snell's Law and Fresnel's Formula (Fresnel Formula) under the condition that the sky is assumed to have uniform brightness and no unnecessary ornaments. Marina Alterman et al propose the use of a Shack-Hartmann wavefront sensor to recover the instantaneous wavefront, etc. The method has higher requirement on the environment and depends on the accuracy of modeling;
and secondly, processing the sequence images by using statistics and a blind processing-based method so as to plane out the influence of fluctuating water surface on the images. Efros et al propose a method of selecting the optimal image blocks in a video to obtain an image with minimal geometric distortion. The method selects the clearest image with the minimum distortion of each subregion from the video frame, and then splices all subregions to obtain a result with smaller distortion. Lie et al first use B-spline image registration to remove severe distortion in video images, and then use the lucky-zone fusion algorithm to synthesize less distorted images from the processed image sequence. The method needs to acquire a video stream with a certain length and match each frame, and has high time complexity, large calculation amount and incapability of ensuring real-time performance.
Disclosure of Invention
Aiming at the defects of the existing underwater air imaging algorithm, the invention provides an active and passive combination underwater air imaging image recovery method based on structured light.
The technical scheme adopted by the invention for solving the technical problems is as follows:
an active and passive combined underwater aerial imaging image recovery method based on structured light comprises
Presetting a standard structured light image; obtaining a distorted actual image and a distorted structured light image through three-channel image separation;
carrying out image registration on the distorted structured light image and the standard structured light image to obtain a correction matrix;
and performing secondary image registration by using the correction matrix and the distorted actual image, and outputting the image to obtain an actual target image.
Further, the method comprises the steps of:
step 1), under the background that a standard image cannot be obtained, a standard structured light image a is preset by using structured light, a structured light image projected to a wave surface is a ', a projection of an aerial detection target B on a ' is B ', and an image shot by a camera is a distorted image C, wherein a, a ', B ', and C are all matrixes, and the following relations specifically exist:
A'＝A×H (1)
B'＝B×H (2)
C＝(αA'+βB') (3)
h represents a fluctuating water surface information matrix, and alpha and beta are weight coefficients;
step 2), considering the influence of water surface fluctuation on the image, and carrying out binarization on the standard structured light image AIs A1The structured-light image A' separated in the distorted image C is also binarized into A1", will A1"conversion to A1Approximate geometric space of (2):
S＝A1”×T (4)
S≈A (5)
s is the final registration result image, T represents a transfer matrix, and S is an approximate representation of A according to the definition of image registration;
step 3), image registration is carried out to recover the distorted image, and C of the distorted image is grayed into C1Since A ' and B ' pass through the same fluctuating water surface at the same time, it can be considered that B ' can obtain a result similar to the original image through the transfer matrix T,
R＝C1×T (6)
R≈α1A+β1B (7)
r denotes the final restored image, α1,β1Representing the weight coefficients.
The structured light introduces a known structural image in advance, the content of the known structural image can be regular or irregular, and the structured light is used for acquiring water surface fluctuation information by using an image registration technology.
A warped image C of the fluctuating water surface modulation, the warped image comprising a warped structured-light image and a target image.
In the method, the extracted distorted structured light contains or partially contains deformation information of a distorted target image.
The invention has the advantages that:
(1) by combining structured light and an image registration algorithm, a standard image is preset by using the structured light under the background that the standard image cannot be obtained, and the distorted structured light projected to the interface between water and air is converted into a geometric space of the standard image by using a registration technology, so that image distortion and distortion caused by random fluctuation of the water surface are effectively eliminated, and the distorted image is recovered;
(2) the method adopts an active and passive combined structured light image recovery method, introduces a standard structured light image in advance, and then obtains the water surface fluctuation information by utilizing a registration technology, thereby avoiding the problems of large calculated amount and poor real-time performance based on an image matching recovery method;
(3) the underwater blank imaging recovery algorithm based on the structured light can recover a distorted image from a single image under the condition of no other prior conditions, has strong adaptability, can recover a high-quality image within a short time, has a better visual effect compared with the traditional iterative registration method, has higher processing speed, and is closer to real-time processing.
Drawings
Fig. 1 a-1 f are comparisons between an active and passive combined underwater-to-empty imaging image restoration method based on structured light and an iterative registration method, where fig. 1a is an actual image, fig. 1b is a standard structured light image, fig. 1c is a 6-time iterative registration mean image, fig. 1d is a random frame in a video, fig. 1e is an image distorted as in fig. 1d, and fig. 1f is a restoration result of the method;
FIG. 2 is a flow chart of the image restoration of the active and passive combined underwater space imaging based on the structured light in the embodiment;
fig. 3 a-3 b are diagrams illustrating analysis of a predetermined standard structured light image in an embodiment, where fig. 3a is a projected structured light image and fig. 3b is an extracted actual structured light image;
fig. 4 a-4 f are diagrams of an embodiment of a process for restoring an underwater air imaging image based on active and passive combination of structured light, where fig. 4a is a standard structured light image, fig. 4b is an actual target image, fig. 4c is a captured distorted image, fig. 4d is an extracted distorted structured light image, fig. 4e is a grayed actual captured image, and fig. 4f is a final restored image.
Detailed Description
The invention will be described in detail below with reference to the drawings and embodiments, examples of which are illustrated in the drawings. The embodiments described below with reference to the drawings are illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
Example (b):
as shown in fig. 2, an active-passive combined underwater-empty imaging image restoration method based on structured light realizes restoration of image distortion and distortion caused by a randomly fluctuating water surface by presetting a standard structured light image and a method based on structured light and image registration, and specifically includes the following technologies:
(1) structured light: the binocular ranging usually results in inaccuracy because of few characteristic points, and on the basis, artificial characteristic points are proposed by people, namely, the structural light is obtained, and the structural light can be roughly divided into three types: 1) a point structured light; 2) line structured light; 3) surface structured light, since structured light has a non-contact measurement; the scheme is mature; can be used at night; the precision is higher, etc., it is usually used for three-dimensional scanning or three-dimensional space recovery;
(2) image registration: the invention relates to a method for aligning different images of the same target to a reference image in a space position, which is a main application method in the field of cross-medium imaging distorted image restoration, and in underwater aerial imaging, the method is mainly used for converting the geometric space of a severely geometric distortion image into a geometric space standard image of a low distortion image, and actually, in cross-medium underwater aerial imaging, a standard image cannot be obtained because the standard image is an expected image.
As shown in fig. 2, an active-passive combined underwater-air imaging image restoration method based on structured light presets a standard structured light image, and obtains a distorted actual image and a distorted structured light image through three-channel image separation; then, carrying out image registration on the distorted structured light image and the standard structured light image to obtain a correction matrix; and finally, performing secondary image registration by using the correction matrix and the distorted actual image, and outputting the image to obtain an actual target image.
Specifically, the active and passive combined underwater aerial imaging image recovery method based on structured light comprises the following steps:
step (1), a standard structured light image A is preset, random wave fluctuation of sea waves is simulated in an acrylic water tank, the random wave fluctuation characteristic is considered, if a checkerboard image is projected, as shown in fig. 3a, the result shows that a black and white checkerboard easily causes the problem of detail loss, as shown in fig. 3B, a blue-green stripe check with a better distinguishing effect is selected, corresponding to fig. 4a, the structured light image projected to a wave surface is A ', an aerial detection target B is supposed to correspond to the projection of fig. 4B on A ' to be B ', a distorted image C modulated by the fluctuating water surface is obtained by a camera, an example distorted image is shown in fig. 4C, wherein A, A ', B, B ' and C are all matrixes, and H represents a fluctuating water surface information matrix, and the following relation specifically exists:
A'＝A×H (1)
B'＝B×H (2)
C＝(αA'+βB') (3)
alpha and beta are weight coefficients;
step (2), considering the influence of random sea waves on the image, and binarizing the standard structured light image A into A1The structured-light image a "separated in the distorted image C is also binarized into a"1Is prepared from "1Conversion to A1Approximate geometric space of (2):
S＝A”1×T (4)
S≈A (5)
s is the final registration result image, T represents the transfer matrix, corresponding to FIG. 4d, and the final registration result image S is an approximate representation of the standard structured light image A according to the definition of image registration;
step (3), the distorted image is restored through image registration, and C of the distorted image is grayed into C1Since A 'and B' pass through at the same timeA wave surface, so that it can be considered that B' also obtains a result similar to the original image through the transfer matrix T,
R＝C1×T (6)
R≈α1A+β1B (7)
r denotes the final restored image, α1,β1Representing the weight coefficients.
Following the above steps, FIG. 4f, obtained from the FIG. 4c process, takes 55.195 s. Observing the concentric circular images of the areas marked in the boxes in fig. 4e and 4f, it can be seen that the method can well recover the distorted images of the underwater space.
The feasibility and the effectiveness of the method are further verified, and a test is performed on MATLAB software, wherein FIG. 1a is an actual target image, FIG. 1b is a standard structured light image, the length of a frame sequence used in iterative registration is 61, the pixel of the image is 253 × 293, and registration is performed for 6 times, so that the image recovery result shown in FIG. 1c is obtained. The picture used in the method is a frame randomly extracted from an image sequence as shown in fig. 1d, and a restored image picture 1f is obtained under the same distortion condition as shown in fig. 1 e. In order to more intuitively distinguish the merits of the two methods, the similarity between the processing result and the original image is evaluated by using image Structure Similarity (SSIM), and the higher the SSIM is, the more similar the two images are. The processing speed is evaluated by using the processing time, the shorter the processing time is, the higher the processing speed is, the better the effectiveness is, the following data are obtained on a 64-bit flagship version win7 system, the version of MATLAB software is R2016a, and Table 1 shows the comparison of the iterative registration method and the result of the method.
TABLE 1 comparison of results of the iterative registration method and the present method
As can be seen from table 1, the method is better than the iterative registration method in both recovery effect and time efficiency, and particularly in aging, the method is only 1/220 of the iterative registration method, which greatly shortens the processing time.
The above is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement and the like made within the spirit and principle of the invention shall be included in the protection scope of the invention.
Claims (5)
1. An active and passive combined underwater aerial imaging image recovery method based on structured light is characterized by comprising the following steps
Presetting a standard structured light image; obtaining a distorted actual image and a distorted structured light image through three-channel image separation;
carrying out image registration on the distorted structured light image and the standard structured light image to obtain a correction matrix;
and performing secondary image registration by using the correction matrix and the distorted actual image, and outputting the image to obtain an actual target image.
2. The active and passive combined underwater air imaging image restoration method based on the structured light as claimed in claim 1, comprising the following steps:
step 1), under the background that a standard image cannot be obtained, a standard structured light image A is preset by using structured light, a structured light image projected to a wave surface is A ', a projection of an aerial detection target B on A ' is B ', and a distorted image C modulated by a fluctuating water surface is obtained by using a camera, wherein A, A ', B, B ', C are matrixes, H represents a fluctuating water surface information matrix, and the following relations specifically exist:
A'＝A×H (1)
B'＝B×H (2)
C＝(αA'+βB') (3)
alpha and beta are weight coefficients;
step 2), considering the influence of the water surface fluctuation on the image,binarizing a standard structured light image A into A1The structured-light image a "separated in the distorted image C is also binarized into a ″1A ″', is1Conversion to A1Approximate geometric space of (2):
S＝A″1×T (4)
S≈A (5)
s is the final registration result image, T represents a transfer matrix, and S is an approximate representation of A according to the definition of image registration;
step 3), image registration is carried out to recover the distorted image, and C of the distorted image is grayed into C1Since A ' and B ' pass through the same fluctuating water surface at the same time, B ' passes through the transfer matrix T to obtain a result similar to the original image,
R＝C1×T (6)
R≈α1A+β1B (7)
r denotes the final restored image, α1,β1Representing the weight coefficients.
3. The active-passive combined underwater aerial imaging image restoration method based on structured light as claimed in claim 2, wherein the structured light is a known structured image introduced in advance, the content of the known structured image can be regular or irregular, and the effect of the method is to obtain water surface fluctuation information by using an image registration technology.
4. The method for restoring an image based on active and passive combined underwater air imaging of claim 2, wherein the distorted image modulated by the fluctuating water surface comprises a distorted structured light image and a target image.
5. The method for restoring an image based on active and passive combined underwater air imaging of claim 2, wherein the extracted distorted structured light contains or partially contains deformation information of a distorted target image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010379205.0A CN111524083B (en) | 2020-05-07 | 2020-05-07 | Active-passive combined underwater empty imaging image recovery method based on structured light |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010379205.0A CN111524083B (en) | 2020-05-07 | 2020-05-07 | Active-passive combined underwater empty imaging image recovery method based on structured light |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111524083A true CN111524083A (en) | 2020-08-11 |
| CN111524083B CN111524083B (en) | 2023-05-05 |
Family
ID=71906814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010379205.0A Active CN111524083B (en) | 2020-05-07 | 2020-05-07 | Active-passive combined underwater empty imaging image recovery method based on structured light |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111524083B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160059A (en) * | 2021-04-29 | 2021-07-23 | 五邑大学 | Underwater image splicing method and device and storage medium |
| CN113392597A (en) * | 2021-06-16 | 2021-09-14 | 桂林电子科技大学 | Wave reconstruction method based on Helmholtz-Hodge decomposition |
| CN114022385A (en) * | 2021-11-07 | 2022-02-08 | 桂林电子科技大学 | Image restoration method based on local surface fitting |
| CN117731244A (en) * | 2024-02-19 | 2024-03-22 | 天津医科大学总医院 | Scoliosis risk early warning system based on infrared thermal imaging |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1584896A1 (en) * | 2004-04-06 | 2005-10-12 | Saab Ab | Passive measurement of terrain parameters |
| RU2356060C1 (en) * | 2007-10-19 | 2009-05-20 | ОАО "Концерн "Океанприбор" | Method of measuring hydroacoustic antenna directional characteristic for propagation of multi-beam signal |
| WO2011121167A1 (en) * | 2010-03-31 | 2011-10-06 | Aw-Energy Oy | Wave energy recovery system |
| CN105550981A (en) * | 2015-11-27 | 2016-05-04 | 中山大学 | Image registration and splicing method on the basis of Lucas-Kanade algorithm |
| JP2018028710A (en) * | 2016-08-15 | 2018-02-22 | 日本電信電話株式会社 | Image generator, image generating method, and program |
| CN109639942A (en) * | 2018-12-14 | 2019-04-16 | 中国科学院深圳先进技术研究院 | Underwater imaging system, underwater imaging apparatus and Underwater Imaging method |
| CN109785268A (en) * | 2019-01-23 | 2019-05-21 | 南通蓝岛海洋工程有限公司 | A kind of underwater image restoration method based on double-spectrum analysis optimization algorithm |
| CN109993708A (en) * | 2019-03-05 | 2019-07-09 | 华南理工大学 | A kind of underwater warp image restoration methods being registrated based on dark primary with B-spline |
| CN110231020A (en) * | 2018-03-05 | 2019-09-13 | 深圳先进技术研究院 | Ripple sensor, ripple method for reconstructing and its application |
| CN110595392A (en) * | 2019-09-26 | 2019-12-20 | 桂林电子科技大学 | Cross line structured light binocular vision scanning system and method |
| CN110763152A (en) * | 2019-10-09 | 2020-02-07 | 哈尔滨工程大学 | Underwater active rotation structure light three-dimensional vision measuring device and measuring method |
| CN111076676A (en) * | 2019-12-16 | 2020-04-28 | 广州海洋地质调查局 | Underwater three-dimensional scanner and control method |
| CN111696049A (en) * | 2020-05-07 | 2020-09-22 | 中国海洋大学 | Deep learning-based underwater distorted image reconstruction method |
-
2020
- 2020-05-07 CN CN202010379205.0A patent/CN111524083B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1584896A1 (en) * | 2004-04-06 | 2005-10-12 | Saab Ab | Passive measurement of terrain parameters |
| RU2356060C1 (en) * | 2007-10-19 | 2009-05-20 | ОАО "Концерн "Океанприбор" | Method of measuring hydroacoustic antenna directional characteristic for propagation of multi-beam signal |
| WO2011121167A1 (en) * | 2010-03-31 | 2011-10-06 | Aw-Energy Oy | Wave energy recovery system |
| CN105550981A (en) * | 2015-11-27 | 2016-05-04 | 中山大学 | Image registration and splicing method on the basis of Lucas-Kanade algorithm |
| JP2018028710A (en) * | 2016-08-15 | 2018-02-22 | 日本電信電話株式会社 | Image generator, image generating method, and program |
| CN110231020A (en) * | 2018-03-05 | 2019-09-13 | 深圳先进技术研究院 | Ripple sensor, ripple method for reconstructing and its application |
| CN109639942A (en) * | 2018-12-14 | 2019-04-16 | 中国科学院深圳先进技术研究院 | Underwater imaging system, underwater imaging apparatus and Underwater Imaging method |
| CN109785268A (en) * | 2019-01-23 | 2019-05-21 | 南通蓝岛海洋工程有限公司 | A kind of underwater image restoration method based on double-spectrum analysis optimization algorithm |
| CN109993708A (en) * | 2019-03-05 | 2019-07-09 | 华南理工大学 | A kind of underwater warp image restoration methods being registrated based on dark primary with B-spline |
| CN110595392A (en) * | 2019-09-26 | 2019-12-20 | 桂林电子科技大学 | Cross line structured light binocular vision scanning system and method |
| CN110763152A (en) * | 2019-10-09 | 2020-02-07 | 哈尔滨工程大学 | Underwater active rotation structure light three-dimensional vision measuring device and measuring method |
| CN111076676A (en) * | 2019-12-16 | 2020-04-28 | 广州海洋地质调查局 | Underwater three-dimensional scanner and control method |
| CN111696049A (en) * | 2020-05-07 | 2020-09-22 | 中国海洋大学 | Deep learning-based underwater distorted image reconstruction method |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113160059A (en) * | 2021-04-29 | 2021-07-23 | 五邑大学 | Underwater image splicing method and device and storage medium |
| CN113160059B (en) * | 2021-04-29 | 2022-04-08 | 五邑大学 | Underwater image splicing method and device and storage medium |
| CN113392597A (en) * | 2021-06-16 | 2021-09-14 | 桂林电子科技大学 | Wave reconstruction method based on Helmholtz-Hodge decomposition |
| CN113392597B (en) * | 2021-06-16 | 2022-10-28 | 桂林电子科技大学 | Wave reconstruction method based on Helmholtz-Hodge decomposition |
| CN114022385A (en) * | 2021-11-07 | 2022-02-08 | 桂林电子科技大学 | Image restoration method based on local surface fitting |
| CN114022385B (en) * | 2021-11-07 | 2024-03-26 | 桂林电子科技大学 | Image restoration method based on local surface fitting |
| CN117731244A (en) * | 2024-02-19 | 2024-03-22 | 天津医科大学总医院 | Scoliosis risk early warning system based on infrared thermal imaging |
| CN117731244B (en) * | 2024-02-19 | 2024-05-10 | 天津医科大学总医院 | Scoliosis risk early warning system based on infrared thermal imaging |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111524083B (en) | 2023-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111524083B (en) | Active-passive combined underwater empty imaging image recovery method based on structured light | |
| CN107704844B (en) | Power transmission line icing thickness identification method based on binocular parallax images of unmanned aerial vehicle | |
| CN109993804A (en) | A kind of road scene defogging method generating confrontation network based on condition | |
| CN106056594A (en) | Double-spectrum-based visible light image extraction system and method | |
| CN113887349A (en) | Road area image identification method based on image and point cloud fusion network | |
| CN103903237A (en) | Dual-frequency identification sonar image sequence splicing method | |
| CN111709888B (en) | Aerial image defogging method based on improved generation countermeasure network | |
| CN115034982A (en) | Underwater image enhancement method based on multi-scale attention mechanism fusion | |
| CN104281999A (en) | Single image defogging method based on structural information | |
| Tragulnuch et al. | High voltage transmission tower detection and tracking in aerial video sequence using object-based image classification | |
| CN110634165A (en) | Light field image de-scattering method based on RGB three-channel information fusion | |
| CN110827375B (en) | Infrared image true color coloring method and system based on low-light-level image | |
| CN113763261B (en) | Real-time detection method for far small target under sea fog weather condition | |
| CN115937021A (en) | Polarization defogging method based on frequency domain feature separation and iterative optimization of atmospheric light | |
| CN116433573A (en) | Airplane surface ice detection method, reconstruction system and equipment for light field speckle imaging | |
| CN112950481B (en) | Water bloom shielding image data collection method based on image mosaic network | |
| CN115546716A (en) | Binocular vision-based method for positioning fire source around power transmission line | |
| CN114663299A (en) | Training method and device suitable for image defogging model of underground coal mine | |
| Yahya et al. | Robust recognition of targets for underwater docking of autonomous underwater vehicle | |
| CN109214243A (en) | Method for tracking target, device and unmanned plane | |
| CN107948540B (en) | Road monitoring camera and method for shooting road monitoring image | |
| CN113505622A (en) | Test system and method for automatically identifying multiple bar codes and LED lamps | |
| CN112507965A (en) | Target identification method and system of electronic lookout system | |
| Tragulnuch et al. | High voltage transmission tower identification in an aerial video sequence using object-based image classification with geometry information | |
| CN116596805B (en) | Polarization defogging method based on polarization state difference of scene object and atmosphere light |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |