CN111325696B - Underwater sound image reverberation suppression method based on normal distribution interval estimation - Google Patents
Underwater sound image reverberation suppression method based on normal distribution interval estimation Download PDFInfo
- Publication number
- CN111325696B CN111325696B CN202010139790.7A CN202010139790A CN111325696B CN 111325696 B CN111325696 B CN 111325696B CN 202010139790 A CN202010139790 A CN 202010139790A CN 111325696 B CN111325696 B CN 111325696B
- Authority
- CN
- China
- Prior art keywords
- image
- normal distribution
- target
- target image
- pixel points
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 29
- 230000001629 suppression Effects 0.000 title claims description 13
- 238000003384 imaging method Methods 0.000 claims abstract description 19
- 238000001914 filtration Methods 0.000 claims description 7
- 238000004458 analytical method Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 abstract description 4
- 230000000007 visual effect Effects 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 5
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 238000012800 visualization Methods 0.000 description 3
- 238000006073 displacement reaction Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G06T5/70—
-
- G06T5/90—
-
- 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
Abstract
The invention relates to a method for suppressing reverberation of an underwater sound image based on normal distribution interval estimation, which is characterized in that all pixel points contained in an original image obtained by high-frequency imaging sonar detection are classified according to minimum distance to be regarded as random variables approximately meeting normal distribution (or unilateral normal distribution), the intrinsic pixel points of a target form a generalized center, a significance level is set, standard deviation (mean square error) is solved, interference bright spots caused by reverberation in the original image can be remarkably filtered by using the normal distribution interval estimation method, the problem of more interference in the target discrimination process is solved, and the visual level of the underwater sound image is improved.
Description
Technical Field
The invention belongs to the field of sonar, and particularly relates to an underwater sound image reverberation suppression method based on normal distribution interval estimation.
Background
The phased array three-dimensional acoustic imaging sonar (the working frequency is 300 kHz) is used as a three-dimensional high-frequency imaging sonar, is a real-time image sonar for displaying underwater target detection results in the form of underwater acoustic images, and has the working characteristics that: high working frequency, short acting distance, more interference factors in water and large image distortion. Therefore, in the phased array three-dimensional acoustic imaging sonar test and application process, volume reverberation formed by scattering of sound waves by tiny plankton and tiny air bubbles in water and interfacial reverberation caused by longitudinal and transverse shaking of a carrier appear as a large number of discrete and random image bright spots on a formed underwater sound image, so that the following two problems are caused:
(1) The image bright spots formed by the reverberation additionally increase the real-time processing workload of the image of the UI software, and the conventional image noise reduction method (such as median filtering, weighted smoothing filtering and the like) has poor processing effect, so that the performance of the high-frequency imaging sonar is affected to a certain extent;
(2) The image bright spots formed by the reverberation form a plurality of interferences to the target discrimination, and the probability of misdiscrimination and false alarm is obviously improved.
Therefore, in the process of processing the underwater acoustic image, effective filtering must be carried out on the bright spots of the reverberation images, so that the practical application efficiency of the high-frequency imaging sonar is improved.
Disclosure of Invention
The invention aims to solve the problem of interference of high-frequency imaging sonar in the aspect of judging targets under the condition of reverberation in the prior art, and provides a method for suppressing the reverberation of an underwater sound image based on normal distribution interval estimation.
The specific technical scheme adopted by the invention is as follows:
a method for suppressing reverberation of an underwater sound image based on normal distribution interval estimation comprises the following steps:
s1: performing image connected domain analysis algorithm analysis on an original image of the high-frequency imaging sonar to determine the number n of targets in the original image and an intrinsic pixel point set A corresponding to each target image i ，i＝1,2,...,n；
S2: based on the intrinsic pixels corresponding to each target imagePoint set A i Solving generalized center e of each target image i ，i＝1,2,...,n；
S3: for all non-target image intrinsic pixel points in the original image, calculating generalized centers e of n target images respectively for each pixel point i And dividing the distance into the intrinsic pixel point sets of the target images corresponding to the generalized centers closest to the target images, so that each target image obtains an expanded pixel point set A 'thereof' i Completing the classification of the intrinsic pixel points of the non-target image;
s4: for each set of extended pixel points A' i Calculating the generalized center e of each pixel point in the collection to the target image i And construct set D with the distance as element i ；
S5: for each set D i Confidence interval estimation is carried out on the elements in the pixel point set according to normal distribution, and an expanded pixel point set A 'is removed' i Sample pixel points with the distance from the middle to the generalized center outside the confidence interval are removed to obtain an expanded pixel point set which is taken as a final intrinsic pixel point set of the corresponding target image, and filtering of the reverberation bright points of the underwater sound image based on normal distribution interval estimation is completed.
Preferably, the generalized center form is a mathematical expression ax+by+cz=1 of the three-dimensional space where the target image is located, and the coefficients of the mathematical expression are solved by using a least square method, so as to obtain the target image a i Is defined by the generalized center e of i Generalized center e i A least squares estimate representing a mathematical expression describing sample pixel points of the target image.
Preferably, the non-target image intrinsic pixel point is
Representing the original image except for the set of all target images +.>
The other pixel points.
Preferably, the set D i Approximately satisfies normal distribution or unilateral normal distribution.
Preferably, in S5, the method is directed to set D i All elements in (1) calculate the standard deviation sigma thereof i And set the significance level alpha i Obtaining a confidence level of 1-alpha i Confidence interval of (C) then from A' i Removing pixel points corresponding to elements falling outside the confidence interval to obtain a new subset
As the final set of intrinsic pixel points for the corresponding target image.
Further, the final intrinsic pixel points of all target images are integrated
All elements in the image are drawn on a display interface to serve as a target underwater sound image for reverberation suppression.
Compared with the prior art, the invention has the following beneficial effects:
according to the invention, all pixel points contained in an original image obtained by high-frequency imaging sonar detection are classified according to the minimum distance to complete the classification of the extended pixel points of the target image, and then the extended pixel points are regarded as random variables which approximately meet normal distribution (or unilateral normal distribution), the intrinsic pixel points of the target form a generalized center, the significance level is set, the standard deviation is solved, the normal distribution interval estimation method is used, the interference bright points caused by reverberation in the original image can be remarkably filtered, the problem of more interference in the target judging process is solved, and the visualization level of the underwater sound image is improved.
Drawings
Fig. 1 is a raw display image obtained by detecting the sea floor with a phased array three-dimensional acoustic camera sonar.
FIG. 2 is a submarine target image processed by the underwater sound image reverberation suppression method according to the present invention with the significance level set to 0.5.
FIG. 3 is a submarine target image processed according to the underwater sound image reverberation suppression method of the present invention with the significance level set to 0.32.
Detailed Description
The invention is further illustrated and described below with reference to the drawings and detailed description. The technical features of the embodiments of the invention can be combined correspondingly on the premise of no mutual conflict.
In the test and application process of the phased array three-dimensional acoustic imaging sonar, the phased array three-dimensional acoustic imaging sonar is influenced by the influence of tiny plankton, tiny bubbles in water, uneven structures of the water body and the like on reverberation formed by scattering of incident sound waves, sonar performance is influenced to a certain extent, and large deviation is caused for target discrimination. The influence of reverberation on the performance of the phased array three-dimensional acoustic shooting sonar is that the interference in a target image is obviously increased, and the performance form is that a large number of discrete, random, tiny and unfixed bright spots appear near the target image.
The inventive concept of the present invention is as follows: firstly, determining the number of targets in an original underwater sound image obtained by high-frequency imaging sonar and intrinsic pixel points of each target image, solving the generalized center of each target image, and completing the classification of the intrinsic pixel points of non-target images to obtain an extended pixel point set of each target image; aiming at each target image extension pixel point set, a set formed by the displacement from each sample pixel point to the generalized center of the target image is established, confidence interval estimation is carried out according to normal distribution, sample pixel points, in the extension pixel point set, of which the displacement to the generalized center is outside the confidence interval are removed, and filtering of the reverberation bright points of the underwater sound image based on the normal distribution interval estimation is completed; the method solves the problem of judging the target by the high-frequency imaging sonar under the reverberation condition, and improves the image visualization level of the high-frequency imaging sonar.
According to the above, the effective suppression of the interference image bright spots caused by reverberation in the original image of the high-frequency imaging sonar can be realized according to the following specific steps:
(1) Analyzing the original image of the high-frequency imaging sonar by using an image connected domain analysis algorithm to determine the number n of targets in the original image, wherein each target image is composed of a series of intrinsic pixel points, so that the corresponding target image can be obtained by the connected domain analysisIntrinsic pixel Point set A i (i=1, 2,., n), wherein a i Representing the set of intrinsic pixel points corresponding to the ith target image.
(2) Based on the corresponding intrinsic pixel point set A of each target image i Solving generalized center e of each target image i Wherein e is i Represents the generalized center of the i-th target image, i=1, 2,..n.
In the invention, the generalized center of the target image is defined as a plane expression of the three-dimensional space where the target image is located, and the plane expression is in the form of: ax+by+cz=1, based on the set of intrinsic pixel points a corresponding to each target image i The coefficients a, b and c of the mathematical expression can be solved by using a least square method to obtain the generalized center e of the ith target image i I=1, 2,..n. Generalized center e i I.e., a least squares estimate of the mathematical expression describing the sample pixel point in the ith target image.
In the step (1), all the target images in the original image are obtained through connected domain analysis and are recorded as a target image set
Whereas the original image is not included in the target image set +.>
The remaining pixels of the non-target image are marked as intrinsic pixels +.>
In this part of the non-target image, there may also be intrinsic pixels that should be classified into the target image, so that these pixels need to be identified and categorized.
(3) Intrinsic pixel points for all non-target images in the original image
Each pixel point in the image is calculated to n target image generalized sense respectivelyCenter e i (i=1, 2,., n) and binning the pixel points into corresponding sets of target image eigen-pixel points on a minimum distance principle. Taking the pixel point j as an example, the distances from the pixel point j to the 1 st, 2 nd and 3 … … n target image generalized centers can be calculated to be l respectively 1 、l 2 、l 3 、……、l n Provided that the smallest of the n distances is l 2 Then the pixel j is divided into the set of intrinsic pixel points A of the 2 nd target image 2 Is a kind of medium. According to the method ∈>
Each pixel point in the target image is respectively drawn into an intrinsic pixel point set of the target image corresponding to the nearest generalized center to obtain an expanded pixel point set A 'of the target image' i . When the point is->
After each pixel point in the target image is divided, an expanded pixel point set A 'of each target image is obtained' i (i=1, 2,., n) satisfying +.>
Thus completing the classification of the non-target intrinsic pixel points.
(4) For each set of extended pixel points A' i (i=1, 2., (i.), n), calculate A' i Each pixel point in (2) to the generalized center e of the target image i The distance L is used as an aggregate element to form a probability distribution aggregate D of discrete random variables which approximately meet normal distribution (or single-side normal distribution) i (i＝1,2,...,n)。
(5) For each set D i Calculating standard deviation (mean square error) sigma of all elements in the set i (σ i Gtoreq.0) for each D i Setting a significance level alpha i The confidence level of 1-alpha can be found from the standard normal distribution probability density function integral value table i Upper boundary value u of the sample of (2) i ＝Φ -1 (1-α i /2)(u i Not less than 0) to obtain D i Corresponding arrangementSignal level is 1-alpha i Is T i ＝[e i -u i σ i ,e i +u i σ i ]。
(6) For each set D i Each element in the list is respectively judged whether it falls in the confidence interval T i In the confidence interval, the pixel points beyond the confidence interval can be regarded as interference pixel points, and the pixels falling in the confidence interval T are removed i The pixels corresponding to the other elements, i.e. the set of culling the expanded pixels A' i Middle to generalized center e i The distance of (2) falls within the confidence interval T i Other sample pixel points. Thus, in the expanded pixel point set A 'of the target image' i On the basis of the elements (sample pixel points) in (i=1, 2,., n), a new subset is constructed by culling part of the pixels that are most likely to be reverberation bright points of the underwater sound image
Make->
Each sample pixel point in (a) is connected with the generalized center e of the target image i The shifts of (a) all fall within the confidence interval T i And (3) filtering the reverberation bright spots of the target underwater sound image based on normal distribution interval estimation.
(7) The final set of intrinsic pixel points of all target images is recorded as
The set represents all target images after reverberation suppression. Will->
All elements (sample pixel points) in the image are drawn on a display interface, namely the target underwater sound image for reverberation suppression.
In order to enable those skilled in the art to better understand the present invention, the above-described method is applied to a specific embodiment to show technical effects thereof.
As shown in fig. 1, the original display image obtained by the detection of the phased array three-dimensional acoustic imaging sonar in this embodiment has n=1 submarine target images, but obviously has more interference bright spots outside the target images, and needs to be reverberated.
For the original display image, reverberation suppression is performed through the steps (1) to (7), and two different significance levels alpha are set in the process i (0.5 and 0.32) controlling the pixel points of the original image to fall within the confidence interval of the corresponding target image through image analysis and processing. At alpha i In the case of =0.5, the target underwater sound image after reverberation suppression is obtained as shown in fig. 2, at α i In the case of=0.32, a reverberation-suppressed target underwater sound image is obtained as shown in fig. 3.
Comparing the image processing effect of the submarine target, the underwater sound image reverberation suppression method based on normal distribution interval estimation can obviously filter discrete and random reverberation bright spots in the original image, improve the application efficiency of imaging sonar and improve the visualization level of the target image.
The above embodiment is only a preferred embodiment of the present invention, but it is not intended to limit the present invention. Various changes and modifications may be made by one of ordinary skill in the pertinent art without departing from the spirit and scope of the present invention. Therefore, all the technical schemes obtained by adopting the equivalent substitution or equivalent transformation are within the protection scope of the invention.
Claims (4)
1. The method for suppressing the reverberation of the underwater sound image based on normal distribution interval estimation is characterized by comprising the following steps of:
s1: performing image connected domain analysis algorithm analysis on an original image of the high-frequency imaging sonar to determine the number n of targets in the original image and an intrinsic pixel point set A corresponding to each target image i ，i＝1,2,...,n；
S2: based on the corresponding intrinsic pixel point set A of each target image i Solving generalized center e of each target image i ，i＝1,2,...,n；
S3: for all non-target image intrinsic pixel points in the original image, calculating generalized centers e of n target images respectively for each pixel point i And dividing the distance into the intrinsic pixel point sets of the target images corresponding to the generalized centers closest to the target images, so that each target image obtains an expanded pixel point set A i ' the classification of the intrinsic pixel points of the non-target image is completed;
s4: for each set of extended pixel points A i ' calculate each pixel point in the collection to the generalized center e of the target image i And construct set D with the distance as element i ；
S5: for each set D i Confidence interval estimation is carried out on the elements in the pixel point set A according to normal distribution, and the expanded pixel point set A is removed i Sample pixel points with the distance from the middle to the generalized center outside the confidence interval are removed to obtain an expanded pixel point set which is taken as a final intrinsic pixel point set of a corresponding target image, and filtering of the reverberation bright points of the underwater sound image based on normal distribution interval estimation is completed; the set D i Approximately meeting normal distribution or unilateral normal distribution;
the generalized center form is a mathematical expression ax+by+cz=1 of a three-dimensional space where the target image is located, and coefficients of the mathematical expression are solved by using a least square method, and the generalized center e i A least squares estimate representing a mathematical expression describing sample pixel points of the target image.
2. The method for suppressing reverberation of an underwater sound image based on normal distribution interval estimation according to claim 1, wherein the intrinsic pixel points of the non-target image are
Representing the original image except for the set of all target images +.>
The other pixel points.
3. The method for suppressing reverberation of an underwater sound image based on normal distribution interval estimation according to claim 1, wherein in S5, for the set D i All elements in (1) calculate the standard deviation sigma thereof i And set the significance level alpha i Obtaining a confidence level of 1-alpha i Confidence interval of (a), then from a i 'eliminating pixel points corresponding to elements falling outside the confidence interval from the confidence interval' to obtain a new subset
As the final set of intrinsic pixel points for the corresponding target image.
4. A method of suppressing reverberation in an underwater sound image based on normal distribution interval estimation according to claim 3, wherein the final intrinsic pixel points of all the target images are integrated
All elements in the image are drawn on a display interface to serve as a target underwater sound image for reverberation suppression.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139790.7A CN111325696B (en) | 2020-03-03 | 2020-03-03 | Underwater sound image reverberation suppression method based on normal distribution interval estimation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010139790.7A CN111325696B (en) | 2020-03-03 | 2020-03-03 | Underwater sound image reverberation suppression method based on normal distribution interval estimation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111325696A CN111325696A (en) | 2020-06-23 |
| CN111325696B true CN111325696B (en) | 2023-07-07 |
Family
ID=71167269
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010139790.7A Active CN111325696B (en) | 2020-03-03 | 2020-03-03 | Underwater sound image reverberation suppression method based on normal distribution interval estimation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111325696B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114462458B (en) * | 2022-04-11 | 2022-07-08 | 自然资源部第一海洋研究所 | Ship underwater signal noise reduction and target enhancement method |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930273A (en) * | 2012-10-15 | 2013-02-13 | 西安电子科技大学 | Auroral oval segmenting method based on brightness self-adaptive level set |
| CN103714542A (en) * | 2013-12-25 | 2014-04-09 | 中国人民解放军海军工程大学 | Extraction method for target highlight in low-resolution high-frequency sonar image |
| CN104880703A (en) * | 2014-02-27 | 2015-09-02 | 中国科学院声学研究所 | Side-scan sonar target detection reverberation suppressing technologies |
| CN105741284A (en) * | 2016-01-28 | 2016-07-06 | 中国船舶重工集团公司第七一〇研究所 | Multi-beam forward-looking sonar target detection method |
| CN110852959A (en) * | 2019-10-14 | 2020-02-28 | 江苏帝一集团有限公司 | Sonar image filtering method based on novel median filtering algorithm |
| CN111462729A (en) * | 2020-03-31 | 2020-07-28 | 因诺微科技(天津)有限公司 | Fast language identification method based on phoneme log-likelihood ratio and sparse representation |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR102047965B1 (en) * | 2011-09-26 | 2019-11-25 | 온타리오 파워제너레이션 인코퍼레이티드 | Ultrasound matrix inspection |
| US9087385B2 (en) * | 2012-11-12 | 2015-07-21 | FMV Innovations, LLC. | Method for improving images captured underwater |
| EP3440627A4 (en) * | 2016-04-07 | 2019-12-04 | Carmel Haifa University Economic Corporation Ltd. | Image dehazing and restoration |
| US10367976B2 (en) * | 2017-09-21 | 2019-07-30 | The United States Of America As Represented By The Secretary Of The Navy | Single image haze removal |
-
2020
- 2020-03-03 CN CN202010139790.7A patent/CN111325696B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930273A (en) * | 2012-10-15 | 2013-02-13 | 西安电子科技大学 | Auroral oval segmenting method based on brightness self-adaptive level set |
| CN103714542A (en) * | 2013-12-25 | 2014-04-09 | 中国人民解放军海军工程大学 | Extraction method for target highlight in low-resolution high-frequency sonar image |
| CN104880703A (en) * | 2014-02-27 | 2015-09-02 | 中国科学院声学研究所 | Side-scan sonar target detection reverberation suppressing technologies |
| CN105741284A (en) * | 2016-01-28 | 2016-07-06 | 中国船舶重工集团公司第七一〇研究所 | Multi-beam forward-looking sonar target detection method |
| CN110852959A (en) * | 2019-10-14 | 2020-02-28 | 江苏帝一集团有限公司 | Sonar image filtering method based on novel median filtering algorithm |
| CN111462729A (en) * | 2020-03-31 | 2020-07-28 | 因诺微科技(天津)有限公司 | Fast language identification method based on phoneme log-likelihood ratio and sparse representation |
Non-Patent Citations (4)
| Title |
|---|
| Kay L Gemba, et.al.Source characterization using recordings made in a reverberant underwater channel.《Applide acoustics》.2016,第105卷第24-34页. * |
| Melita A. Samoilys, et.al.Determining methods of underwater visual census for estimating the abundance of coral reef fishes.《Environmental Biology of Fishes》.2000,第57卷(第3期),第289-304页. * |
| 宋泽林.基于时频域滤波的亮点特征提取及识别研究.《中国优秀硕士学位论文全文数据库 (工程科技Ⅱ辑)》.2019,(第8期),第C036-87页. * |
| 王志杰等.水下目标声图像特征分析与二次处理.《现代电子技术》.2007,(第16期),第118-121页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111325696A (en) | 2020-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102306377B (en) | Method and device for reducing noise in ultrasound image | |
| CN102663708B (en) | Ultrasonic image processing method based on directional weighted median filter | |
| CN116703910B (en) | Intelligent detection method for quality of concrete prefabricated bottom plate | |
| CN106651813B (en) | A kind of non-local mean denoising method of more fragments compositings | |
| CN109100788B (en) | Seismic data non-local mean de-noising method | |
| CN111325696B (en) | Underwater sound image reverberation suppression method based on normal distribution interval estimation | |
| CN110675410A (en) | Side-scan sonar sunken ship target unsupervised detection method based on selective search algorithm | |
| CN105741284B (en) | A kind of multi-beam Forward-looking Sonar object detection method | |
| CN116188488B (en) | Gray gradient-based B-ultrasonic image focus region segmentation method and device | |
| CN111505651B (en) | Feature extraction method for potential moving object of active sonar echo map | |
| Shuchun et al. | Preprocessing for stereo vision based on LOG filter | |
| CN110599422A (en) | Weighted average salt and pepper noise reduction algorithm based on edge protection | |
| CN116612112B (en) | Visual inspection method for surface defects of bucket | |
| CN111062954B (en) | Infrared image segmentation method, device and equipment based on difference information statistics | |
| CN114926377B (en) | Modeling method of side-scan sonar gain compensation judgment model | |
| CN102867292B (en) | Stepped mean filtering method aimed at imaging data of multibeam forward-looking sonars | |
| JP4644145B2 (en) | Ultrasonic diagnostic equipment | |
| Li et al. | Object representation for multi-beam sonar image using local higher-order statistics | |
| CN109427042B (en) | Method for extracting layered structure and spatial distribution of local sea area sedimentary layer | |
| CN110728692A (en) | Image edge detection method based on Scharr operator improvement | |
| CN106780407B (en) | Denoising system and denoising method for ultrasonic image speckle noise | |
| Li et al. | Ultrasound speckle reduction based on image segmentation and diffused region growing | |
| CN112070765B (en) | Cloth detection method based on double-sided filtering combined improvement OTSU | |
| TWI736446B (en) | Seabed edge detection method capable of filtering horizontal noise | |
| CN116524281A (en) | K-means clustering-based moss attaching underwater planar structure sonar image classification method |
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 |