CN114627367A - Sea bottom line detection method for side-scan sonar image - Google Patents
Sea bottom line detection method for side-scan sonar image Download PDFInfo
- Publication number
- CN114627367A CN114627367A CN202210531542.6A CN202210531542A CN114627367A CN 114627367 A CN114627367 A CN 114627367A CN 202210531542 A CN202210531542 A CN 202210531542A CN 114627367 A CN114627367 A CN 114627367A
- Authority
- CN
- China
- Prior art keywords
- image
- line
- scan sonar
- sea bottom
- obtaining
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
Abstract
The invention relates to the technical field of side-scan sonar image analysis, in particular to a submarine line detection method of a side-scan sonar image, which analyzes by using a mode of combining K-Means and average peak detection and comprises the following steps: s1, obtaining the image amplitude of the original side-scan sonar image; s2, performing K-means clustering on the original image; s3, obtaining a boundary line; s4, obtaining an average gray scale statistical curve; s5, obtaining the average pixel position of the sea bottom line; s6, extracting the sea bottom line; and S7, drawing a seabed line. The invention can detect the submarine line of the side-scan sonar image containing the target object, accurately display the submarine line and avoid the defect that the traditional maximum amplitude method or maximum gradient method cannot accurately display.
Description
Technical Field
The invention relates to the technical field of side-scan sonar image analysis, in particular to a sea bottom line detection method for a side-scan sonar image.
Background
The characteristic target information in the side-scan sonar image has important application value in the aspects of ocean scientific research (such as seabed sediment distribution and deep-sea hydrothermal solution forming mechanism), ocean engineering (such as submarine pipeline site selection, submarine landform acquisition and sunken ship discovery), ocean military and the like. The sea bottom line in the side-scan sonar waterfall layout represents the distance from the towed fish to the sea bottom, is the boundary line between a water drop area and a substrate area, and is also an important parameter for target measurement, slant distance correction and image gray level equalization. The high-quality side-scan sonar image which can efficiently and accurately track the submarine line has very important significance for national defense activities such as underwater torpedo detection, enemy underwater investigation equipment identification and the like. At present, side-scan Sonar processing software (such as Triton, Sonar Web, Discovery and the like) at home and abroad adopts a traditional maximum amplitude method or a maximum gradient method as a semi-automatic undersea line tracking method. However, because the reflection intensity of the target object is generally higher compared with the seabed reflection of the natural substrate, and the target area generally contains the shadow, the two aspects affect the target area, so that the seabed line tracking accuracy of the traditional maximum amplitude method or the maximum gradient method in the target area is lower, and the effective tracking of the seabed line in the target area by the traditional maximum amplitude method or the maximum gradient method is difficult to realize effectively.
Disclosure of Invention
The invention aims to solve the defects in the prior art and provides a sea bottom line detection method for a side-scan sonar image.
In order to achieve the purpose, the invention adopts the following technical scheme:
a submarine line detection method of a side-scan sonar image utilizes a mode of combining K-Means and average peak detection to carry out analysis, and comprises the following steps:
s1, obtaining the image amplitude of the side scan sonar original image: reading an original image of a side scan sonar containing a target object to obtain an overall image frame containing pixel points, and expressing the overall image frame by m rows and n columns;
s2, performing K-means clustering on the original images: selecting a K value of 2, dividing pixel points of an original image into a water column region and a substrate region, and classifying to obtain a clustering image;
s3, obtaining boundary line: carrying out binarization processing on the clustered image to obtain a binarized image comprising a plurality of boundary lines;
s4, obtaining an average gray scale statistical curve: carrying out gray level analysis on the original image, and calculating the average gray level value of each column of the original image to obtain an average gray level statistical curve;
s5, obtaining the average pixel position of the sea bottom line: carrying out maximum amplitude detection on the average gray scale statistical curve obtained in S4 to obtain the average pixel where the sea bottom line is locatedPosition ofRepresented by pn;
S6, extracting the sea bottom line: the method for extracting the sea bottom line from the binarized image obtained in S3 comprises the following steps:
s6.1, from the first line of the binary imagepnAs a center, selectingdFor searching for distances, in [ QUOTE ]In the search interval of (2), the image point in the first line is extracted and QUOTE is used Represents;
s6.2, QUOTE from the second line of the binarized image As a center, selectingdFor searching for distances, in [ QUOTE ]In the search interval of (2), image points in the second line are extracted using QUOTE Represents;
s6.3, repeating the steps until the extraction of the image points of all the rows of the binary image is finished;
all image points finally extracted by S6 constitute the scanning seafloor line;
s7, drawing a sea bottom line: the scanned sea-bottom line obtained in S6 is drawn onto the original image to obtain a final sea-bottom line.
Preferably, in S6, if the search space exceeds the map width, the part of the search space exceeding the map width is removed.
The invention has the beneficial effects that:
1. the submarine line detection method can be used for carrying out submarine line detection on the side-scan sonar image containing the target object, and precisely detecting the submarine line.
2. The water column region and the substrate region are rapidly divided through the clustering image and the binarization image, so that the position of the sea bottom line is conveniently analyzed.
3. The submarine line interval is positioned through the average pixel position, and the submarine line detection efficiency is improved.
Drawings
FIG. 1 is an overall step diagram of the method for detecting sea bottom lines of side-scan sonar images according to the present invention;
FIG. 2 is an original image of a first side scan sonar;
FIG. 3 is the sea-bottom line tracking result of the original image maximum amplitude method of the first side-scan sonar;
FIG. 4 is a clustered image of a first side scan sonar;
FIG. 5 is a binarized image of a first side scan sonar;
FIG. 6 is a statistical plot of the mean gray scale of a first side-scan sonar;
FIG. 7 is a scanned sea bottom line obtained after the search of the first side-scan sonar binarized image;
FIG. 8 is a first raw image with the final seafloor line;
FIG. 9 is an original image of a second side scan sonar;
FIG. 10 is the sea bottom line tracking result of the maximum amplitude method of the original image of the second side scan sonar;
FIG. 11 is a clustered image of a second side scan sonar;
FIG. 12 is a binarized image of a second side scan sonar;
FIG. 13 is a statistical plot of the average gray scale of the second side scan sonar;
FIG. 14 is the scanned sea bottom line obtained after the search of the binarized image of the second side scan sonar;
FIG. 15 is a second original image with the final seafloor line plotted.
In the figure, 1, water column region; 2. a substrate region; 3. a target object; 4. averaging pixel positions; 5. scanning the sea bottom line; 6. and finally, the sea bottom line.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments.
Referring to fig. 1, a submarine line detection method for a side-scan sonar image uses a combination of K-Means and average peak detection for analysis, where K-Means is also called K-Means clustering algorithm (K-Means clustering algorithm), which is an iterative solution clustering analysis algorithm. The seabed line detection method integrally comprises the following steps:
s1, obtaining the image amplitude of the original image of the side-scan sonar: and reading an original image of the side scan sonar containing the target object 3, and obtaining an overall picture containing pixel points. The image contains all pixel points of the original image, and is processed by QUOTE And (4) showing.
S2, performing K-means clustering on the original images: and selecting a K value of 2, wholly dividing the pixel points of the original image into a water column region 1 and a substrate region 2, and classifying to obtain a clustering image. The K value of 2 is set to divide the original image into two parts, the divided water column region 1 contains the target 3, and the junction between the water column region 1 and the substrate region 2 contains the sea bottom line.
S3, obtaining boundary line: and carrying out binarization processing on the clustered image to obtain a binarized image comprising a plurality of boundary lines, wherein the boundary lines of the binarized image are prominent.
S4, obtaining an average gray scale statistical curve: and carrying out gray level analysis (counting according to the direction vertical to the flight path) on the original image, and calculating the average gray level of each column of the original image to obtain an average gray level statistical curve.
S5, obtaining the average pixel position 4 of the sea bottom line: carrying out maximum amplitude detection on the average gray scale statistical curve obtained in S4 to obtain the average pixel position 4 of the sea bottom linepnTo indicate. The maximum amplitude detection is to find the maximum amplitude point in the average gray scale statistical curve and to set the pixel position corresponding to the maximum amplitude point as the average pixel position 4.
S6, extracting the sea bottom line: the method for extracting the sea bottom line from the binarized image obtained in S3 comprises the following steps:
s6.1, from the first line of the binary imagepnAs the center, select d as the search distance in [ QUOTE ]In the search interval of (2), the image point in the first line is extracted and QUOTE is used This image point is a point of a white portion in the binarized image;
s6.2, QUOTE from the second line of the binarized image As the center, select d as the search distance in [ QUOTE ]In the search interval of (2), image points in the second line are extracted, using QUOTE This image point is also a point of a white portion in the binarized image;
and S6.3, repeating the steps until the extraction of the image points of all the rows of the binary image is completed, so that a section of white contour line can be obtained, and the section of contour line finally extracted through S6 is the scanning seabed line 5.
It should be noted that the above-mentioned search distance d has a value in the range of QUOTE If the value is too small, the searching range is too small, and the image point can not be easily searched; the value is too large, the search range is too large, and the pixel points of the undersea line are not unique.
It should be noted that, when the search region exceeds the image frame, the portion of the search region exceeding the image frame needs to be removed, so as to ensure that the search range does not exceed the binary image.
S7, drawing a sea bottom line: the scanned seabed line 5 obtained in S6 is drawn onto the original image to obtain the final seabed line 6.
Example one
Figure 2 is an original image of a first side scan sonar including a water column region 1 and a substrate region 2.
FIG. 3 is the result of the line tracing directly by the maximum amplitude method, and it can be seen that there is no precise delineation of the line. The detection of the sea bottom line is performed by the method of the present invention.
First, the image frame of the first original image is read, and the image frame size is obtained as 265 rows × 275 columns (i.e., m =265, n = 275).
Referring to fig. 4, after that, clustering is performed by K-means, and K =2 is taken, a cluster image is obtained, and it can be seen that the cluster image entirely includes two parts.
Referring to fig. 5, the cluster image is binarized to obtain a binarized image, and a plurality of boundary lines are visible, but these boundary lines include the sea bottom line and the boundary of the target 3, and therefore, it is necessary to perform search and screening.
Referring to fig. 6, gray statistics are performed on the first original image, and an average gray value of each column of the original image is calculated, so that an average gray statistics curve of the first original image can be obtained. The maximum amplitude detection of the average gray scale statistic curve can result in 193 as the average pixel position 4 where the sea bottom line is located, that ispn=193。
Referring to fig. 7, a first line of an image is binarizedpn(i.e., 193) as the center, and a distance of 0.05n (i.e., 14), i.e., at [179,207 ]]Is searched for in the interval of (2) to obtain the image point QUOTE of the first line . Order Quote In the second row [183,214]Is searched for in the interval of (2) to obtain the image point QUOTE of the second line And repeating the steps until all the rows are searched, and extracting the scanning seabed line 5.
Referring to fig. 8, the scanned sub-sea line 5 is rendered onto the original image to obtain the final sub-sea line 6.
Example two
Figure 9 is a second side scan sonar raw image, including water column region 1 and substrate region 2.
FIG. 10 is the result of the seafloor line tracking directly by the maximum amplitude method, and it can be seen that the seafloor line profile is not accurately delineated. The detection of the sea bottom line is performed by the method of the present invention.
First, the image frame of the second original image is read, and the image frame size is 623 rows × 675 columns (i.e., m =623, n = 675).
Referring to fig. 11, after that, clustering is performed by K-means, and K =2 is taken to obtain a clustered image, and it can be seen that the clustered image includes two parts as a whole.
Referring to fig. 12, the cluster image is binarized to obtain a binarized image, and a plurality of boundary lines are visible, but these boundary lines include the sea bottom line and the boundary of the target 3, and therefore, it is necessary to perform search and screening.
Referring to fig. 13, the average gray scale statistical curve of the first original image may be obtained by performing gray scale statistics on the second original image and calculating the average gray scale value of each column of the original image. Maximum vibration is carried out on the average gray level statistical curveThe average pixel position 4 (of the sea bottom line) can be obtained by amplitude detectionpn=670)。
Referring to fig. 14, a first line of an image is binarized topn(i.e., 670) as the center, and a distance of 0.08n (i.e., 54), i.e., at [616,724 ]]The search is carried out in the interval of (2), but because the maximum image frame of the original image only reaches 675, the exceeding part is removed, and the search interval of the first line is finally determined as [616,675 ]]Obtaining the image point QUOTE of the first line . Order Quote In the second row [582,690]But because the maximum frame of the original image only reaches 675, the excess part is removed, and the search interval of the second row is finally determined as [585,675 ]]Obtaining the image point QUOTE of the second line And repeating the steps until all the rows are searched, and extracting the scanning seabed line 5.
Referring to fig. 15, the scanned sub-sea line 5 is rendered onto the original image to obtain the final sub-sea line 6.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention should be equivalent or changed within the scope of the present invention.
Claims (3)
1. A submarine line detection method of side scan sonar images is characterized in that: the analysis was performed using a combination of K-Means and mean peak detection, which included the following steps:
s1, obtaining the image amplitude of the side scan sonar original image: reading an original image of a side scan sonar containing a target object (3) to obtain an overall picture containing pixel points, and expressing the overall picture by m rows and n columns;
s2, performing K-means clustering on the original images: selecting a K value of 2, dividing pixel points of an original image into a water column region (1) and a substrate region (2), and classifying to obtain a clustering image;
s3, obtaining boundary line: carrying out binarization processing on the clustered image to obtain a binarized image comprising a plurality of boundary lines;
s4, obtaining an average gray scale statistical curve: carrying out gray level analysis on the original image, calculating the average gray level of each column of the original image, and obtaining an average gray level statistical curve;
s5, obtaining the average pixel position of the sea bottom line (4): maximum amplitude detection is carried out on the average gray scale statistical curve obtained in S4 to obtain the average pixel position (4) of the sea bottom lineWith pnRepresents;
s6, extracting the sea bottom line: the method for extracting the sea bottom line from the binarized image obtained in S3 comprises the following steps:
s6.1, from the first line of the binary imagepnAs a center, selectingdFor searching for distances, in [ QUOTE ]In the search interval of (2), the image point in the first line is extracted and QUOTE is used Represents;
s6.2, QUOTE from the second line of the binarized image As a center, selectingdFor searching for distances, in [ QUOTE ]In the search interval of (2), image points in the second line are extracted, using QUOTE Represents;
s6.3, repeating the steps until the extraction of the image points of all the rows of the binary image is finished;
all image points finally extracted by S6 constitute the scanning seafloor line (5);
s7, drawing a seabed line: the scanned sea bottom line (5) obtained in S6 is rendered onto the original image to obtain the final sea bottom line (6).
3. The sea line detection method of the side-scan sonar image according to claim 2, comprising: in S6, if the search interval exceeds the map width, the part of the search interval exceeding the map width is removed.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210531542.6A CN114627367B (en) | 2022-05-17 | 2022-05-17 | Sea bottom line detection method for side-scan sonar image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210531542.6A CN114627367B (en) | 2022-05-17 | 2022-05-17 | Sea bottom line detection method for side-scan sonar image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114627367A true CN114627367A (en) | 2022-06-14 |
CN114627367B CN114627367B (en) | 2022-07-26 |
Family
ID=81907001
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210531542.6A Active CN114627367B (en) | 2022-05-17 | 2022-05-17 | Sea bottom line detection method for side-scan sonar image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114627367B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116930976A (en) * | 2023-06-19 | 2023-10-24 | 自然资源部第一海洋研究所 | Submarine line detection method of side-scan sonar image based on wavelet mode maximum value |
CN117554966A (en) * | 2024-01-12 | 2024-02-13 | 哈船通航(三亚)技术服务合伙企业(有限合伙) | Sonar data intelligent processing method for accurate positioning of whole water area |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
RU2012144838A (en) * | 2012-10-22 | 2014-04-27 | Открытое акционерное общество "Государственный научно-исследовательский навигационно-гидрографический институт" (ОАО "ГНИНГИ") | METHOD FOR DETERMINING DEPTHS AT REAL TIME WHEN EXAMINING THE BOTTOM RELIEF WITH A SIDE-REVIEW HYDROLOCATOR |
CN107167810A (en) * | 2017-05-02 | 2017-09-15 | 河海大学常州校区 | A kind of submarine target rapid extracting method of side-scan sonar imaging |
CN108872997A (en) * | 2018-05-10 | 2018-11-23 | 国家海洋局第二海洋研究所 | A kind of seabed line detecting method based on side scan sonar data fusion and accurate processing |
CN110675410A (en) * | 2019-09-25 | 2020-01-10 | 江苏海洋大学 | Side-scan sonar sunken ship target unsupervised detection method based on selective search algorithm |
CN110703261A (en) * | 2019-09-09 | 2020-01-17 | 江泽林 | Side-scan sonar bottom tracking method based on multi-peak scoring system |
CN111368633A (en) * | 2020-01-18 | 2020-07-03 | 中国海洋大学 | AUV-based side-scan sonar image identification method |
CN111443344A (en) * | 2020-04-07 | 2020-07-24 | 中国人民解放军军事科学院国防科技创新研究院 | Automatic extraction method and device for side-scan sonar sea bottom line |
CN111476809A (en) * | 2020-04-08 | 2020-07-31 | 北京石油化工学院 | Side-scan sonar image target identification method |
CN112882037A (en) * | 2021-04-28 | 2021-06-01 | 北京星天科技有限公司 | Side-scan sonar sea bottom line detection method and device |
CN113378932A (en) * | 2021-06-11 | 2021-09-10 | 中交第三航务工程局有限公司 | Side-scan sonar position correction method based on high-precision heterogeneous common-view image |
CN113466839A (en) * | 2021-09-03 | 2021-10-01 | 北京星天科技有限公司 | Side-scan sonar sea bottom line detection method and device |
-
2022
- 2022-05-17 CN CN202210531542.6A patent/CN114627367B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
RU2012144838A (en) * | 2012-10-22 | 2014-04-27 | Открытое акционерное общество "Государственный научно-исследовательский навигационно-гидрографический институт" (ОАО "ГНИНГИ") | METHOD FOR DETERMINING DEPTHS AT REAL TIME WHEN EXAMINING THE BOTTOM RELIEF WITH A SIDE-REVIEW HYDROLOCATOR |
CN107167810A (en) * | 2017-05-02 | 2017-09-15 | 河海大学常州校区 | A kind of submarine target rapid extracting method of side-scan sonar imaging |
CN108872997A (en) * | 2018-05-10 | 2018-11-23 | 国家海洋局第二海洋研究所 | A kind of seabed line detecting method based on side scan sonar data fusion and accurate processing |
CN110703261A (en) * | 2019-09-09 | 2020-01-17 | 江泽林 | Side-scan sonar bottom tracking method based on multi-peak scoring system |
CN110675410A (en) * | 2019-09-25 | 2020-01-10 | 江苏海洋大学 | Side-scan sonar sunken ship target unsupervised detection method based on selective search algorithm |
CN111368633A (en) * | 2020-01-18 | 2020-07-03 | 中国海洋大学 | AUV-based side-scan sonar image identification method |
CN111443344A (en) * | 2020-04-07 | 2020-07-24 | 中国人民解放军军事科学院国防科技创新研究院 | Automatic extraction method and device for side-scan sonar sea bottom line |
CN111476809A (en) * | 2020-04-08 | 2020-07-31 | 北京石油化工学院 | Side-scan sonar image target identification method |
CN112882037A (en) * | 2021-04-28 | 2021-06-01 | 北京星天科技有限公司 | Side-scan sonar sea bottom line detection method and device |
CN113378932A (en) * | 2021-06-11 | 2021-09-10 | 中交第三航务工程局有限公司 | Side-scan sonar position correction method based on high-precision heterogeneous common-view image |
CN113466839A (en) * | 2021-09-03 | 2021-10-01 | 北京星天科技有限公司 | Side-scan sonar sea bottom line detection method and device |
Non-Patent Citations (6)
Title |
---|
MUSTAFA UMIT GUMUSAY 等: "A review of seagrass detection, mapping and monitoring applications using acoustic systems", 《EUROPEAN JOURNAL OF REMOTE SENSING》 * |
库安邦 等: "一种联合单波束测深的侧扫声呐海底线提取方法", 《海洋通报》 * |
王涛 等: "基于K-means聚类与数学形态学的侧扫声呐图像目标轮廓自动提取方法", 《海洋科学》 * |
王涛 等: "基于侧扫声呐图像纹理特征的海底底质分类研究", 《声学技术》 * |
赵建虎 等: "侧扫声呐图像海底线自动提取方法研究", 《武汉大学学报 信息科学版》 * |
赵玉新 等: "海底声呐图像智能底质分类技术研究综述", 《智能系统学报》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116930976A (en) * | 2023-06-19 | 2023-10-24 | 自然资源部第一海洋研究所 | Submarine line detection method of side-scan sonar image based on wavelet mode maximum value |
CN116930976B (en) * | 2023-06-19 | 2024-03-26 | 自然资源部第一海洋研究所 | Submarine line detection method of side-scan sonar image based on wavelet mode maximum value |
CN117554966A (en) * | 2024-01-12 | 2024-02-13 | 哈船通航(三亚)技术服务合伙企业(有限合伙) | Sonar data intelligent processing method for accurate positioning of whole water area |
CN117554966B (en) * | 2024-01-12 | 2024-03-19 | 哈船通航(三亚)技术服务合伙企业(有限合伙) | Sonar data intelligent processing method for accurate positioning of whole water area |
Also Published As
Publication number | Publication date |
---|---|
CN114627367B (en) | 2022-07-26 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114627367B (en) | Sea bottom line detection method for side-scan sonar image | |
CN108444447B (en) | Real-time autonomous detection method for fishing net in underwater obstacle avoidance system | |
CN111028154B (en) | Side-scan sonar image matching and stitching method for rugged seafloor | |
CN101915910B (en) | Method and system for identifying marine oil spill object by marine radar | |
CN107492094A (en) | A kind of unmanned plane visible detection method of high voltage line insulator | |
CN110378921B (en) | Intelligent identification method for substrate layer boundary of channel based on floating mud rheological property and gray level co-occurrence matrix | |
CN104992172B (en) | Port remote sensing image shore ship detection method based on coastal outburst and different area scanning | |
CN111753577A (en) | Apple identification and positioning method in automatic picking robot | |
CN107909002B (en) | Sea-land segmentation method of infrared remote sensing image based on coastline matching | |
CN111008664B (en) | Hyperspectral sea ice detection method based on space-spectrum combined characteristics | |
CN106530313A (en) | Sea-sky line real-time detection method based on region segmentation | |
CN109359533A (en) | A kind of tidal saltmarsh method based on multiband remote sensing image | |
CN116433672B (en) | Silicon wafer surface quality detection method based on image processing | |
CN113344953B (en) | Machine vision tidal bore flow velocity measurement method based on unmanned aerial vehicle | |
CN115797813B (en) | Water environment pollution detection method based on aerial image | |
CN111967337A (en) | Pipeline line change detection method based on deep learning and unmanned aerial vehicle images | |
CN107169412B (en) | Remote sensing image harbor-berthing ship detection method based on mixed model decision | |
CN114821358A (en) | Optical remote sensing image marine ship target extraction and identification method | |
CN114693524A (en) | Side-scan sonar image accurate matching and fast splicing method, equipment and storage medium | |
CN107967452B (en) | Video-based deep sea mineral distribution identification method and system | |
Hu et al. | A sample enhancement method based on simple linear iterative clustering superpixel segmentation applied to multibeam seabed classification | |
CN114743059B (en) | Automatic classification method for submarine geographic entities by integrating topographic features | |
CN115436966A (en) | Batch extraction method for laser radar reference water depth control points | |
CN109471106B (en) | SAR ocean internal wave stripe recognition method combining clustering analysis and boundary tracking method | |
CN112164079A (en) | Sonar image segmentation 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 |