CN109471106A - In conjunction with the SAR internal wave of ocean fringe counting method method of clustering and frontier tracing method - Google Patents
In conjunction with the SAR internal wave of ocean fringe counting method method of clustering and frontier tracing method Download PDFInfo
- Publication number
- CN109471106A CN109471106A CN201811398861.4A CN201811398861A CN109471106A CN 109471106 A CN109471106 A CN 109471106A CN 201811398861 A CN201811398861 A CN 201811398861A CN 109471106 A CN109471106 A CN 109471106A
- Authority
- CN
- China
- Prior art keywords
- image
- ocean
- sar
- wave
- fringe
- 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 71
- 238000001914 filtration Methods 0.000 claims description 7
- 238000005516 engineering process Methods 0.000 claims description 6
- 238000003064 k means clustering Methods 0.000 claims description 6
- 238000009394 selective breeding Methods 0.000 claims description 3
- 238000012544 monitoring process Methods 0.000 abstract description 2
- 238000012545 processing Methods 0.000 description 11
- 238000001514 detection method Methods 0.000 description 7
- 239000011159 matrix material Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 230000001427 coherent effect Effects 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000937378 Everettia interior Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000002265 prevention Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 239000013535 sea water Substances 0.000 description 1
- 238000010187 selection method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
- G01S13/9021—SAR image post-processing techniques
- G01S13/9027—Pattern recognition for feature extraction
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S13/00—Systems using the reflection or reradiation of radio waves, e.g. radar systems; Analogous systems using reflection or reradiation of waves whose nature or wavelength is irrelevant or unspecified
- G01S13/88—Radar or analogous systems specially adapted for specific applications
- G01S13/89—Radar or analogous systems specially adapted for specific applications for mapping or imaging
- G01S13/90—Radar or analogous systems specially adapted for specific applications for mapping or imaging using synthetic aperture techniques, e.g. synthetic aperture radar [SAR] techniques
Landscapes
- Engineering & Computer Science (AREA)
- Remote Sensing (AREA)
- Radar, Positioning & Navigation (AREA)
- Physics & Mathematics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention relates to a kind of SAR internal wave of ocean fringe counting method methods of combination clustering and frontier tracing method, first, pretreatment is filtered to the interior wave SAR initial data obtained from European Space Agency website or other platforms, obtains the gray value of the identification each pixel of image scene；Secondly, filtered image is carried out K-mean clustering, and the gray value of image is replaced according to classification；Then frontier tracing is carried out to new gray level image, draws out the profile of wave striped in significantly.Method of the invention can recognize that the obvious fringe area of interior wave point, to provide technical support for undersea safety monitoring, provide service to carry out undersea trouble free service.
Description
Technical field
The invention belongs to internal wave of ocean scientific domains, more precisely, are to belong to interior wave detection technology field, provide one kind
In conjunction with the SAR internal wave of ocean fringe counting method method of K-means clustering and frontier tracing method.
Background technique
Internal wave of ocean is one of disaster of world today's property, has sudden strong, and destructive power is strong, the huge spy of energy
Point.It hides in water, often makes people's prevention too late, therefore has the title of " underwater devil ".Internal wave of ocean often will cause great peace
Full accident, if there is the underwater navigations object such as submarine or torpedo unfortunately to encounter internal wave of ocean, they are just difficult to manipulate or even be pressed into
Fragment.Therefore, EARLY RECOGNITION is carried out to internal wave of ocean, is the important component of internal wave of ocean detection, be ocean navigation safety
The modern management of work provides basic guarantee.
Currently, the ERS, Radarsat of countries and regions such as European Space Agency, Canada, German space office and Italy,
Envisat, TerraSAR-X and COSMO-Skymed etc. be spaceborne and carried SAR sensor to obtain each sea area in the world largely extra large
Wave remote sensing images in ocean provide data abundant for internal wave of ocean research.Mainly according to internal wave of ocean to the tune of extra large surface wave
Making mechanism carries out a wide range of remotely sensed image using electromagnetic wave imaging mechanism.Further utilize SAR (Synthetic Aperture
Radar) remote sensing images can directly acquire the horizontal directions parameter informations such as spatial position and wavelength, the wave direction of interior wave.It can be with
In conjunction with the internals wave of ocean such as the velocity of wave of wave, depth of pycnocline, density of sea water difference and Internal wave amplitude in the acquisition such as field observation, historical summary
Vertical parameter.Therefore, SAR has unique application value and development potentiality in terms of internal wave of ocean remote sensing research, can be with
People are greatly enriched to the understanding of internal wave of ocean.
Interior wave identification is that internal wave of ocean detects vital component part, and the most common interior wave recognition methods is edge inspection
Survey method is split processing to image, and this method in accuracy although have certain guarantee, generally existing processing data
Amount is big, not fast enough the feature of speed.Another common method is sea SAR image power spectrum feature extraction, to the two of image
Dimension power spectrum does one-dimensional transform, after normalized, the normalized power spectrum signature of various oceanographic phenomenas is obtained, through finite sample
The feature of interior wave is obtained after statistics, analysis.This method is needed according to sample statistics, and accuracy and adaptability are not good enough.Additionally
There is the interior wave characteristic detection based on àtrous wavelet, is changed according to interior wave characteristics of image in conjunction with the ability of wavelet multi scale edge detecting
Be wave multi-scale morphology in àtrous wavelet carries out into binary wavelet, in conjunction with image procossing method it is extractable in wave side
Edge feature.But the detection response of different scale is not identical, will lead to edge redundancy, noise is not also inhibited, increases
The process of subsequent processing.
Existing internal wave of ocean detection technique causes processing difficulty big since the data of SAR image are complicated, data volume is big,
Accuracy is difficult to hold；On the other hand, due to the objective factor of coherent speckle noise, edge detection difficulty is big, follow-up processing flow
Complexity adds somewhat to detection difficulty and accuracy.
Summary of the invention
The present invention provides the SAR internal wave of ocean fringe counting method side of a kind of combination K-means clustering and frontier tracing method
Method, using satellites such as the earth observation satellite series Envisat satellite of European Space Agency and sentry's No.1s, with remote sensing technology, meter
Calculation machine image processing techniques identifies the internal wave of ocean in SAR image.
In order to achieve the above object, the technical solution of the present invention is to provide a kind of combination K-means clustering and boundaries
The SAR internal wave of ocean fringe counting method method of tracing, it includes following procedure:
Satellite remote sensing date image is obtained, internal wave SAR initial data is filtered pretreatment, obtains identification image scene
The gray value of each pixel after the filtering；
K-mean clustering is carried out to filtered image, and replaces the gray value of image according to classification, is had
The cluster image of new gray value；
Frontier tracing is carried out to cluster image, draws out the profile of most apparent interior wave striped.
Optionally, it chooses Lee and filters the filtering carried out to image, reduce interference of the noise to SAR image, and obtain image
In each pixel gray value.
Optionally, when carrying out clustering using K-means algorithm, classification number k takes 3；According to the bright fringe of internal wave of ocean,
The characteristic information of dark fringe and background colour, characteristics of image is divided into three classes；According to the affiliated cluster of original gray value, to image weight
It is new to assign gray value, to increase the contrast of image.
Optionally, to, by the three classes cluster sample obtained after final iteration, successively being replaced in each clustering cluster in clustering
The element that all values are 0,130,255, respectively corresponds dark fringe, background colour, bright fringe, the gray value of three category features is separated.
Optionally, when carrying out frontier tracing to cluster image, based on selected threshold value, cluster image is converted into binary map
The coordinates of multiple starting points is arranged as after, as the starting point of frontier tracing, carry out eight neighborhood frontier tracing or four neighborhood boundaries with
Track draws out track path.
Optionally, when cluster image being changed into bianry image, bright fringe is made to be shown as 1, other are 0.
Optionally, pass through maximum variance between clusters or artificial selection method or histogram technology method or iterative method, Lai Xuanding
Threshold value needed for cluster image is converted to bianry image.
Optionally, when frontier tracing, multiple starting points are selected to be tracked by routine nesting circulation, and choose curve most
Long value is 60000~100000 as restrictive condition, the value range of greatest length.
In order to realize the preliminary identification to internal wave of ocean, a kind of combination K-means clustering provided by the invention and side
The SAR internal wave of ocean fringe counting method method of boundary's tracing, at the satellite remote sensing dates image such as European Space Agency Envisat
Reason, first pre-processes initial data, obtains the gray value of each pixel of identification image scene after the filtering；Secondly,
Filtered image is subjected to K-mean clustering, and replaces the gray value of image according to classification；Then to new grayscale image
As carrying out frontier tracing, the profile of most apparent interior wave striped is drawn out.The method can recognize that interior wave point compared with
Apparent fringe area provides service to provide technical support for undersea safety monitoring to carry out undersea trouble free service.
Detailed description of the invention
Fig. 1 is the flow chart in conjunction with frontier tracing to synthetic aperture radar internal wave of ocean fringe counting method algorithm；
Fig. 2 is the untreated SAR striograph of the embodiment of the present invention；
Fig. 3 is internal wave of ocean SAR image filter preprocessing result figure of the embodiment of the present invention；
Fig. 4 is internal wave of ocean SAR image clustering processing result figure of the embodiment of the present invention；
Fig. 5 is internal wave of ocean SAR image frontier tracing method recognition result figure of the embodiment of the present invention.
Specific embodiment
As shown in Figure 1, providing a kind of combination K- the present invention is based on the internal wave of ocean detection technique of synthetic aperture radar image-forming
The recognition methods of means clustering and frontier tracing method, to identify the obvious fringe area of interior wave point.
1, initial data pre-processes
Due to the coherent imaging mechanism inherent characteristic of synthetic aperture radar, so that SAR image generates coherent speckle noise, therefore will
The gray value square of each pixel in image scene is obtained after passing through filtering from European Space Agency Envisat satellite remote sensing date image
Battle array.Filtering method is filtered using the Lee of 3 × 3 windows.
2, the K-mean clustering based on filtered image
Clustering refers to technique study and processing with mathematics, is carried out according to the similitude of data characteristics to given object
Classification.The main thought of K-means cluster is to cluster discrete many data points using k mass center, and similitude is larger
Data point be classified as one kind, be to carry out the final optimal solution that converges to using the mass center ownership and centroid position of constantly updating data point.
Algorithm detailed process includes assigning initial cluster center, data point being belonged to by distance, updates cluster centre, until repeatedly
It withholds and holds back.When carrying out clustering using K-means algorithm, classification number k need to give in advance, according to internal wave of ocean in the present invention
The characteristic information of bright, dark fringe and background colour, therefore a width SAR image can be divided into three classes by characteristics of image, i.e., k takes 3.And it will most
Three classes cluster sample after the completion of whole iteration, successively replacing in each clustering cluster all values is 0,130,255, respectively correspond dark fringe,
Background colour, bright fringe.According to the intensity value ranges 0~255 of eight chromatic graphs, the advantages of replacement in this way is to greatest extent by three classes spy
The gray value of sign demarcates, and increases the contrast of image.
The element of the first kind is all become into a kind of value after filtered image is clustered, the second class all becomes another
One kind value, third class is similarly.The matrix being made of new element is obtained in this way as cluster image.
More particularly, in this example, image file is read, matrix data is obtained.
3 initial cluster center values, such as 40,200,400 are given, the first kind, the second class, third class are denoted as.Successively calculate
All data return the data in the smallest class to the distance (Euclidean space distance) of these three initial values in matrix.
After the completion of classification, the respective average value of three classes data is calculated, as 3 new cluster centre values, is calculated again former
Beginning data to new central value distance, and by apart from minimum principle sort out, until close iteration twice cluster centre value, variation
Difference stops iteration less than 0.1.
By the good data of iteration, change.Total data i.e. in the first kind becomes 0, and the second class becomes 130, third
Class is 255.Data result is saved as into image (cluster image).
After handling by clustering, the contrast of image can be made to increase.This is because after clustering, we according to
The affiliated cluster of original gray value imparts gray value to image again, after the gray value of image changes, gray value it
Between difference also become larger, this allow for image contrast increase.
3, based on the frontier tracing processing of cluster image
Since frontier tracing method is that the element that search for certain column be 0 needs to cluster first therefore before carrying out frontier tracing
Image afterwards is changed into bianry image, that is, allows bright fringe to be shown as 1, other are 0.And grayscale image is when being changed into bianry image,
Appropriate threshold is found using maximum variance between clusters, for threshold value the above are 1, image is become binary map accordingly the following are 0 by threshold value
Picture.Furthermore the selection method of optimal threshold further includes artificial selection, histogram technology and iterative method.Due to maximum variance between clusters
To be derived on the basis of histogram technology method by principle of least square method, have the characteristics that it is simple, fireballing, therefore
It uses in this example.
For frontier tracing method, the present invention is using eight neighborhood frontier tracing, and in addition there are four neighborhood frontier tracings.Its
Middle neighborhood refers to that element nearest around any point in matrix, four neighborhoods, eight neighborhood refer to from all directions.P (x, y) is set up an office as image
In a boundary point, then the next boundary point of point must be in its eight neighborhood.Frontier tracing method around this principle, is looked for first
To a boundary point positioned at the object boundary area upper left corner as search starting point, according to counterclockwise or clockwise direction, certainly
It is upper and under, from left to right, search for its eight neighborhood, find next boundary point, then continued searching using this boundary point as current point, directly
To returning to search starting point or meeting maximum curve length value, do not continue to search for.The completion of frontier tracing, it is necessary first to determine
The initial position of eight neighborhood search each time, that is, determine that eight neighbouring pictures are examined successively since which pixel of eight neighborhood
Element could quickly and effectively find out next boundary point.
Therefore originate starting point selection it is particularly important, choose difference will lead to it is different as a result, and often choose do not conform to
The suitable result that cannot be wanted.Therefore the present invention selects multiple starting points to track by routine nesting circulation, and chooses curve
Greatest length is constantly debugged as restrictive condition, and taking greatest length is 60000~100000.
A specific embodiment of the invention presented below:
The internal wave of ocean that this example occurs for 14:11 afternoon on the 15th of August in 2006 or so, center longitude are as follows: 21 ° 11 '
N, 116 ° of 45 ' E (20 ° of 40 ' 47 ' N of N~21 °, 116 ° of 10 ' 10 ' E of E~117 °), has chosen European Space Agency's Envisat satellite data,
Study of recognition is carried out to synthetic aperture radar internal wave of ocean striped algorithm in conjunction with K-means clustering and frontier tracing hair.
Satellite remote sensing experimental data is operated according to flow chart shown in FIG. 1, the specific steps are as follows:
(1) original remotely-sensed data is filtered by the Lee of 3 × 3 windows of building, is filtered pretreatment.
(2) filtered image is obtained to (1) step and cluster image is obtained by K-mean clustering.
(3) the cluster image obtained to (2) step finds a suitable threshold of image using maximum variance between clusters
Value is bianry image greyscale image transitions.Then the coordinate for arranging multiple starting points on the image, as rising for frontier tracing
Point, optional four or eight directions on tracking direction, the present invention select eight directions, setting number seeds N (60000~
100000) frontier tracing, is then carried out, track path is drawn out.
Processing result using Envisat satellite data based on algorithm of the invention is as Figure 2-Figure 5, Fig. 2 be without
The internal wave of ocean SAR image of processing, Fig. 3 are internal wave of ocean SAR image filter preprocessings as a result, Fig. 4 is internal wave of ocean SAR image
Filter preprocessing is as a result, Fig. 5 is internal wave of ocean SAR image frontier tracing method recognition result, in the i.e. interior wave in the grey path in Fig. 5
Stripe information.
It is discussed in detail although the contents of the present invention have passed through above preferred embodiment, but it should be appreciated that above-mentioned
Description is not considered as limitation of the present invention.After those skilled in the art have read above content, for of the invention
A variety of modifications and substitutions all will be apparent.Therefore, protection scope of the present invention should be limited to the appended claims.
Claims (8)
1. a kind of SAR internal wave of ocean fringe counting method method of combination K-means clustering and frontier tracing method, feature exist
In, include following procedure:
Satellite remote sensing date image is obtained, internal wave SAR initial data is filtered pretreatment, obtains identification image scene and is filtering
The gray value of each pixel after wave；
K-mean clustering is carried out to filtered image, and replaces the gray value of image according to classification, obtains having newly
The cluster image of gray value；
Frontier tracing is carried out to cluster image, draws out the profile of wave striped in apparent.
2. SAR internal wave of ocean fringe counting method method as described in claim 1, which is characterized in that
It chooses Lee filtering to be filtered SAR image, to eliminate the interference of noise, and obtains each pixel of SAR image
Gray value.
3. SAR internal wave of ocean fringe counting method method as described in claim 1, which is characterized in that
When carrying out clustering using K-means algorithm, classification number k takes 3；According to the bright fringe, dark fringe and back of internal wave of ocean
The characteristic information of scenery, characteristics of image is divided into three classes；According to the affiliated cluster of original gray value, gray scale is assigned again to image
Value, so that the contrast of image increases.
4. SAR internal wave of ocean fringe counting method method as claimed in claim 3, which is characterized in that
To all values by the three classes cluster sample obtained after final iteration, are successively replaced in each clustering cluster in clustering is 0,
130,255 element respectively corresponds dark fringe, background colour, bright fringe, and the gray value of three category features is separated.
5. SAR internal wave of ocean fringe counting method method as described in claim 3 or 4, which is characterized in that
When carrying out frontier tracing to cluster image, based on selected threshold value, arrangement is more after cluster image is converted to bianry image
The coordinate of a starting point carries out eight neighborhood frontier tracing or four neighborhood frontier tracings as the starting point of frontier tracing, draw out with
Track path.
6. SAR internal wave of ocean fringe counting method method as claimed in claim 5, which is characterized in that
When cluster image is changed into bianry image, bright fringe is set to be shown as 1, other are 0.
7. SAR internal wave of ocean fringe counting method method as claimed in claim 5, which is characterized in that
By maximum variance between clusters or artificial selection method or histogram technology method or iterative method, image will be clustered to select
Threshold value needed for being converted to bianry image.
8. SAR internal wave of ocean fringe counting method method as claimed in claim 5, which is characterized in that
When frontier tracing, multiple starting points are selected to be tracked by routine nesting circulation, and choose curve greatest length as limit
Condition processed, the value range of greatest length are 60000~100000.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811398861.4A CN109471106B (en) | 2018-11-22 | 2018-11-22 | SAR ocean internal wave stripe recognition method combining clustering analysis and boundary tracking method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811398861.4A CN109471106B (en) | 2018-11-22 | 2018-11-22 | SAR ocean internal wave stripe recognition method combining clustering analysis and boundary tracking method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109471106A true CN109471106A (en) | 2019-03-15 |
| CN109471106B CN109471106B (en) | 2021-04-13 |
Family
ID=65672992
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811398861.4A Expired - Fee Related CN109471106B (en) | 2018-11-22 | 2018-11-22 | SAR ocean internal wave stripe recognition method combining clustering analysis and boundary tracking method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109471106B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113031013A (en) * | 2021-03-03 | 2021-06-25 | 北京航空航天大学 | Satellite-borne GNSS-R sea ice boundary detection method and system |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2746538A1 (en) * | 1996-03-21 | 1997-09-26 | Framatome Sa | Detecting obstacles hooked under PWR upper reactor internals |
| CN101710422A (en) * | 2009-12-11 | 2010-05-19 | 西安电子科技大学 | Image segmentation method based on overall manifold prototype clustering algorithm and watershed algorithm |
| CN101833762A (en) * | 2010-04-20 | 2010-09-15 | 南京航空航天大学 | Different-source image matching method based on thick edges among objects and fit |
| WO2011080944A1 (en) * | 2009-12-28 | 2011-07-07 | 株式会社パスコ | Rice crop status tracking system, rice crop status tracking method, rice crop status tracking program |
| CN102722883A (en) * | 2012-04-16 | 2012-10-10 | 上海交通大学 | Polarized SAR (synthetic aperture radar) image segmentation method with space adaptivity |
| CN103714148A (en) * | 2013-12-24 | 2014-04-09 | 西安电子科技大学 | SAR image search method based on sparse coding classification |
| CN104008552A (en) * | 2014-06-16 | 2014-08-27 | 南京大学 | Time sequence SAR image cultivated land extraction method based on dynamic time warp |
| CN104182754A (en) * | 2014-08-19 | 2014-12-03 | 山东临沂烟草有限公司 | Rural resident point information extraction method based on high-resolution remote-sensing image |
| CN104239900A (en) * | 2014-09-11 | 2014-12-24 | 西安电子科技大学 | Polarized SAR image classification method based on K mean value and depth SVM |
| CN104751147A (en) * | 2015-04-16 | 2015-07-01 | 成都汇智远景科技有限公司 | Image recognition method |
| CN104766095A (en) * | 2015-04-16 | 2015-07-08 | 成都汇智远景科技有限公司 | Mobile terminal image identification method |
-
2018
- 2018-11-22 CN CN201811398861.4A patent/CN109471106B/en not_active Expired - Fee Related
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2746538A1 (en) * | 1996-03-21 | 1997-09-26 | Framatome Sa | Detecting obstacles hooked under PWR upper reactor internals |
| CN101710422A (en) * | 2009-12-11 | 2010-05-19 | 西安电子科技大学 | Image segmentation method based on overall manifold prototype clustering algorithm and watershed algorithm |
| WO2011080944A1 (en) * | 2009-12-28 | 2011-07-07 | 株式会社パスコ | Rice crop status tracking system, rice crop status tracking method, rice crop status tracking program |
| CN101833762A (en) * | 2010-04-20 | 2010-09-15 | 南京航空航天大学 | Different-source image matching method based on thick edges among objects and fit |
| CN102722883A (en) * | 2012-04-16 | 2012-10-10 | 上海交通大学 | Polarized SAR (synthetic aperture radar) image segmentation method with space adaptivity |
| CN103714148A (en) * | 2013-12-24 | 2014-04-09 | 西安电子科技大学 | SAR image search method based on sparse coding classification |
| CN104008552A (en) * | 2014-06-16 | 2014-08-27 | 南京大学 | Time sequence SAR image cultivated land extraction method based on dynamic time warp |
| CN104182754A (en) * | 2014-08-19 | 2014-12-03 | 山东临沂烟草有限公司 | Rural resident point information extraction method based on high-resolution remote-sensing image |
| CN104239900A (en) * | 2014-09-11 | 2014-12-24 | 西安电子科技大学 | Polarized SAR image classification method based on K mean value and depth SVM |
| CN104751147A (en) * | 2015-04-16 | 2015-07-01 | 成都汇智远景科技有限公司 | Image recognition method |
| CN104766095A (en) * | 2015-04-16 | 2015-07-08 | 成都汇智远景科技有限公司 | Mobile terminal image identification method |
Non-Patent Citations (4)
| Title |
|---|
| TAO RONGHUA ET AL.: "GLCM and Fuzzy Clustering for Ocean Features Classification", 《2010 INTERNATIONAL CONFERENCE ON MACHINE VISION AND HUMAN-MACHINE INTERFACE》 * |
| 吴国良 杨浩: "基于曲线的图像边界跟踪", 《电工理论与新技术学术年会》 * |
| 范开国 等: "《合成孔径雷达海洋内波遥感探测技术与应用》", 28 February 2017 * |
| 陈捷 等: "SAR 图像海洋内波参数自动提取方法", 《海洋技术学报》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113031013A (en) * | 2021-03-03 | 2021-06-25 | 北京航空航天大学 | Satellite-borne GNSS-R sea ice boundary detection method and system |
| CN113031013B (en) * | 2021-03-03 | 2023-07-18 | 北京航空航天大学 | Satellite-borne GNSS-R sea ice boundary detection method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109471106B (en) | 2021-04-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107563303B (en) | Robust ship target detection method based on deep learning | |
| Zhao et al. | A coupled convolutional neural network for small and densely clustered ship detection in SAR images | |
| CN109583369B (en) | Target identification method and device based on target area segmentation network | |
| Liu et al. | Multiscale morphological compressed change vector analysis for unsupervised multiple change detection | |
| CN111626290B (en) | Infrared ship target detection and identification method under complex sea surface environment | |
| Chen et al. | Ship detection from coastal surveillance videos via an ensemble Canny-Gaussian-morphology framework | |
| CN109086818B (en) | Ocean frontal surface identification method and device | |
| CN107358260B (en) | Multispectral image classification method based on surface wave CNN | |
| Chang et al. | Multisensor satellite image fusion and networking for all-weather environmental monitoring | |
| Priyadharsini et al. | Object detection in underwater acoustic images using edge based segmentation method | |
| CN108564092A (en) | Sunflower disease recognition method based on SIFT feature extraction algorithm | |
| CN107239755A (en) | Offshore oil and gas platform extraction system based on high score satellite remote sensing date | |
| Song et al. | Automatic ship detection for optical satellite images based on visual attention model and LBP | |
| CN107609564A (en) | Submarine target image-recognizing method based on joint segmentation and Fourier descriptor storehouse | |
| Unsalan et al. | Classifying land development in high-resolution satellite imagery using hybrid structural-multispectral features | |
| Andriyanov et al. | Pattern recognition on radar images using augmentation | |
| CN114764801A (en) | Weak and small ship target fusion detection method and device based on multi-vision significant features | |
| Hu et al. | A sample enhancement method based on simple linear iterative clustering superpixel segmentation applied to multibeam seabed classification | |
| Deng et al. | Ship detection from optical satellite image using optical flow and saliency | |
| CN109471106A (en) | In conjunction with the SAR internal wave of ocean fringe counting method method of clustering and frontier tracing method | |
| CN107729903A (en) | SAR image object detection method based on area probability statistics and significance analysis | |
| CN116756486A (en) | Offshore target identification method and device based on acousto-optic electromagnetic multi-source data fusion | |
| Moughal et al. | An automatic unsupervised method based on context-sensitive spectral angle mapper for change detection of remote sensing images | |
| CN116434074A (en) | Target identification method based on adjacent branch complementation significance and multiple priori sparse representation | |
| Kong et al. | Automatic detection technology of sonar image target based on the three‐dimensional imaging |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20210413 |