CN108520271A - Submarine geomorphy type sorter design method based on factorial analysis - Google Patents
Submarine geomorphy type sorter design method based on factorial analysis Download PDFInfo
- Publication number
- CN108520271A CN108520271A CN201810213212.6A CN201810213212A CN108520271A CN 108520271 A CN108520271 A CN 108520271A CN 201810213212 A CN201810213212 A CN 201810213212A CN 108520271 A CN108520271 A CN 108520271A
- Authority
- CN
- China
- Prior art keywords
- factor
- depth
- landforms
- type
- seabed
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
Landscapes
- Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Geophysics And Detection Of Objects (AREA)
Abstract
The submarine geomorphy type sorter design method based on factorial analysis that the invention discloses a kind of.Include the following steps:1) depth distribution feature, including the degree of bias, kurtosis, seabed depth standard deviation, seabed depth Difference Entropy, seabed roughness and the seabed depth coefficient of variation are calculated according to seabed depth measurement data;2) using depth distribution feature as original variable, application factor analysis method extracts geomorphologic factor;3) according to geomorphologic factor, geomorphic type grader is designed using support vector machines;4) the depth distribution characteristic value and geomorphologic factor for calculating landforms to be identified identify geomorphic type using the grader of design.The present invention has many advantages, such as that method is simple, calculation amount is small, recognition accuracy is high, saves manpower.The present invention is suitable for submarine geomorphy type identification.
Description
Technical field
The present invention relates to the technical fields such as marine charting, ocean engineering, Marine oil and gas resource, and in particular to one kind based on because
The submarine geomorphy type sorter design method of son analysis.
Background technology
Landforms are the general names of the various rolling shapes of earth surface.The type of seafloor topography include ancient stream channel, scour trough,
Submarine canyon, deep water water channel, seamount, carbonate platform, cliff, landslide etc..Geomorphological Classification is submarine geomorphy research and drawing
Basis, landform shape can reflect the inner link of morphogenesis type and origin cause of formation control form, be to carry out deep layer Geo knowledge digging
The key of pick.
Multibeam sounding system can detect wide covering, high-resolution seafloor topography fine-feature.The system uses
Strip-type measures, and can measure the water depth value of dozens or even hundreds of seabed measured points in the plane vertical with course-and-bearing simultaneously,
Or all standing depth of water band of an one fixed width, it can accurately and quickly measure the submarine target in the one fixed width of course line
Size, shape and height change.
Landforms parameter is the number description to landforms, for characterizing the spatial distribution characteristic of landforms.There are many landforms parameter, no
It is understood with subject and field and is classified also different.Landforms parameter can be divided into micro-parameter and macroparameter two major classes.It is micro-
See that parameter is described and reflection be specific location geomorphic feature.Common micro-parameter mainly has:The gradient, slope aspect, length of grade,
Planar curvature, profile curvature etc..Macroparameter is described and reflection is geomorphic feature in large area.Common macroscopic view ginseng
Number mainly has:Landform depth standards are poor, terrain variance entropy, terrain roughness, the elevation coefficient of variation etc..
Seafloor topography is more complicated, currently, a large amount of geomorphic type analysis limited to the understanding of submarine geomorphy type
It relies primarily on and is accomplished manually, by the observation and experience of technical staff come Division identification.This method can make full use of technology
The knowledge of personnel, flexibility is good, but technical staff is needed to have abundant Geo knowledge and observation judgement experience, has prodigious
Subjectivity, there are poor in timeliness, labor intensity is big the shortcomings of.Especially because seafloor data has magnanimity rank, rely solely on
The artificial ability of technical staff can not much undertake the processing task of mass data.
Invention content
The space structure feature of present invention application landform depth distribution characteristic present landforms, the extraction of application factor analysis method
The geomorphologic factor for reflecting geomorphic type establishes geomorphic type grader using support vector machines, realizes geomorphic type identification.Have
Method is simple, calculation amount is small, recognition accuracy is high, saves the advantages that manpower.Suitable for submarine geomorphy type identification.
The present invention includes the following steps:
(1) seabed depth distribution characteristics calculates:
Basis respectively Calculate the seabed depth standard deviation m in region to be identified1, the degree of bias
m2, kurtosis m3, Difference Entropy m4, roughness m5, coefficient of variation m6, whereinziFor area to be identified
Seabed depth value in domain at ith measurement point,For seabed depth average value, i=1,2,3 ... ..., n, n is to wait for
Points are measured in identification region;
(2) geomorphologic factor extracts:
Original variable is m1、m2、m3、m4、m5And m6, standard landforms are Ai, i=1,2,3 ... ..., k, application factor analysis
Method extracts the common factor f of original variablei, the variance contribution ratio of i=1,2,3 ... ..., t, each factor are λi, i=1,2,
3 ... ..., t, if meetingThen fi, i=1,2 ... ..., j are geomorphologic factor, wherein and k is geomorphic type number, according to
Training data determines that t is common factor number, fi、λi, t determine that θ is threshold value, is set in program parameter, j according to factorial analysis
For geomorphologic factor number;
(3) geomorphic type classifier design:
According to geomorphologic factor fi, i=1,2 ... ..., j determine landforms type sorter using support vector machines;
(4) geomorphic type identifies:
Calculate the depth distribution characteristic value m of landforms to be identified1、m2、m3、m4、m5And m6, extraction geomorphologic factor fi, i=1,
2 ... ..., j, the grader obtained according to step (3) determine the type of landforms to be identified.
Description of the drawings
Fig. 1 (a) to Fig. 1 (e) is respectively the landform of submarine plateau, coombe, landslide, protuberance, water channel this 5 kinds of geomorphic types
Figure;
Fig. 2 is that the depth coefficient of variation and the depth difference entropy of 5 kinds of landforms cross figure;
Fig. 3 is that the depth coefficient of variation and the terrain roughness of 5 kinds of landforms cross figure;
Fig. 4 is that depth difference entropy and the depth standards difference of 5 kinds of landforms cross figure;
Fig. 5 is that terrain roughness and the depth standards difference of 5 kinds of landforms cross figure;
Fig. 6 is that the depth coefficient of variation and the depth standards difference of 5 kinds of landforms cross figure;
Fig. 7 is that depth standards difference and the kurtosis of 5 kinds of landforms cross figure;
Fig. 8 is the variance contribution ratio figure of the common factor of 5 kinds of geomorphic type seabed depth distribution characteristics;
Fig. 9 is the cumulative proportion in ANOVA figure of the common factor of 5 kinds of geomorphic type seabed depth distribution characteristics;
Figure 10 is the grader of 5 kinds of landforms of design;
Figure 11 is the identification result of geomorphic type in the present embodiment.
Specific implementation mode
The present embodiment calculates landform depth distribution feature, including seabed depth standard according to multi-beam sounding survey data
Difference, the degree of bias, kurtosis, Difference Entropy, roughness and the coefficient of variation extract geomorphologic factor, geomorphic type are determined using support vector machines
Grader realizes the identification of submarine plateau, coombe, landslide, protuberance, water channel this 5 kinds of geomorphic types.
Specific identification step is as follows:
(1) seabed depth distribution characteristics calculates:
Basis respectively Calculate the seabed depth standard deviation m in region to be identified1, the degree of bias
m2, kurtosis m3, Difference Entropy m4, roughness m5, coefficient of variation m6, whereinziFor area to be identified
Seabed depth value in domain at ith measurement point,For seabed depth average value, i=1,2,3 ... ..., n, n is to wait for
Points are measured in identification region.
In the present embodiment, seabed depth data are obtained by multi-beam method measurement, and Fig. 1 (a) to Fig. 1 (e) is respectively sea
Base frame, coombe, landslide, protuberance, water channel this 5 kinds of geomorphic types topographic map;Fig. 2 to Fig. 7 is respectively that the depth of 5 kinds of landforms becomes
Cross figure, the depth coefficient of variation and terrain roughness of different coefficient and depth difference entropy crosses figure, depth difference entropy and depth standards
Difference cross figure, the depth coefficient of variation and the depth standards difference of figure, terrain roughness and depth standards difference that cross crosses figure, depth standards
Difference crosses figure with kurtosis.
The dimensional discrepancy of the depth distribution characteristic value of 5 kinds of landforms in the present embodiment is larger.In Fig. 2 to Fig. 7, trenches and mesas is rushed
The characteristic value on ground is substantially distributed in different regions, can be relatively recognized accurately according only to the range of depth distribution characteristic value
Come;The depth distribution feature difference of other geomorphic types is smaller, and there are more laps in figure, according only to depth distribution spy
Sign identification geomorphic type difficulty is larger.
(2) geomorphologic factor extracts:
Original variable is m1、m2、m3、m4、m5And m6, standard landforms are Ai, i=1,2,3 ... ..., k, application factor analysis
Method extracts the common factor f of original variablei, the variance contribution ratio of i=1,2,3 ... ..., t, each factor are λi, i=1,2,
3 ... ..., t, if meetingThen fi, i=1,2 ... ..., j are geomorphologic factor, wherein and k is geomorphic type number, according to
Training data determines that t is common factor number, fi、λi, t determine that θ is threshold value, is set in program parameter, j according to factorial analysis
For geomorphologic factor number.
In the present embodiment, geomorphic type number is k=5, and the common factor number of the original variable of 5 kinds of landforms is t=6, Fig. 8
For the variance contribution ratio distribution of 6 common factors of 5 kinds of geomorphic types, 6 seabed depth distribution characteristics, Fig. 9 is 5 kinds of landforms classes
The cumulative proportion in ANOVA of 6 common factors of 6 seabed depth distribution characteristics of type.In the present embodiment, θ=80% obtains 3
Geomorphologic factor.
(3) geomorphic type classifier design:
According to geomorphologic factor fi, i=1,2 ... ..., j determine landforms type sorter using support vector machines.
In the present embodiment, 3 geomorphologic factors, the geomorphic type grader that Figure 10 is, wherein Figure 10 (a) are extracted
For determining the landforms that come down, Figure 10 (b) is for determining protuberance landforms, and Figure 10 (c) is for determining tableland, water channel, coombe landforms.
(4) geomorphic type identifies:
Calculate the depth distribution characteristic value m of landforms to be identified1、m2、m3、m4、m5And m6, extraction geomorphologic factor fi, i=1,
2 ... ..., j, the grader obtained according to step (3) determine the type of landforms to be identified.
Figure 11 is the identification result of geomorphic type in the present embodiment.
Claims (1)
1. a kind of submarine geomorphy type sorter design method based on factorial analysis, feature include the following steps:
(1) seabed depth distribution characteristics calculates:
Basis respectively Calculate the seabed depth standard deviation m in region to be identified1, the degree of bias
m2, kurtosis m3, Difference Entropy m4, roughness m5, coefficient of variation m6, wherein ziFor area to be identified
Seabed depth value in domain at ith measurement point,For seabed depth average value, i=1,2,3 ... ..., n, n is to wait for
Points are measured in identification region;
(2) geomorphologic factor extracts:
Original variable is m1、m2、m3、m4、m5And m6, standard landforms are Ai, i=1,2,3 ... ..., k, application factor analysis method carries
Take the common factor f of original variablei, the variance contribution ratio of i=1,2,3 ... ..., t, each factor are λi, i=1,2,3 ... ..., t,
If meetingThen fi, i=1,2 ... ..., j are geomorphologic factor, wherein k is geomorphic type number, according to training data
It determines, t is common factor number, fi、λi, t determine that θ is threshold value, is set in program parameter according to factorial analysis, j be landforms because
Subnumber;
(3) geomorphic type classifier design:
According to geomorphologic factor fi, i=1,2 ... ..., j determine landforms type sorter using support vector machines;
(4) geomorphic type identifies:
Calculate the depth distribution characteristic value m of landforms to be identified1、m2、m3、m4、m5And m6, extraction geomorphologic factor fi, i=1,2 ... ...,
J, the grader obtained according to step (3) determine the type of landforms to be identified.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810213212.6A CN108520271B (en) | 2018-03-15 | 2018-03-15 | Submarine geomorphy type sorter design method based on factorial analysis |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810213212.6A CN108520271B (en) | 2018-03-15 | 2018-03-15 | Submarine geomorphy type sorter design method based on factorial analysis |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108520271A true CN108520271A (en) | 2018-09-11 |
CN108520271B CN108520271B (en) | 2019-10-01 |
Family
ID=63433726
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810213212.6A Expired - Fee Related CN108520271B (en) | 2018-03-15 | 2018-03-15 | Submarine geomorphy type sorter design method based on factorial analysis |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108520271B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110806444A (en) * | 2019-11-14 | 2020-02-18 | 山东科技大学 | Seabed sediment recognition and classification method based on shallow stratum profiler and SVM |
CN112834837A (en) * | 2020-11-20 | 2021-05-25 | 国网天津市电力公司 | User behavior fine analysis method based on non-invasive load monitoring |
CN112907615A (en) * | 2021-01-08 | 2021-06-04 | 中国石油大学(华东) | Submarine landform unit contour and detail identification method based on region growing |
CN117173548A (en) * | 2023-08-10 | 2023-12-05 | 中国地质大学(武汉) | Method and device for constructing intelligent classification model of submarine topography and classification method |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005052890A1 (en) * | 2003-11-28 | 2005-06-09 | Adam Wcislo | Manufacturing of three-dimensional topographical scale models for the purpose of science |
CN103645480A (en) * | 2013-12-04 | 2014-03-19 | 北京理工大学 | Geographic and geomorphic characteristic construction method based on laser radar and image data fusion |
CN107016371A (en) * | 2017-04-09 | 2017-08-04 | 北京工业大学 | UAV Landing Geomorphological Classification method based on improved depth confidence network |
CN107067012A (en) * | 2017-04-25 | 2017-08-18 | 中国科学院深海科学与工程研究所 | Submarine geomorphy cell edges intelligent identification Method based on image procossing |
CN107292339A (en) * | 2017-06-16 | 2017-10-24 | 重庆大学 | The unmanned plane low altitude remote sensing image high score Geomorphological Classification method of feature based fusion |
-
2018
- 2018-03-15 CN CN201810213212.6A patent/CN108520271B/en not_active Expired - Fee Related
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2005052890A1 (en) * | 2003-11-28 | 2005-06-09 | Adam Wcislo | Manufacturing of three-dimensional topographical scale models for the purpose of science |
CN103645480A (en) * | 2013-12-04 | 2014-03-19 | 北京理工大学 | Geographic and geomorphic characteristic construction method based on laser radar and image data fusion |
CN107016371A (en) * | 2017-04-09 | 2017-08-04 | 北京工业大学 | UAV Landing Geomorphological Classification method based on improved depth confidence network |
CN107067012A (en) * | 2017-04-25 | 2017-08-18 | 中国科学院深海科学与工程研究所 | Submarine geomorphy cell edges intelligent identification Method based on image procossing |
CN107292339A (en) * | 2017-06-16 | 2017-10-24 | 重庆大学 | The unmanned plane low altitude remote sensing image high score Geomorphological Classification method of feature based fusion |
Non-Patent Citations (3)
Title |
---|
DAWEI WANG ET AL;: "《Architecture and evolution of deep-water cyclic deposits in the Qiongdongnan Basin, South China Sea: Relationship with the Pleistocene climate events 》", 《MARINE GEOLOGY》 * |
李学杰 等;: "《三沙海底峡谷识别与地貌特征分析》", 《海洋地质与第四纪地质》 * |
王大伟 等;: "《浊流及其相关的深水底形研究进展》", 《地球科学进展》 * |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110806444A (en) * | 2019-11-14 | 2020-02-18 | 山东科技大学 | Seabed sediment recognition and classification method based on shallow stratum profiler and SVM |
CN110806444B (en) * | 2019-11-14 | 2022-06-07 | 山东科技大学 | Seabed sediment recognition and classification method based on shallow stratum profiler and SVM |
CN112834837A (en) * | 2020-11-20 | 2021-05-25 | 国网天津市电力公司 | User behavior fine analysis method based on non-invasive load monitoring |
CN112834837B (en) * | 2020-11-20 | 2022-12-09 | 国网天津市电力公司 | User behavior fine analysis method based on non-invasive load monitoring |
CN112907615A (en) * | 2021-01-08 | 2021-06-04 | 中国石油大学(华东) | Submarine landform unit contour and detail identification method based on region growing |
CN117173548A (en) * | 2023-08-10 | 2023-12-05 | 中国地质大学(武汉) | Method and device for constructing intelligent classification model of submarine topography and classification method |
CN117173548B (en) * | 2023-08-10 | 2024-04-02 | 中国自然资源航空物探遥感中心 | Method and device for constructing intelligent classification model of submarine topography and classification method |
Also Published As
Publication number | Publication date |
---|---|
CN108520271B (en) | 2019-10-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108520271B (en) | Submarine geomorphy type sorter design method based on factorial analysis | |
KR101924278B1 (en) | Apparatus and method for extraction of tidal creeks in tidal flat zones using drone | |
Steiner et al. | Supraglacial ice cliffs and ponds on debris-covered glaciers: spatio-temporal distribution and characteristics | |
Fabbri et al. | High-resolution 3-D mapping using terrestrial laser scanning as a tool for geomorphological and speleogenetical studies in caves: An example from the Lessini mountains (North Italy) | |
CN108629364B (en) | non-Gaussian submarine landform type identification method based on multi-fractal spectral features | |
Schumann et al. | The utility of spaceborne radar to render flood inundation maps based on multialgorithm ensembles | |
Bauer | Analysis of dolines using multiple methods applied to airborne laser scanning data | |
CN113034689A (en) | Laser point cloud-based terrain three-dimensional model, terrain map construction method and system, and storage medium | |
CN108459318A (en) | Potential landslide EARLY RECOGNITION method based on remote sensing technology | |
Bullard et al. | Morphometric analysis of aeolian bedforms in the Namib Sand Sea using ASTER data | |
Goodwin et al. | Characterizing urban surface cover and structure with airborne lidar technology | |
CN111666904A (en) | Interpretation and identification method for high-resolution remote sensing image geological disasters of power transmission line | |
CN108460422B (en) | Submarine geomorphy kind identification method based on depth distribution feature | |
DOMÍNGUEZ-CUESTA et al. | GIS as a tool to detect flat erosional surfaces in coastal areas: a case study in North Spain | |
CN108320291B (en) | Seabed landform boundary extraction method based on Dajin algorithm | |
Liu et al. | A geomorphological model for landslide detection using airborne LIDAR data | |
Dorninger et al. | Automated detection and interpretation of geomorphic features in LiDAR point clouds | |
Ashmawy et al. | Comparative study of the drainage basin morphometry extracted from topographic maps and SRTM DEMs: an example from Ghadir watershed, Eastern Desert, Egypt | |
Mandlburger et al. | Derivation of a countrywide river network based on Airborne Laser Scanning DEMs-results of a pilot study | |
Launspach | Automated sinkhole extraction and morphological analysis in northeast Iowa using high-resolution LiDAR data | |
Rettelbach et al. | From images to hydrologic networks-understanding the arctic landscape with graphs | |
Zylshal et al. | An object based image analysis approach to semi-automated karst morphology extraction | |
Doumit | Digital Terrain Analysis of Lebanon: A Study of Geomorphometry | |
CN114723911B (en) | Seabed geographic entity boundary automatic identification method based on D-P algorithm and optimal path | |
Shahzad et al. | Object Based Image Analysis For Delineation Of Slope Units |
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 | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20191001 Termination date: 20200315 |