CN116580321A - Automatic recognition method for remote sensing image shoreline - Google Patents
Automatic recognition method for remote sensing image shoreline Download PDFInfo
- Publication number
- CN116580321A CN116580321A CN202310849825.XA CN202310849825A CN116580321A CN 116580321 A CN116580321 A CN 116580321A CN 202310849825 A CN202310849825 A CN 202310849825A CN 116580321 A CN116580321 A CN 116580321A
- Authority
- CN
- China
- Prior art keywords
- shoreline
- remote sensing
- identified
- distance value
- historical
- 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 43
- 238000007781 pre-processing Methods 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 238000012544 monitoring process Methods 0.000 claims description 32
- 238000004590 computer program Methods 0.000 claims description 13
- 238000002372 labelling Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 6
- 238000012876 topography Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 4
- 238000000605 extraction Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 230000008859 change Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000003628 erosive effect Effects 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000000691 measurement method Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 239000002352 surface water Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
-
- 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
- Y02A10/00—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE at coastal zones; at river basins
- Y02A10/40—Controlling or monitoring, e.g. of flood or hurricane; Forecasting, e.g. risk assessment or mapping
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Image Processing (AREA)
- Processing Or Creating Images (AREA)
Abstract
The embodiment of the invention discloses an automatic recognition method for a remote sensing image shoreline, which comprises the following steps: acquiring a historical remote sensing image, and preprocessing the historical remote sensing image to obtain a shoreline historical information map of different time periods; establishing a historical remote sensing distance value sample library of the distance between the shoreline and the selected ground object according to the time dimension; acquiring surface data of the current shoreline to obtain a surface distance value sequence of the distance between the current shoreline and the selected ground object; performing discrete difference calculation on the historical remote sensing distance value sample library and the ground surface distance value sequence to obtain a remote sensing difference coefficient; acquiring a remote sensing image of a shoreline to be identified, and preprocessing the remote sensing image of the shoreline to be identified to obtain a shoreline information map to be identified; establishing a to-be-identified distance value sequence of the distance between the shoreline and the selected ground object in the to-be-identified shoreline information map; substituting the remote sensing difference coefficient into the distance value sequence to be identified, and correcting the actual position of the shoreline to form a shoreline profile.
Description
Technical Field
The invention relates to the technical field of remote sensing image data processing, in particular to an automatic recognition method for a remote sensing image shoreline.
Background
For a long time, a field measurement method is generally adopted for mapping the coastline, and the method is the most original conventional coastline measurement method, namely, an optical measuring instrument (theodolite, total station and the like) is adopted to collect coastline characteristic points at regular intervals near a climax tide level line, and the coastline is obtained by marking on a digital topographic map and connecting the coastline characteristic points into lines. Through the development of GPS positioning measurement technology, the GPS mobile station still needs to be manually carried to be positioned on site although the GPS mobile station can be carried out all-weather, dynamically and in real time. The method can comprehensively consider the characteristics of topography, vegetation, environment and the like, has certain accuracy, is limited by high execution difficulty, is limited by conditions of topography, weather and the like, has a very long working period for completing one-time measurement, and has low efficiency. In order to meet the shoreline monitoring requirements, a new method is needed to enable monitoring of a wide range of shorelines.
Remote Sensing (RS) is a space detection technology based on an aerial photography technology, and by virtue of the characteristics of non-contact property, short image acquisition period, abundant remote sensing image information, less condition restriction of acquired information and the like, the method can effectively solve the difficulty encountered in coastline extraction and meet the requirement of dynamic monitoring in a research area. The satellite remote sensing image is an important data source for extracting the shore line of the surface water area because of the characteristics of macroscopicity and real-time property. However, the automatic extraction of the land water shoreline based on the satellite radar is only suitable for the shoreline extraction of a small space area with negligible topographic relief and space difference, and has low practicability. The common shoreline extraction method is that a worker interprets satellite remote sensing images acquired by a satellite sensor, and the land water area shoreline is drawn from the satellite remote sensing images according to the information such as the geochemical characteristics, the optical characteristics and the like of various shorelines, and the processing process is completely dependent on manual work and has poor accuracy.
Disclosure of Invention
Therefore, an object of the embodiments of the present invention is to provide an automatic recognition method for a remote sensing image shoreline, which can realize accurate monitoring of a shoreline contour, effectively reduce difficulty in shoreline monitoring, and improve monitoring efficiency.
In a first aspect, an embodiment of the present invention provides a method for automatically identifying a remote sensing image shoreline, where the method includes:
and acquiring a historical remote sensing image, and preprocessing the historical remote sensing image to obtain a shoreline historical information map in different time periods.
And establishing a historical remote sensing distance value sample library of the distance between the shoreline and the selected ground object according to the time dimension.
And acquiring the earth surface data of the current shoreline to obtain an earth surface distance value sequence of the distance between the current shoreline and the selected ground object.
And performing discrete difference calculation on the historical remote sensing distance value sample library and the ground surface distance value sequence to obtain a remote sensing difference coefficient.
And acquiring a remote sensing image of the shoreline to be identified, and preprocessing the remote sensing image of the shoreline to be identified to obtain a shoreline information map to be identified.
And establishing a to-be-identified distance value sequence of the distance between the shoreline and the selected ground object in the to-be-identified shoreline information map.
Substituting the remote sensing difference coefficient into the distance value sequence to be identified, and correcting the actual position of the shoreline by taking the selected ground feature as a reference to form a shoreline profile.
With reference to the first aspect, an embodiment of the present invention provides a first possible implementation manner of the first aspect, where the obtaining a historical remote sensing image, preprocessing the historical remote sensing image, and obtaining a shoreline historical information map includes:
and selecting the appointed time range as a first time period, and acquiring a shoreline long-time-sequence remote sensing monitoring image and a historical image of a lake contour line sample library in the first time period.
And in the first time period, matching the different types of historical images, and adjusting the historical images to the same precision to obtain the image with the specified precision.
And labeling the specified precision image in the first time period with the shoreline hydrologic data, the surrounding ground feature position, the surrounding terrain and the altitude to obtain a shoreline historical information map.
And respectively processing the history images in n different time periods to obtain a shoreline history information map in different time periods, wherein n is a natural number larger than 1.
With reference to the first aspect, the embodiment of the present invention provides a second possible implementation manner of the first aspect, wherein the establishing, in a time dimension, a historical remote sensing distance value sample library of distances between a shoreline and a selected ground object includes:
selecting a plurality of shoreline points in a shoreline history information map in a first time period, and respectively marking the points as a 1 To a m Wherein m is a natural number greater than 1.
In a shoreline history information map in a first time period, selecting selected ground objects closest to the selected shoreline points respectively corresponding to a plurality of the shoreline points, and marking the ground objects as b respectively 1 To b m . Calculating distance values between a plurality of shoreline points and a plurality of corresponding selected ground objects to obtain d respectively 1 =|a 1 -b 1 |，d 2 =|a 2 -b 2 |，d 3 =|a 3 -b 3 |……，d m =|a m -b m |。
In the shoreline historical information maps in n different time periods, respectively finding the selected ground objects in the shoreline historical information maps in the first time period, selecting the shoreline point closest to each selected ground object in each shoreline historical information map, and calculating a distance value to obtain:
d 21 =|a 21 -b 21 |，d 22 =|a 22 -b 22 |，d 23 =|a 23 -b 23 |……，d 2m =|a 2m -b 2m |；
……
d n1 =|a n1 -b n1 |，d n2 =|a n2 -b n2 |，d n3 =|a n3 -b n3 |……，d nm =|a nm -b nm |；
a historical remote sensing distance value sample library is formed:
D=。
with reference to the first aspect, an embodiment of the present invention provides a third possible implementation manner of the first aspect, where the acquiring surface data of the current shoreline to obtain a surface distance value sequence of a distance between the current shoreline and the selected ground object includes:
finding out a plurality of selected ground objects b selected in the historical information map 1 To b m 。
Corresponding to a plurality of selected ground objects, respectively selecting the closest shoreline points on the actual ground surface of the current shoreline, and respectively marking the closest shoreline points as a 1 ' to a m ’。
Calculating distance values between a plurality of selected ground features and a plurality of corresponding current shoreline points to obtain a ground surface distance value sequence:
D’=（d 1 ’=|a 1 ’-b 1 |，d 2 ’=|a 2 ’-b 2 |，d 3 ’=|a 3 ’-b 3 |……，d m ’=|a m ’-b m |）。
with reference to the first aspect, an embodiment of the present invention provides a fourth possible implementation manner of the first aspect, where the performing discrete difference calculation on the historical remote sensing distance value sample library and the surface distance value sequence to obtain a remote sensing difference coefficient includes:
discrete difference value calculation is carried out on the historical remote sensing distance value and the ground surface distance value of each group of shorelines and the selected ground object respectively, and a difference coefficient sequence is obtained:
S m =（，/>，/>……，/>）。
calculating the average value of the difference coefficient sequence to obtain a remote sensing difference coefficient S=。
With reference to the first aspect, an embodiment of the present invention provides a fifth possible implementation manner of the first aspect, where the collecting a remote sensing image of a shore line to be identified, preprocessing the remote sensing image of the shore line to be identified, to obtain a shore line information map to be identified, includes:
and acquiring a shoreline remote sensing monitoring image to be identified.
And adjusting the shore line remote sensing monitoring image to be identified and the shore line historical information map to the same precision to obtain a remote sensing monitoring image with specified precision.
Labeling the specified precision remote sensing monitoring image by combining the ground object category hyperspectral and the sar wave band fusion information base to obtain a to-be-identified shore line information map marked with shore line hydrologic data, surrounding ground object positions, surrounding topography and altitude.
With reference to the first aspect, an embodiment of the present invention provides a sixth possible implementation manner of the first aspect, where the establishing, in the to-be-identified shore line information map, a to-be-identified distance value sequence of a distance between a shore line and a selected ground object includes:
selecting a plurality of shoreline points from the shoreline information map to be identified, and marking the points as e respectively 1 To e p Wherein p is a natural number greater than 1.
In the shoreline information map to be identified, selecting the selected ground features closest to the selected shoreline points respectively corresponding to a plurality of the shoreline points, and marking the ground features as f respectively 1 To f p 。
Calculating distance values between a plurality of shoreline points and a plurality of corresponding selected ground features to respectively obtain a distance value sequence to be identified:
G=（g 1 =|e 1 -f 1 |，g 2 =|e 2 -f 2 |，g 3 =|e 3 -f 3 |……，g p =|e p -f p |）。
with reference to the first aspect, an embodiment of the present invention provides a seventh possible implementation manner of the first aspect, where substituting the remote sensing difference coefficient into the distance value sequence to be identified, correcting an actual position of a shore line with reference to a selected ground feature, to form a shore line contour includes:
substituting the remote sensing difference coefficient S into the distance value sequence G to be identified, and correcting each distance value to obtain a corrected distance value sequence:
G’=（g 1 ’=g 1 *（1±S），g 2 ’=g 2 *（1±S），g 3 ’=g 3 *（1±S）……，g p ’=g p *（1±S））。
and correcting the actual position of the shoreline by taking the selected ground feature in the shoreline information map to be identified as a reference to form a shoreline contour.
In a second aspect, an embodiment of the present invention further provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the foregoing method for automatically identifying a remote sensing image shoreline when executing the computer program.
In a third aspect, an embodiment of the present invention further provides a computer readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements a remote sensing image shoreline automatic identification method as described above.
The embodiment of the invention has the beneficial effects that:
according to the remote sensing image shoreline automatic identification method, a historical remote sensing distance value sample library is established based on a shoreline historical information map in different time periods, the position of a selected ground object is fixed and is used as a reference object, the distance from the selected ground object to the shoreline is calculated, then a remote sensing difference coefficient is calculated according to the distance between the shoreline and the selected ground object, and the actual position of the shoreline is corrected to form a complete shoreline contour. The method and the device realize accurate monitoring of the shoreline contour, effectively reduce the difficulty of shoreline monitoring, improve the monitoring efficiency, and simultaneously provide technical support for subsequent overall process monitoring of ecological meteorological changes of the lake. The method combines the characteristics of different shorelines and selected ground features to correct the shorelines, obtain the shorelines in a strict sense, and improve the accuracy of the shoreline determination. Based on the method, a shoreline change model can be established, and the shoreline transition condition can be accurately analyzed.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of the method for automatically identifying the shoreline of the remote sensing image.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein can be arranged and designed in a wide variety of different configurations.
Referring to fig. 1, a first embodiment of the present invention provides an automatic recognition method for a remote sensing image shoreline, which includes:
and acquiring a historical remote sensing image, and preprocessing the historical remote sensing image to obtain lake shoreline historical information maps in different time periods.
And establishing a historical remote sensing distance value sample library of the distance between the shoreline and the selected ground object according to the time dimension.
And acquiring the surface data of the current lake shoreline to obtain a surface distance value sequence of the distance between the current shoreline and the selected ground object.
And performing discrete difference calculation on the historical remote sensing distance value sample library and the ground surface distance value sequence to obtain a remote sensing difference coefficient.
And collecting the lake shoreline remote sensing image to be identified, and preprocessing the lake shoreline remote sensing image to be identified to obtain the lake shoreline information map to be identified.
And establishing a to-be-identified distance value sequence of the distance between the shoreline and the selected ground object in the to-be-identified lake shoreline information map.
Substituting the remote sensing difference coefficient into the distance value sequence to be identified, and correcting the actual position of the shoreline by taking the selected ground feature as a reference to form a shoreline profile.
Specifically, the obtaining the historical remote sensing image, preprocessing the historical remote sensing image, and obtaining the lake shoreline historical information map includes:
and selecting the appointed time range as a first time period, and acquiring a lake shoreline long-time-sequence remote sensing monitoring image and a history image of a lake contour line sample library in the first time period.
And in the first time period, matching the different types of historical images, and adjusting the historical images to the same precision to obtain the image with the specified precision.
The precision refers to the consistency and alignment degree of different types of historical images on the spatial reference. Because different kinds of images may have problems of shooting angles, ground deformation, image distortion and the like, image matching and adjustment are required to be performed so that the images correspond to the same geographic position on the same precision level.
Specifically, the matching processing is performed on different kinds of history images, and the history images are adjusted to the same precision to obtain an image with specified precision, including:
loading different kinds of historical images, performing basic preprocessing, cutting the edges of the images, adjusting the sizes and rotating the images, and ensuring the alignment and consistency of the images.
And adjusting the resolution of the preprocessed image to a preset intermediate value by using an interpolation algorithm to obtain an image with specified accuracy.
And outputting the image with the specified precision into a specified format and storing the image.
And labeling the specified precision image in the first time period with the shoreline hydrologic data, the surrounding ground feature positions, the surrounding terrain and the altitude to obtain a lake shoreline historical information map.
Specifically, in a lake shoreline historical information map, a boundary line of a lake shoreline water area is marked by using ground object category hyperspectral data and an SAR wave band fusion information base; and combining hyperspectral data to identify and label different types of water bodies such as lakes, rivers, wetlands and the like.
Labeling the land feature positions around the lake shoreline by using the land feature type hyperspectral data, classifying the land feature according to the reflectivity and the spectral characteristics of different wave bands in the hyperspectral data, and labeling different land feature types such as cities, villages, forests, farmlands and the like.
And marking the fluctuation and change of the surrounding terrain by combining the SAR wave band data and the terrain information base. The echo signals of the SAR wave bands are used for providing terrain height information, including the slope of the terrain, mountain or hills and other terrain features.
And labeling the altitude in the map by utilizing the terrain information base and the hyperspectral data of the ground object category. Providing terrain elevation information by Digital Elevation Model (DEM) data in a terrain information base; and (3) associating the altitude with a specific ground object type by combining hyperspectral data, and marking the altitude of mountains or hills.
And respectively processing the history images in n different time periods to obtain lake shoreline history information maps in different time periods.
Specifically, the establishing a historical remote sensing distance value sample library of the distance between the shoreline and the selected ground object according to the time dimension comprises:
selecting a plurality of shoreline points from a lake shoreline historical information map in a first time period, and marking the points respectivelyDenoted as a 1 To a m Wherein m is a natural number greater than 1.
In a lake shoreline historical information map in a first time period, selecting selected ground objects closest to the selected shoreline points respectively corresponding to a plurality of shoreline points, and marking the selected ground objects as b respectively 1 To b m 。
By comparing the shoreline historical information maps of different time periods, a shoreline point which is kept relatively stable in the shoreline historical information map is selected, and a plurality of selected shoreline points represent areas with slower shoreline erosion or erosion rates.
Calculating distance values between a plurality of shoreline points and a plurality of corresponding selected ground objects to obtain d respectively 1 =|a 1 -b 1 |，d 2 =|a 2 -b 2 |，d 3 =|a 3 -b 3 |……，d m =|a m -b m |。
In the lake shoreline historical information maps in n different time periods, respectively finding the selected ground objects in the shoreline historical information maps in the first time period, corresponding to a plurality of the selected ground objects, respectively selecting the shoreline points closest to each shoreline historical information map, and calculating distance values to obtain:
d 21 =|a 21 -b 21 |，d 22 =|a 22 -b 22 |，d 23 =|a 23 -b 23 |……，d 2m =|a 2m -b 2m |；
……
d n1 =|a n1 -b n1 |，d n2 =|a n2 -b n2 |，d n3 =|a n3 -b n3 |……，d nm =|a nm -b nm |；
a historical remote sensing distance value sample library is formed:
D=。
specifically, the collecting the surface data of the current lake shoreline to obtain a surface distance value sequence of the distance between the current shoreline and the selected ground feature includes:
finding out a plurality of selected ground objects b selected in the historical information map 1 To b m 。
Corresponding to a plurality of selected ground objects, respectively selecting the closest shoreline points on the actual ground surface of the current lake shoreline, and respectively marking the closest shoreline points as a 1 ' to a m ’。
Calculating distance values between a plurality of selected ground features and a plurality of corresponding current shoreline points to obtain a ground surface distance value sequence:
D’=（d1’，d2’，d3’……，dm’）。
specifically, the discrete difference calculation is performed on the historical remote sensing distance value sample library and the ground surface distance value sequence to obtain a remote sensing difference coefficient, which includes:
discrete difference value calculation is carried out on the historical remote sensing distance value and the ground surface distance value of each group of shorelines and the selected ground object respectively, and a difference coefficient sequence is obtained:
S m =（，/>，/>……，/>）。
calculating the average value of the difference coefficient sequence to obtain a remote sensing difference coefficient S=。
Specifically, the collecting the lake shoreline remote sensing image to be identified, and preprocessing the lake shoreline remote sensing image to be identified to obtain the lake shoreline information map to be identified includes:
and collecting lake shoreline remote sensing monitoring images to be identified.
And adjusting the lake shoreline remote sensing monitoring image to be identified and the lake shoreline historical information map to the same precision to obtain a remote sensing monitoring image with specified precision.
Labeling the specified precision remote sensing monitoring image by combining the feature class hyperspectral and the sar wave band fusion information base to obtain a lake shoreline information map to be identified, wherein the lake shoreline hydrological data, the surrounding feature positions, the surrounding topography and the altitude of the lake shoreline information map are marked.
Specifically, the establishing a to-be-identified distance value sequence of the distance between the shoreline and the selected ground object in the to-be-identified lake shoreline information map includes:
selecting a plurality of shoreline points from the lake shoreline information map to be identified, and marking the points as e respectively 1 To e p Wherein p is a natural number greater than 1.
In the lake shoreline information map to be identified, selecting the selected ground objects closest to the selected shoreline points respectively corresponding to a plurality of shoreline points, and marking the ground objects as f respectively 1 To f p 。
Calculating distance values between a plurality of shoreline points and a plurality of corresponding selected ground features to respectively obtain a distance value sequence to be identified:
G=（g 1 =|e 1 -f 1 |，g 2 =|e 2 -f 2 |，g 3 =|e 3 -f 3 |……，g p =|e p -f p |）。
specifically, the substituting the remote sensing difference coefficient into the distance value sequence to be identified, correcting the actual position of the shoreline by taking the selected ground feature as a reference, and forming the shoreline profile includes:
substituting the remote sensing difference coefficient S into the distance value sequence G to be identified, and correcting each distance value to obtain a corrected distance value sequence:
G’=（g 1 ’=g 1 *（1±S），g 2 ’=g 2 *（1±S），g 3 ’=g 3 *（1±S）……，g p ’=g p *（1±S））。
and correcting the actual position of the shoreline by taking the selected ground feature in the lake shoreline information map to be identified as a reference to form a shoreline contour.
Substituting the remote sensing difference coefficient S into the distance value sequence G to be identified includes:
and summing or multiplying each distance value in the distance value sequence G to be identified with 1 and the remote sensing difference coefficient S respectively to obtain a corrected distance value sequence G'. The sum or difference is determined according to whether the difference between the historical remote sensing distance value of each group of shorelines and the selected ground object and the ground surface distance value is positive or negative.
A second embodiment of the present invention provides a computer device, including a memory, a processor, and a computer program stored on the memory and capable of running on the processor, where the processor implements the remote sensing image shoreline automatic identification method as described above when executing the computer program.
A third embodiment of the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements a remote sensing image shoreline automatic identification method as described above.
The embodiment of the invention aims to protect an automatic recognition method for a remote sensing image shoreline, which has the following effects:
1. the method has the advantages that accurate monitoring of the shoreline outline is achieved, the difficulty of shoreline monitoring is effectively reduced, the monitoring efficiency is improved, and meanwhile, technical support is provided for subsequent overall process monitoring of ecological meteorological changes of lakes.
2. And by combining the characteristics of different shorelines and selected ground features, correcting the shorelines to obtain the shorelines in a strict sense, and improving the accuracy of the shoreline determination. Based on the method, a shoreline change model can be established, and the shoreline transition condition can be accurately analyzed.
The computer program product of the remote sensing image shoreline automatic identification method and device provided by the embodiment of the invention comprises a computer readable storage medium storing program codes, and the instructions included in the program codes can be used for executing the method in the previous method embodiment, and specific implementation can be referred to the method embodiment and will not be repeated here.
Specifically, the storage medium can be a general storage medium, such as a mobile disk, a hard disk and the like, and when a computer program on the storage medium is run, the remote sensing image shoreline automatic identification method can be executed, so that accurate monitoring of the shoreline outline can be realized, the difficulty of shoreline monitoring is effectively reduced, and the monitoring efficiency is improved.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a non-volatile computer readable storage medium executable by a processor. Based on this understanding, the technical solution of the present invention may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-only Memory (ROM), a random access Memory (Ramdom Access Memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
Finally, it should be noted that: the above examples are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention, but it should be understood by those skilled in the art that the present invention is not limited thereto, and that the present invention is described in detail with reference to the foregoing examples: any person skilled in the art may modify or easily conceive of the technical solution described in the foregoing embodiments, or perform equivalent substitution of some of the technical features, while remaining within the technical scope of the present disclosure; such modifications, changes or substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention, and are intended to be included in the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. The automatic recognition method for the remote sensing image shoreline is characterized by comprising the following steps of:
acquiring a historical remote sensing image, and preprocessing the historical remote sensing image to obtain a shoreline historical information map of different time periods;
establishing a historical remote sensing distance value sample library of the distance between the shoreline and the selected ground object according to the time dimension;
acquiring surface data of the current shoreline to obtain a surface distance value sequence of the distance between the current shoreline and the selected ground object;
performing discrete difference calculation on the data in the historical remote sensing distance value sample library and the ground surface distance value sequence to obtain a remote sensing difference coefficient;
acquiring a remote sensing image of a shoreline to be identified, and preprocessing the remote sensing image of the shoreline to be identified to obtain a shoreline information map to be identified;
establishing a to-be-identified distance value sequence of the distance between the shoreline and the selected ground object in the to-be-identified shoreline information map;
substituting the remote sensing difference coefficient into the distance value sequence to be identified, and correcting the actual position of the shoreline by taking the selected ground feature as a reference to form a shoreline profile.
2. The method for automatically identifying a shore line of a remote sensing image according to claim 1, wherein the acquiring a historical remote sensing image, preprocessing the historical remote sensing image, and obtaining a shore line historical information map comprises:
selecting a designated time range as a first time period, and acquiring a shoreline long-time-sequence remote sensing monitoring image and a historical image of a lake contour line sample library in the first time period;
in a first time period, matching different types of historical images, and adjusting to the same precision to obtain an image with specified precision;
labeling the specified precision image in the first time period with the shoreline hydrological data, the surrounding ground feature position, the surrounding terrain and the altitude to obtain a shoreline historical information map;
and respectively processing the history images in n different time periods to obtain a shoreline history information map in different time periods, wherein n is a natural number larger than 1.
3. The method for automatically identifying a shore line of a remote sensing image according to claim 2, wherein the establishing a historical remote sensing distance value sample library of distances between the shore line and the selected ground object according to the time dimension comprises:
selecting a plurality of shoreline points in a shoreline history information map in a first time period, and respectively marking the points as a 1 To a m Wherein m is a natural number greater than 1;
in a shoreline history information map in a first time period, selecting selected ground objects closest to the selected shoreline points respectively corresponding to a plurality of the shoreline points, and marking the ground objects as b respectively 1 To b m ；
Calculating distance values between a plurality of shoreline points and a plurality of corresponding selected ground objects to obtain respectively
；
In the shoreline historical information maps in n different time periods, respectively finding the selected ground objects in the shoreline historical information maps in the first time period, selecting the shoreline point closest to each selected ground object in each shoreline historical information map, and calculating a distance value to obtain:
；
……
；
a historical remote sensing distance value sample library is formed:
D=。
4. the method for automatically identifying a remote sensing image shoreline according to claim 3, wherein the step of acquiring the surface data of the current shoreline to obtain a surface distance value sequence of the distance between the current shoreline and the selected ground feature comprises the steps of:
finding out a plurality of selected ground objects b selected in the historical information map 1 To b m ；
Corresponding to a plurality of selected ground objects, respectively selecting the closest shoreline points on the actual ground surface of the current shoreline, and respectively marking the closest shoreline points as a 1 ' to a m ’；
Calculating distance values between a plurality of selected ground features and a plurality of corresponding current shoreline points to obtain a ground surface distance value sequence:
D’=（d 1 ’=|a 1 ’-b 1 |，d 2 ’=|a 2 ’-b 2 |，d 3 ’=|a 3 ’-b| 3 ……，d m ’=|a m ’-b m |）。
5. the method for automatically identifying a shore line of a remote sensing image according to claim 4, wherein the performing discrete difference calculation on the historical remote sensing distance value sample library and the surface distance value sequence to obtain a remote sensing difference coefficient comprises:
discrete difference value calculation is carried out on the historical remote sensing distance value and the ground surface distance value of each group of shorelines and the selected ground object respectively, and a difference coefficient sequence is obtained:
S m =（，/>，/>……，/>）；
calculating the average value of the difference coefficient sequence to obtain a remote sensing difference coefficient S=。
6. The method for automatically identifying a shore line of a remote sensing image according to claim 1, wherein the steps of collecting a shore line remote sensing image to be identified, preprocessing the shore line remote sensing image to be identified, and obtaining a shore line information map to be identified include:
collecting a shoreline remote sensing monitoring image to be identified;
the shore line remote sensing monitoring image to be identified and the shore line historical information map are adjusted to be under the same precision, and a remote sensing monitoring image with specified precision is obtained;
labeling the specified precision remote sensing monitoring image by combining the ground object category hyperspectral and the sar wave band fusion information base to obtain a to-be-identified shore line information map marked with shore line hydrologic data, surrounding ground object positions, surrounding topography and altitude.
7. The method for automatically identifying a shore line of a remote sensing image according to claim 5, wherein the step of establishing a sequence of distance values to be identified for the distance between the shore line and the selected ground object in the shore line information map to be identified comprises the steps of:
selecting a plurality of shoreline points from the shoreline information map to be identified, and marking the points as e respectively 1 To e p Wherein p is a natural number greater than 1;
in the shoreline information map to be identified, selecting the selected ground features closest to the selected shoreline points respectively corresponding to a plurality of the shoreline points, and marking the ground features as f respectively 1 To f p ；
Calculating distance values between a plurality of shoreline points and a plurality of corresponding selected ground features to respectively obtain a distance value sequence to be identified:
G=（g 1 =|e 1 -f 1 |，g 2 =|e 2 -f 2 |，g 3 =|e 3 -f 3 |……，g p =|e p -f p |）。
8. the method for automatically identifying a shore line of a remote sensing image according to claim 7, wherein substituting the remote sensing difference coefficient into the sequence of distance values to be identified, correcting the actual position of the shore line based on the selected ground feature, and forming a shore line contour comprises:
substituting the remote sensing difference coefficient S into the distance value sequence G to be identified, and correcting each distance value to obtain a corrected distance value sequence:
G’=（g 1 ’=g 1 *（1±S），g 2 ’=g 2 *（1±S），g 3 ’=g 3 *（1±S）……，g p ’=g p *（1±S））；
and correcting the actual position of the shoreline by taking the selected ground feature in the shoreline information map to be identified as a reference to form a shoreline contour.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor implements the remote sensing image shoreline automatic identification method as claimed in any one of claims 1 to 8 when the computer program is executed by the processor.
10. A computer readable storage medium having stored thereon a computer program, wherein the computer program when executed by a processor implements the remote sensing image shoreline automatic identification method according to any of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310849825.XA CN116580321B (en) | 2023-07-12 | 2023-07-12 | Automatic recognition method for remote sensing image shoreline |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310849825.XA CN116580321B (en) | 2023-07-12 | 2023-07-12 | Automatic recognition method for remote sensing image shoreline |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116580321A true CN116580321A (en) | 2023-08-11 |
| CN116580321B CN116580321B (en) | 2023-09-08 |
Family
ID=87543488
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310849825.XA Active CN116580321B (en) | 2023-07-12 | 2023-07-12 | Automatic recognition method for remote sensing image shoreline |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116580321B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389826A (en) * | 2015-12-23 | 2016-03-09 | 国家海洋局第一海洋研究所 | High-resolution SAR remote sensing extraction method for coastline of coral island |
| CN107358161A (en) * | 2017-06-08 | 2017-11-17 | 深圳先进技术研究院 | A kind of tidal saltmarsh method and system based on classification of remote-sensing images |
| CN109034083A (en) * | 2018-08-03 | 2018-12-18 | 青岛大学 | A kind of natural Extracting costline method and apparatus based on more scape remote sensing images |
| CN115331102A (en) * | 2022-07-29 | 2022-11-11 | 长江空间信息技术工程有限公司(武汉) | Remote sensing image river and lake shoreline intelligent monitoring method based on deep learning |
-
2023
- 2023-07-12 CN CN202310849825.XA patent/CN116580321B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389826A (en) * | 2015-12-23 | 2016-03-09 | 国家海洋局第一海洋研究所 | High-resolution SAR remote sensing extraction method for coastline of coral island |
| CN107358161A (en) * | 2017-06-08 | 2017-11-17 | 深圳先进技术研究院 | A kind of tidal saltmarsh method and system based on classification of remote-sensing images |
| CN109034083A (en) * | 2018-08-03 | 2018-12-18 | 青岛大学 | A kind of natural Extracting costline method and apparatus based on more scape remote sensing images |
| CN115331102A (en) * | 2022-07-29 | 2022-11-11 | 长江空间信息技术工程有限公司(武汉) | Remote sensing image river and lake shoreline intelligent monitoring method based on deep learning |
Non-Patent Citations (2)
| Title |
|---|
| 刘亚飞: "基于IDL的岛屿岸线及港口码头的人工智能提取", 测绘与空间地理信息, vol. 37, no. 2, pages 96 - 98 * |
| 田德政: "模拟涨潮的复杂海岸类型岸线自动提取方法", 《海洋环境科学》, vol. 39, no. 1, pages 153 - 161 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116580321B (en) | 2023-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Fuller et al. | The UK Land Cover Map 2000: construction of a parcel-based vector map from satellite images | |
| Pietro et al. | Developing terrestrial-LIDAR-based digital elevation models for monitoring beach nourishment performance | |
| CN111951392A (en) | Beach above-dry-water-level terrain reconstruction method based on time-series remote sensing images and water level monitoring data | |
| Yan et al. | Shoreline change detection and forecast along the Yancheng coast using a digital shoreline analysis system | |
| EP3794386B1 (en) | Determination of location-specific weather information for agronomic decision support | |
| CN106197383A (en) | A kind of remote sensing estimation method of sea ice volume | |
| CN113486975A (en) | Ground object classification method, device, equipment and storage medium for remote sensing image | |
| Vos et al. | Benchmarking satellite-derived shoreline mapping algorithms | |
| Gao et al. | Analysis of flood inundation in ungauged basins based on multi-source remote sensing data | |
| CN114943161B (en) | Inland lake terrain inversion method based on multi-source remote sensing data | |
| CN112200050A (en) | Lake water volume space-time change analysis method and device based on multi-source satellite data | |
| CN113960625B (en) | Water depth inversion method based on satellite-borne single-photon laser active and passive remote sensing fusion | |
| Beaucage et al. | Synthetic aperture radar satellite data for offshore wind assessment: A strategic sampling approach | |
| CN116580321B (en) | Automatic recognition method for remote sensing image shoreline | |
| US20210287393A1 (en) | Landmark configuration matcher | |
| CN116994012A (en) | Map spot matching system and method based on ecological restoration | |
| Liu et al. | Sub-pixel technique for time series analysis of shoreline changes based on multispectral satellite imagery | |
| CN114152302B (en) | Lake water storage variation estimation method, system, electronic device and medium | |
| Al-Nasrawi et al. | Geoinformatic analysis of vegetation and climate change on intertidal sedimentary landforms in southeastern Australian estuaries from 1975-2015 | |
| Hua et al. | The research of artificial shoreline extraction based on airborne LIDAR data | |
| Kyzivat et al. | Contemporary and historical detection of small lakes using super resolution Landsat imagery: promise and peril | |
| Łysko et al. | CCMORPH—Coastal cliffs morphology analysis toolbox | |
| Zhang et al. | Detection of Low Elevation Outliers in TanDEM-X DEMs With Histogram and Adaptive TIN | |
| Liang et al. | Using Sentinel images for analyzing water and land separability in an agricultural river basin | |
| Wang et al. | Icelandic coastline extraction based on water index using Landsat-8 image |
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 |