CN113158718A - Sea ice monitoring method and system for offshore ship - Google Patents
Sea ice monitoring method and system for offshore ship Download PDFInfo
- Publication number
- CN113158718A CN113158718A CN202011347720.7A CN202011347720A CN113158718A CN 113158718 A CN113158718 A CN 113158718A CN 202011347720 A CN202011347720 A CN 202011347720A CN 113158718 A CN113158718 A CN 113158718A
- Authority
- CN
- China
- Prior art keywords
- sea ice
- sea
- information
- remote sensing
- data
- 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.)
- Pending
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 89
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000012216 screening Methods 0.000 claims abstract description 58
- 230000003595 spectral effect Effects 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 16
- 230000015572 biosynthetic process Effects 0.000 claims abstract description 13
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 13
- 238000003786 synthesis reaction Methods 0.000 claims abstract description 13
- 230000003993 interaction Effects 0.000 claims abstract description 8
- 238000000605 extraction Methods 0.000 claims description 26
- 238000007781 pre-processing Methods 0.000 claims description 19
- 238000007726 management method Methods 0.000 claims description 13
- 238000012937 correction Methods 0.000 claims description 10
- 230000003287 optical effect Effects 0.000 claims description 10
- 230000010287 polarization Effects 0.000 claims description 10
- 238000001228 spectrum Methods 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 6
- 238000003709 image segmentation Methods 0.000 claims description 6
- 230000008520 organization Effects 0.000 claims description 6
- 230000005855 radiation Effects 0.000 claims description 5
- 238000003860 storage Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Chemical compound O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 199
- 230000006870 function Effects 0.000 description 6
- 239000013535 sea water Substances 0.000 description 6
- 238000012360 testing method Methods 0.000 description 5
- 230000003746 surface roughness Effects 0.000 description 4
- 238000005259 measurement Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000007 visual effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000000149 penetrating effect Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 239000005457 ice water Substances 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Images
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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/08—Feature extraction
- G06F2218/10—Feature extraction by analysing the shape of a waveform, e.g. extracting parameters relating to peaks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10032—Satellite or aerial image; Remote sensing
- G06T2207/10044—Radar image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30181—Earth observation
- G06T2207/30184—Infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Remote Sensing (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Astronomy & Astrophysics (AREA)
- Electromagnetism (AREA)
- Computer Networks & Wireless Communication (AREA)
- Radar Systems Or Details Thereof (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a sea ice monitoring method and a sea ice monitoring system for a marine vessel, wherein the method comprises the steps of firstly, acquiring remote sensing data according to the application requirement of sea ice monitoring; then, aiming at the sea ice target, a polarized SAR image feature decomposition and synthesis algorithm aiming at the sea ice information is formulated according to the scattering characteristic and the spectral characteristic of the obtained remote sensing data, and feature enhancement is realized to generate a remote sensing image and auxiliary data; then, pre-screening the sea ice area by the generated remote sensing image and auxiliary data by adopting an automatic identification method aiming at the sea ice information; and then, finely screening and interpreting the pre-screened sea ice area by a man-machine interaction tool, realizing the detailed plotting, size and area calculation of the sea ice, obtaining a sea ice monitoring result, realizing the monitoring of the sea ice in the key sea area in winter, and providing safety early warning for the port entering and exiting and normal navigation of the ship.
Description
Technical Field
The invention relates to the technical field of marine vessel remote sensing monitoring, in particular to a marine vessel sea ice monitoring method and a marine vessel sea ice monitoring system.
Background
About 3-4% of the world ocean is covered by sea ice, so that on one hand, the sea ice has important influence on global climate, heat balance and water balance; on the other hand, the sea ice forms serious obstacles to ship navigation, submarine mining, polar region ocean investigation and the like, and even causes extra-large disasters, so that the sea ice is closely monitored in all countries.
The sea ice in the northern sea area of China can cause serious influence and potential safety hazard to ship navigation in winter, the sea ice often appears in the near-shore sea area of the Bohai sea and the northern part of the yellow sea of China in winter, because the weather conditions are different in winter every year, the sea ice disaster situations appearing in each year have great difference, when the ice situation is serious, coastal ports and navigation channels of the Bohai sea and the northern part of the yellow sea can be blocked by the firm ice, the sea surface is covered by thick ice, so that ships block ice, the navigation is forced to be interrupted, the offshore production is forced to be stopped, and marine engineering facilities are damaged. In 2009 in winter, the most serious sea ice disasters appear in Bohai sea and yellow sea for 30 years, according to incomplete statistics of oceans and fishery halls in Shandong province, only direct economic loss of fishery in Shandong province exceeds 22 hundred million yuan, and disaster fishermen lose disasters, so that sea ice in key sea areas in cold weather in winter needs to be monitored, and countermeasures are taken in time.
At present, the method for monitoring sea ice commonly used in the industry is a telemetry method, which is an advanced method established by applying modern scientific technology. The method can completely depend on an instrument to observe, such as timely, synchronous and large-range observation of sea ice by utilizing satellite remote sensing energy, the microwave remote sensing data has strong penetrability and plays an important role in sea ice monitoring, the sea ice monitoring utilizes the characteristics of all-time, all-weather, multiband, multi-polarization working modes, variable measurement visual angles, strong penetrability and the like of a microwave remote sensing satellite data SAR, and an SAR image contains rich earth surface texture structure information. And the SAR is an active microwave sensor, and has the characteristics of all-time, all-weather, multi-band, multi-polarization working mode, variable measurement visual angle, strong penetrating capability and the like, so that SAR data plays a significant role in sea ice monitoring and forecasting.
At present, sea ice classification methods based on SAR images are classified and identified according to the presenting characteristics of the sea ice on the SAR images at a certain moment, and preprocessing is carried out. However, the traditional preprocessing work is not directed at the sea ice target, the scattering characteristic and the spectral characteristic of the sea ice target are not analyzed, the characteristics of the sea ice target are enhanced in a targeted manner, and the sea ice target cannot assist in accurately identifying sea ice information.
Disclosure of Invention
In order to solve the problems in sea ice monitoring in the prior art, the invention provides a sea ice monitoring method for a marine ship, which is characterized in that the microwave remote sensing satellite data SAR is combined with two-stage screening of automatic screening and fine screening to extract and classify fine information of sea ice, the sea ice monitoring efficiency is improved, the sea ice in key sea areas in winter can be monitored, and safety early warning is provided for the entering and exiting port and normal navigation of the ship.
The technical scheme of the invention is as follows:
a sea ice monitoring method for a marine vessel is characterized by comprising the following steps:
the first step is as follows: acquiring remote sensing data according to the application requirement of sea ice monitoring;
the second step is as follows: aiming at the sea ice target, a polarized SAR image feature decomposition and synthesis algorithm aiming at sea ice information is formulated according to the scattering characteristic and the spectral characteristic of the obtained remote sensing data, and feature enhancement is realized to generate a remote sensing image and auxiliary data;
the third step: pre-screening the sea ice area by the generated remote sensing image and the auxiliary data by adopting an automatic identification method aiming at the sea ice information;
the fourth step: and performing fine screening and interpretation on the pre-screened sea ice area through a human-computer interaction tool, and realizing detailed plotting, size and area calculation of the sea ice to obtain a sea ice monitoring result.
Preferably, the method further comprises the fifth step of: and feeding back a sea ice monitoring result, early warning the generated navigation obstruction influence and the influence on ships in the near sea area, and feeding back early warning information to a user.
Preferably, the method further comprises a sixth step of: and performing data organization management, storage and archiving on the obtained sea ice monitoring result and related information.
Preferably, the first step is to provide an acquisition demand of the remote sensing data according to an application demand of sea ice monitoring, generate an order demand according to the acquisition demand, and feed back the order demand to the base platform so that the base platform can complete acquisition, downloading and output of the data according to the order demand, thereby acquiring the remote sensing data.
Preferably, in the first step, the acquisition requirement of the remote sensing data is the band selection of the SAR data, the band selection of the optical multispectral data, the observation time selection and/or the polarization mode.
Preferably, the second step is to perform spectrum selection and calculation aiming at the spectral characteristics of the sea ice information on the optical image according to a formulated polarimetric SAR image feature decomposition and synthesis algorithm aiming at the sea ice information, so as to realize feature enhancement on the image and generate a remote sensing image; enhancing the textural features of the sea ice information based on the SAR data parameter extraction result to generate auxiliary data;
and/or the second step further comprises format analysis, geometric correction and radiation correction processing aiming at the sea ice information.
Preferably, the third step is to complete the pre-screening of the sea ice region by using an SAR sea ice image segmentation method, so as to realize the automatic extraction of the sea ice information in a large range.
A sea ice monitoring system for a marine vessel is characterized by comprising a data acquisition module, a sea ice information preprocessing module, a sea ice region pre-screening module and a sea ice region fine-screening module which are sequentially connected,
the data acquisition module acquires remote sensing data according to the application requirement of sea ice monitoring;
the sea ice information preprocessing module is used for formulating a polarized SAR image feature decomposition and synthesis algorithm aiming at sea ice information according to the scattering characteristic and the spectral characteristic of the obtained remote sensing data aiming at a sea ice target, and realizing feature enhancement to generate a remote sensing image and auxiliary data;
the sea ice area pre-screening module is used for pre-screening the sea ice area by aiming at the sea ice information through an automatic identification method according to the generated remote sensing image and the auxiliary data, so that the automatic extraction of the sea ice information in a large range is realized;
the sea ice area fine screening module provides a man-machine interaction tool for screening and interpreting the pre-screened sea ice area, so that detailed plotting, size and area calculation of the sea ice are realized, and a sea ice monitoring result is obtained.
Preferably, the system also comprises a sea ice monitoring result feedback and early warning module, wherein the sea ice monitoring result feedback and early warning module feeds back a sea ice monitoring result, gives an early warning to the generated navigation obstruction influence and the influence on ships in the nearby sea area, and feeds back early warning information to users;
and/or the system further comprises a filing management module, wherein the filing management module is used for carrying out data organization management, storage and filing on the obtained sea ice monitoring result and related information.
Preferably, the sea ice information preprocessing module performs spectrum selection and calculation aiming at the spectral characteristics of the sea ice information on the optical image according to a formulated polarization SAR image feature decomposition and synthesis algorithm aiming at the sea ice information, so as to realize feature enhancement on the image and generate a remote sensing image; enhancing the textural features of the sea ice information based on the SAR data parameter extraction result to generate auxiliary data;
and/or the sea ice region pre-screening module completes the pre-screening of the sea ice region by utilizing an SAR sea ice image segmentation method, and realizes the automatic extraction of the sea ice information in a large range.
The invention has the following technical effects:
the invention relates to a sea ice monitoring method for a marine vessel, which utilizes satellite remote sensing to monitor sea ice, and a polarization SAR image feature decomposition and synthesis algorithm for sea ice information is formulated according to the scattering property and the spectral property of the obtained remote sensing data aiming at a sea ice target to realize feature enhancement so as to generate a remote sensing image and auxiliary data. The sea ice monitoring utilizes the characteristics of all-weather, multi-band, multi-polarization working mode, variable measurement visual angle, strong penetrating power and the like of microwave remote sensing satellite data SAR, and the SAR image contains rich surface texture structure information. The sea ice has stronger echo capability to the microwave radar than that of the sea water, brighter color tone than that of the surrounding sea water and higher contrast ratio of the sea ice and the surrounding sea water, so that the relevant information of the sea ice area can be extracted from the SAR image. The second step is to preprocess sea ice data, and the main function is to provide image data of various formats required by the sea ice monitoring system, thereby improving the compatibility of the system. The method can carry out preprocessing processes such as system geometric correction, radiation correction, speckle noise filtration and the like on remote sensing data, and prepares for sea ice identification, and the steps are different from conventional preprocessing; enhancing the textural features of the sea ice information based on the SAR data parameter extraction result; and performing spectrum selection and calculation aiming at sea ice information spectral characteristics on the optical image to realize the characteristic enhancement of the image. And then, the third step and the fourth step are combined to sequentially carry out pre-screening and further fine screening on the sea ice area, and the automatic screening and the fine screening, namely the two-stage screening, are more targeted, so that the accuracy of sea ice information monitoring is improved. The electromagnetic wave characteristics of sea water and sea ice are greatly different, so that the propagation of radar waves in the sea ice and the sea water is obviously different, a strong radar transmitting layer is formed on an ice-water contact surface, the sea ice part shows rich echo phenomena on radar images, and the sea water part shows strong attenuation and absorption phenomena. Therefore, the information extraction of the sea ice can be realized by utilizing the different scattering characteristics of the sea ice on the SAR image. The invention can realize the automatic extraction of the information of the sea ice resource by utilizing the remote sensing images (mainly SAR data) of different types of sensors, simultaneously provides the manual auxiliary function and realizes the fine information extraction and classification of the sea ice. Because sea ice classification mainly depends on surface roughness characteristics (such as surface roughness, dielectric constant of sea ice, radar beam direction and the like) in a small range, the sea ice classification also utilizes SAR data polarization information, texture characteristics and the like to assist the identification of sea ice information, can monitor the sea ice in key sea areas in winter, and provides safety early warning for port entry and exit and normal navigation of ships.
The invention relates to a sea vessel sea ice monitoring system, which corresponds to the sea vessel sea ice monitoring method and can be understood as a system for realizing the sea vessel sea ice monitoring method, and comprises a data acquisition module, a sea ice information preprocessing module, a sea ice region pre-screening module, a sea ice region fine-screening module, a further sea ice monitoring result feedback and early warning module and a filing management module which are sequentially connected, wherein the modules work in a mutual cooperation manner, the sea ice region pre-screening module realizes the pre-screening of the sea ice region by using an automatic identification method to realize the automatic extraction of the sea ice information in a large range, the sea ice region fine-screening module provides a human-computer interaction tool to further screen and interpret the sea ice region, a plotting and calculating tool is provided to realize the functions of detailed plotting, size and area calculation of the sea ice, and acquiring fine information of sea ice coverage to obtain a sea ice monitoring result. The sea ice monitoring result feedback and early warning module feeds back the monitoring result, early warning is carried out on the possible navigation obstruction influence and the influence on ships close to the sea area, and early warning information is fed back to a user. The system provided by the invention realizes automatic extraction of information of sea ice resources by utilizing different types of sensor remote sensing images (mainly SAR data), and simultaneously provides an artificial assistance function, and the microwave remote sensing satellite data SAR combines two-stage screening of automatic screening and fine screening, so that fine information extraction and classification of sea ice are realized, and the sea ice monitoring efficiency is improved.
Drawings
FIG. 1 is a flow chart of the marine vessel sea ice monitoring method of the present invention.
FIG. 2 is a preferred flow chart of the marine vessel sea ice monitoring method of the present invention.
Fig. 3 is a diagram of a deep cooperative sparse coding network structure.
FIG. 4 is another preferred flow chart of the marine vessel sea ice monitoring method of the present invention.
FIG. 5 is a block diagram of a preferred configuration of the marine vessel sea ice monitoring system of the present invention.
Detailed Description
The present invention will be described with reference to the accompanying drawings.
The invention relates to a sea ice monitoring method for a marine vessel, which has a flow chart shown in figure 1 and sequentially comprises the following steps:
the first step is as follows: acquiring remote sensing data (microwave remote sensing data) according to the application requirement of sea ice monitoring; the specific steps are as shown in an optimal flow chart shown in fig. 2, firstly, task planning is carried out on data, the acquisition requirement of remote sensing data (namely, data acquisition task planning, such as the wave band of SAR data, the wave band selection of optical multispectral data, the polarization mode and the observation time selection) is provided according to the application requirement of sea ice monitoring, the order requirement is generated according to the acquisition requirement, the order requirement is fed back to a basic platform through an external interface, and the basic platform finishes the work of data acquisition, data downloading, remote sensing data output and the like according to the order requirement.
The second step is as follows: aiming at the sea ice target, a polarized SAR image feature decomposition and synthesis algorithm aiming at sea ice information is formulated according to the scattering characteristic and the spectral characteristic of the obtained remote sensing data, and feature enhancement is realized to generate a remote sensing image and auxiliary data; the step is a unique sea ice information preprocessing step, and specifically comprises the preferred flow chart shown in figure 2, the inputted remote sensing data is subjected to preprocessing work of SAR data format analysis, geometric and radiation correction, image feature enhancement and data parameter extraction aiming at the sea ice, the preprocessing work mainly provides required image data in various formats for sea ice monitoring, the compatibility of a system is improved, the remote sensing data is subjected to preprocessing processes of system geometric correction, radiation correction, speckle noise filtration and the like, and preparation is made for sea ice identification, the specific preprocessing work of the invention aims at a sea ice target, an SAR image polarization feature decomposition and synthesis algorithm aiming at the sea ice information is formulated on the basis of analyzing the scattering characteristic and the spectral characteristic of the sea ice target, the characteristic enhancement is realized, the characteristic enhancement mainly comprises texture feature enhancement and image feature enhancement, and preferably, the texture feature of the SAR ice information is enhanced based on the result of the data parameter extraction, and spectrum selection and calculation aiming at sea ice information spectral characteristics are carried out on the optical image, so that the characteristic enhancement of the image is realized, and a remote sensing image and auxiliary data are further formed. Further, feature optimization can be performed and data parameters can be extracted based on the deep cooperative sparse coding network, as shown in fig. 3, the deep cooperative sparse coding network not only can effectively optimize a neighbor pixel feature group to improve recognition accuracy, but also can effectively inhibit the influence of speckle noise of the SAR image. The deep collaborative sparse coding network is high in calculation efficiency, has excellent feature representation capability, particularly shows better efficiency when the image size is large, effectively inhibits the influence of speckle noise, improves the SAR image target identification precision by realizing feature optimization on the image and extracting data parameters, and outputs an identification result.
The third step: pre-screening the sea ice area by the generated remote sensing image and the auxiliary data by adopting an automatic identification method aiming at the sea ice information; that is to say, the preprocessed remote sensing image and the related auxiliary data are firstly pre-screened for the sea ice range by using an automatic identification method (for example, a specific algorithm based on polarization information, scattering information and the like of the SAR image), and preferably, the pre-screening for the sea ice region is completed by using an SAR sea ice image segmentation method, so that the automatic extraction of the sea ice information in a large range is realized.
The fourth step: fine screening and interpretation are carried out on the pre-screened sea ice area through a human-computer interaction tool, so that detailed plotting, size and area calculation of the sea ice are realized, and a sea ice monitoring result is obtained; that is, after the previous pre-screening is completed, the sea ice is finely screened to obtain the fine information covered by the sea ice, and the sea ice monitoring result is obtained.
The fifth step: as shown in fig. 2, the sea ice monitoring result is fed back, the influence on the ship in the sea area and the influence on the ship in the near sea area, which may be caused by the sea ice monitoring result, are pre-warned, and the pre-warning information is fed back to the user. The release of sea ice monitoring information is realized, the sea ice monitoring information is released to a command center, and the command center provides safety early warning information service for the ship entering and exiting port and normal navigation.
A sixth step: as shown in fig. 2, the generated monitoring results and some related information are subjected to data organization management and archiving.
Another embodiment of the sea ice monitoring method for the marine vessel according to the present invention is shown in fig. 4, which focuses on a sea ice target information extraction flowchart based on deep learning, and the sea ice data preprocessing is to extract texture features and structural features, analyze the format of the extracted texture features and structural features, perform geometric correction by setting training samples and test samples, complete image enhancement (not shown in the figure), perform feature optimization based on a depth-collaborative sparse coding network, and extract data parameters. Then sea ice area pre-screening and fine screening are carried out, namely joint sparse representation is carried out as shown in the figure, training samples are taken as dictionaries, sparse representation of all test samples on the dictionaries is solved, and preliminary screening of the test samples is completed; and calculating residual errors on each sub-dictionary after the test samples are sparsely reconstructed, judging category labels, completing detailed screening of the test samples, and performing morphological smoothing processing and output on the recognition results to complete the whole process.
The invention also relates to a marine vessel sea ice monitoring system, which corresponds to the marine vessel sea ice monitoring method and can be understood as a system for realizing the method, and the preferred structure of the system is shown in fig. 5 and comprises a data acquisition module, a sea ice information preprocessing module, a sea ice region pre-screening module, a sea ice region fine-screening module, a sea ice monitoring result feedback and early warning module and a filing management module which are sequentially connected. The data acquisition module is used for acquiring remote sensing data according to the application requirements of sea ice monitoring; the sea ice information preprocessing module is used for formulating a polarization SAR image feature decomposition and synthesis algorithm aiming at sea ice information according to the scattering characteristic and the spectral characteristic of the obtained remote sensing data aiming at a sea ice target, realizing feature enhancement to generate a remote sensing image and auxiliary data, specifically, carrying out spectrum selection and calculation aiming at the spectral characteristic of the sea ice information on an optical image, realizing feature enhancement to the image to generate the remote sensing image, and enhancing the texture feature of the sea ice information to generate the auxiliary data based on the SAR data parameter extraction result; the sea ice area pre-screening module pre-screens the generated remote sensing image and the auxiliary data aiming at the sea ice information by using an automatic identification method to realize the pre-screening of the sea ice area and realize the automatic extraction of the sea ice information in a large range, preferably, the sea ice area pre-screening can be realized by using an SAR sea ice image segmentation method to realize the automatic extraction of the sea ice information in the large range; the sea ice area fine screening module provides a human-computer interaction tool for further screening and interpreting the pre-screened sea ice area, provides a plotting and calculating tool, realizes the functions of detailed plotting, size and area calculation of the sea ice, acquires fine information covered by the sea ice and obtains a sea ice monitoring result; the sea ice monitoring result feedback and early warning module feeds back a sea ice monitoring result, early warning is carried out on the generated navigation obstruction influence and the influence on ships near the sea area, and early warning information is fed back to a user, the sea ice monitoring information can be issued to a command center, and the command center provides safety early warning information service for the port entering and exiting and normal navigation of the ships; and the filing management module is used for carrying out data organization management, storage and filing on the obtained sea ice monitoring result and related information.
The system provided by the invention realizes automatic extraction of information of sea ice resources by using different types of sensor remote sensing images (mainly SAR data), provides an artificial auxiliary function, and also realizes fine information extraction and classification of sea ice by using SAR data polarization information, texture characteristics and the like to assist identification of sea ice information in the system as the sea ice classification mainly depends on surface roughness characteristics (such as surface roughness, dielectric constant of sea ice, radar beam direction and the like) in a small range, and the microwave remote sensing satellite data SAR combines two-stage screening of automatic screening and fine screening, thereby improving the sea ice monitoring efficiency.
It should be noted that the above-mentioned embodiments enable a person skilled in the art to more fully understand the invention, without restricting it in any way. Therefore, although the present invention has been described in detail with reference to the drawings and examples, it will be understood by those skilled in the art that various changes and modifications can be made therein without departing from the spirit and scope of the invention.
Claims (10)
1. A sea ice monitoring method for a marine vessel is characterized by comprising the following steps:
the first step is as follows: acquiring remote sensing data according to the application requirement of sea ice monitoring;
the second step is as follows: aiming at the sea ice target, a polarized SAR image feature decomposition and synthesis algorithm aiming at sea ice information is formulated according to the scattering characteristic and the spectral characteristic of the obtained remote sensing data, and feature enhancement is realized to generate a remote sensing image and auxiliary data;
the third step: pre-screening the sea ice area by the generated remote sensing image and the auxiliary data by adopting an automatic identification method aiming at the sea ice information;
the fourth step: and performing fine screening and interpretation on the pre-screened sea ice area through a human-computer interaction tool, and realizing detailed plotting, size and area calculation of the sea ice to obtain a sea ice monitoring result.
2. The marine vessel sea ice monitoring method of claim 1, further comprising a fifth step of: and feeding back a sea ice monitoring result, early warning the generated navigation obstruction influence and the influence on ships in the near sea area, and feeding back early warning information to a user.
3. A marine vessel sea ice monitoring method according to claim 2, further comprising a sixth step of: and performing data organization management, storage and archiving on the obtained sea ice monitoring result and related information.
4. The marine vessel sea ice monitoring method of one of claims 1 to 3, wherein the first step is to provide a demand for obtaining remote sensing data according to an application demand of sea ice monitoring, generate an order demand according to the demand for obtaining, and feed back the order demand to a base platform so that the base platform can complete data obtaining, downloading and outputting according to the order demand, thereby obtaining the remote sensing data.
5. The marine vessel sea ice monitoring method of claim 4, wherein in the first step the acquisition requirements of the remote sensing data are SAR data band selection, optical multi-spectral data band selection, observation time selection and/or polarization mode.
6. The marine vessel sea ice monitoring method of one of claims 1 to 3, wherein the second step is to perform spectrum selection and calculation aiming at sea ice information spectrum characteristics on the optical image according to a formulated polarized SAR image feature decomposition and synthesis algorithm aiming at sea ice information, so as to realize feature enhancement on the image to generate a remote sensing image; enhancing the textural features of the sea ice information based on the SAR data parameter extraction result to generate auxiliary data;
and/or the second step further comprises format analysis, geometric correction and radiation correction processing aiming at the sea ice information.
7. The sea vessel sea ice monitoring method of one of claims 1 to 3, wherein the third step is to perform pre-screening on the sea ice region by using an SAR sea ice image segmentation method, so as to realize automatic extraction of information on a large range of sea ice.
8. A sea ice monitoring system for a marine vessel is characterized by comprising a data acquisition module, a sea ice information preprocessing module, a sea ice region pre-screening module and a sea ice region fine-screening module which are sequentially connected,
the data acquisition module acquires remote sensing data according to the application requirement of sea ice monitoring;
the sea ice information preprocessing module is used for formulating a polarized SAR image feature decomposition and synthesis algorithm aiming at sea ice information according to the scattering characteristic and the spectral characteristic of the obtained remote sensing data aiming at a sea ice target, and realizing feature enhancement to generate a remote sensing image and auxiliary data;
the sea ice area pre-screening module is used for pre-screening the sea ice area by aiming at the sea ice information through an automatic identification method according to the generated remote sensing image and the auxiliary data, so that the automatic extraction of the sea ice information in a large range is realized;
the sea ice area fine screening module provides a man-machine interaction tool for screening and interpreting the pre-screened sea ice area, so that detailed plotting, size and area calculation of the sea ice are realized, and a sea ice monitoring result is obtained.
9. The marine vessel sea ice monitoring system of claim 8, further comprising a sea ice monitoring result feedback and early warning module, wherein the sea ice monitoring result feedback and early warning module feeds back a sea ice monitoring result, gives an early warning to the produced navigation obstruction effect and the effect on ships in the nearby sea area, and feeds back early warning information to a user;
and/or the system further comprises a filing management module, wherein the filing management module is used for carrying out data organization management, storage and filing on the obtained sea ice monitoring result and related information.
10. The marine vessel sea ice monitoring system of claim 8 or 9, wherein the sea ice information preprocessing module performs spectral selection and calculation for sea ice information spectral characteristics on the optical image according to a formulated polarized SAR image feature decomposition and synthesis algorithm for sea ice information, so as to realize feature enhancement on the image to generate a remote sensing image; enhancing the textural features of the sea ice information based on the SAR data parameter extraction result to generate auxiliary data;
and/or the sea ice region pre-screening module completes the pre-screening of the sea ice region by utilizing an SAR sea ice image segmentation method, and realizes the automatic extraction of the sea ice information in a large range.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011347720.7A CN113158718A (en) | 2020-11-26 | 2020-11-26 | Sea ice monitoring method and system for offshore ship |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011347720.7A CN113158718A (en) | 2020-11-26 | 2020-11-26 | Sea ice monitoring method and system for offshore ship |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113158718A true CN113158718A (en) | 2021-07-23 |
Family
ID=76882573
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011347720.7A Pending CN113158718A (en) | 2020-11-26 | 2020-11-26 | Sea ice monitoring method and system for offshore ship |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113158718A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114548187A (en) * | 2022-03-16 | 2022-05-27 | 东北大学秦皇岛分校 | Sea ice type identification method based on ship ice-induced vibration |
| CN115792898A (en) * | 2022-12-09 | 2023-03-14 | 中船重工鹏力（南京）大气海洋信息系统有限公司 | Floating ice detection method based on X-band target monitoring radar |
-
2020
- 2020-11-26 CN CN202011347720.7A patent/CN113158718A/en active Pending
Non-Patent Citations (2)
| Title |
|---|
| 周晓虎: "基于多源遥感数据的中国东北地区森林信息提取研究", 中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑, no. 08, 15 August 2020 (2020-08-15), pages 5 - 58 * |
| 徐雯佳等: "河北省卫星遥感海冰业务化监测系统建设及应用现状", 河北省卫星遥感海冰业务化监测系统建设及应用现状, no. 06, 25 June 2018 (2018-06-25), pages 52 - 56 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114548187A (en) * | 2022-03-16 | 2022-05-27 | 东北大学秦皇岛分校 | Sea ice type identification method based on ship ice-induced vibration |
| CN115792898A (en) * | 2022-12-09 | 2023-03-14 | 中船重工鹏力（南京）大气海洋信息系统有限公司 | Floating ice detection method based on X-band target monitoring radar |
| CN115792898B (en) * | 2022-12-09 | 2023-11-28 | 中船鹏力(南京)大气海洋信息系统有限公司 | Floating ice detection method based on X-band target monitoring radar |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109636742B (en) | Mode conversion method of SAR image and visible light image based on countermeasure generation network | |
| CN100547438C (en) | A kind of oil-gas exploration method and system | |
| Brown et al. | Multiple methods, maps, and management applications: Purpose made seafloor maps in support of ocean management | |
| CN109447089B (en) | High-resolution arctic sea ice type extraction method based on super-resolution technology | |
| CN111781146B (en) | Wave parameter inversion method using high-resolution satellite optical image | |
| CN113158718A (en) | Sea ice monitoring method and system for offshore ship | |
| CN109635765B (en) | Automatic extraction method for remote sensing information of shallow sea coral reef | |
| CN110703244B (en) | Method and device for identifying urban water body based on remote sensing data | |
| CN113538559B (en) | Extraction method of offshore aquaculture raft extraction index based on hyperspectral remote sensing image | |
| CN107239755A (en) | Offshore oil and gas platform extraction system based on high score satellite remote sensing date | |
| CN109211798A (en) | A kind of annual sea ice distributed intelligence extracting method based on remote sensing image spectral signature | |
| CN114119630B (en) | Coastline deep learning remote sensing extraction method based on coupling map features | |
| CN112651977A (en) | Method and system for monitoring marine ship fishery breeding | |
| CN112989940B (en) | Raft culture area extraction method based on high-resolution third satellite SAR image | |
| CN115018285A (en) | Storm surge and sea wave fine early warning system and early warning method | |
| Ma et al. | Automatic geolocation and measuring of offshore energy infrastructure with multimodal satellite data | |
| CN112946643B (en) | Offshore wind power extraction method and system based on time sequence radar remote sensing | |
| Wei et al. | Texture feature analysis in oil spill monitoring by SAR image | |
| Fan et al. | Marine floating raft aquaculture dynamic monitoring based on multi-source GF imagery | |
| CN117111063A (en) | Polarized SAR image feature extraction method | |
| CN116385593A (en) | Hyperspectral remote sensing mineral mapping method based on quantitative semi-supervised learning | |
| CN112329675B (en) | Polarization SAR data identification collapse construction method based on Fourier transform | |
| CN115631405A (en) | SegFormer-based SAR image ocean inner wave stripe segmentation method | |
| Aanstoos et al. | Earthen levee monitoring with synthetic aperture radar | |
| He et al. | Notice of Retraction: Multi-Source Data Fusion Technology and Its Application in Geological and Mineral Survey |
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 |