A method and system for all-weather monitoring of port congestion using synthetic aperture radar

Abstract

The present invention relates to a method and system for all-weather monitoring of port congestion using synthetic aperture radar. The measurement method includes: constructing a synthetic aperture radar image database; vertically polarizing the time-series original synthetic aperture radar image data of each container terminal in the target port, and obtaining the time-series polarized synthetic aperture radar image data of each container terminal in the target port; using a threshold method to identify container pixels in the time-series polarized synthetic aperture radar image data of each container terminal in the target port; using the ratio of container pixels to total terminal pixels as a congestion monitoring indicator of the target port, and measuring the congestion of the target port. Compared with the prior art, the present invention has the following significant advantages: compared with optical satellite images, it can eliminate the interference of clouds, realize all-weather monitoring, and accurately and comprehensively evaluate and predict the future trend of freight rate index changes.

Description

Technical Field

[0001] The invention relates to the field of space information technology, in particular to a method and a system for all-weather monitoring of port congestion using synthetic aperture radar. Background Art

[0002] With the rapid development of global container trade, port congestion is becoming increasingly serious. Port congestion not only prolongs the waiting time for ships, but also may cause significant losses to multiple stakeholders in the shipping supply chain, such as shipping companies, cargo owners and ports. The level of port congestion has become an important indicator for measuring port performance, and has a direct impact on the competitiveness and attractiveness of liner companies, cargo owners and ports.

[0003] At present, there are very limited methods for monitoring the level of port congestion. Some methods use the data of the Automatic Identification System (AIS) of ships to propose indicators to measure the congestion of ports, but this method and this indicator cannot accurately identify the container stacking situation at the port terminal, which limits the expansion of its application. With the rapid development of satellite technology, some methods use optical satellite images to monitor port congestion. However, optical satellite images are easily interfered by clouds. According to research data published by the International Satellite Cloud Climatology Program (ISCCP), more than 60% of the earth's surface is covered by clouds on average each year, resulting in widespread clouds on optical remote sensing images. The cloud problem limits the application of optical satellites in continuous monitoring of port congestion. Synthetic aperture radar (SAR) is not limited by light and climate conditions, and can achieve all-day and all-weather earth observation, which effectively makes up for the shortcomings of optical satellite earth observation. Therefore, it has become an urgent problem to develop new port congestion monitoring technologies based on synthetic aperture radar (SAR) to achieve all-weather monitoring of port congestion. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for all-weather monitoring of port container terminal congestion using synthetic aperture radar (SAR). First, the original data of synthetic aperture radar is obtained and polarized; second, the high conductivity of metal is used, and containers usually appear as bright reflective targets on SAR images. The threshold method is used to identify container pixels in satellite images to construct an all-weather port congestion index; finally, the constructed port congestion index is analyzed with the container freight index for historical changes to achieve effective prediction of future changes in the freight index.

[0005] The technical solution to achieve the purpose of the present invention is:

[0006] In a first aspect, a method for all-weather monitoring of port congestion using synthetic aperture radar is provided, wherein the method comprises the following steps:

[0007] Constructing a synthetic aperture radar image database, which includes the regional boundary contour vector data of the target port, the regional boundary contour vector data of each container terminal in the target port, and the time-series original synthetic aperture radar image data of the location of the target port;

[0008] Perform vertical polarization and normalization processing on the time-series raw synthetic aperture radar image data of the target port location;

[0009] Combine the regional boundary contour vector data of the target port and the regional boundary contour vector data of each container terminal in the target port, perform vector cutting on the normalized processing result, and obtain the time-series polarization synthetic aperture radar image data of each container terminal in the target port;

[0010] The threshold method is used to identify container pixels in the time-series polarimetric synthetic aperture radar image data of each container terminal in the target port.

[0011] The ratio of container pixels to total dock pixels is used as the congestion monitoring indicator of the target port to measure the congestion condition of the target port.

[0012] As a further optimization solution: when the congestion monitoring index of the target port exceeds the preset congestion determination threshold, the current congestion of the target port is determined.

[0013] As a further optimization scheme: the regional boundary contour vector data of the target port includes the latitude and longitude values ​​of the target port, the number of container terminals in the target port, the latitude and longitude values ​​of each container terminal in the target port, and the regional area of ​​each container terminal.

[0014] As a further optimization scheme: the calculation formula of the congestion monitoring index of the target port is:

[0015] ,

[0016] Where: R t Represents the target port in t The congestion rate at the time, N Represents the number of container terminals in the target port, C n,t Representing container terminals n exist t The number of container pixels at the time, A n Representing container terminals n The total number of pixels.

[0017] As a further optimization scheme: the method of using the threshold method to identify container pixels in the time-series polarization synthetic aperture radar image data of each container terminal in the target port includes:

[0018] Step 1: Obtain optical cloud-free satellite image data that is contemporaneous with the time-series polarimetric synthetic aperture radar image data of each container terminal in the target port, and manually annotate the container pixels in the optical cloud-free satellite image data of the same period;

[0019] Step 2: Traverse the time-series polarization synthetic aperture radar image data set of the container terminal in the target port Q , statistics show Q The minimum pixel value of all the time-series polarized synthetic aperture radar image data m and maximum value M ,by As the initial threshold, Q Identify container pixels in all time-series polarized synthetic aperture radar image data:

[0020] When the pixel in the synthetic aperture radar image data after time series polarization i The pixel value P i >K l When i Identify it as a container pixel, otherwise the pixel i Identified as non-container pixels; among them, l Represents the number of iterations;

[0021] Step 3: Based on the recognition results of step 2, calculate Q The ratio of the number of container pixels to the total number of pixels in all the time-series polarized synthetic aperture radar image data is obtained to obtain the radar container pixel ratio set { B q l} q∈Q ;in, B q l express Q Medium time series polarimetric synthetic aperture radar image data q The ratio of the number of container pixels to the total number of pixels;

[0022] Step 4: Calculate the optical cloud-free satellite image data set for the same period R The ratio of the number of container pixels to the total number of pixels in each optical cloud-free satellite image data is used to obtain the optical container pixel ratio set { β r} r∈R ;in, βr express R China Optical Cloud-free Satellite Image Data r The ratio of the number of container pixels to the total number of pixels;

[0023] Step 5: Calculate { B q l} q∈Q and{ β r} r∈R Pearson correlation coefficient P l ；

[0024] Step 6: Order l = l +1, return to step 2 and recalculate K l , and recalculate the Pearson correlation coefficient P l , until l Reaching the set maximum value L , get the correlation coefficient set { P l} l∈[1,L] ;

[0025] Step 7: Select { P l} l∈[1,L] The maximum value corresponding to l The value is the optimal value l * ,by As the optimal threshold, the container pixels in the time-series polarimetric synthetic aperture radar image data of each container terminal in the selected target port are identified.

[0026] As a further optimization: B q l = C q l / A q ,in, C q l express Q Medium time series polarimetric synthetic aperture radar image data q By threshold K l The number of container pixels identified, A q Represents the time series polarization synthetic aperture radar image data q The total number of pixels.

[0027] As a further optimization: β r = C r / A r ,in, C r express R China Optical Cloud-free Satellite Image Data r The number of manually labeled container pixels, A r Represents optical cloud-free satellite image data r The total number of pixels.

[0028] In a second aspect, a system for monitoring port congestion around the clock using synthetic aperture radar is provided, the system comprising:

[0029] A database construction module is used to construct a synthetic aperture radar image database, wherein the image database includes regional boundary contour vector data of the target port, regional boundary contour vector data of each container terminal in the target port, time-series original synthetic aperture radar image data of the location of the target port, and time-series original synthetic aperture radar image data of each container terminal in the target port;

[0030] An image processing module is used to vertically polarize the time-series original synthetic aperture radar image data of each container terminal in the target port, and obtain the time-series polarized synthetic aperture radar image data of each container terminal in the target port;

[0031] A pixel recognition module is used to recognize container pixels in the time-series polarization synthetic aperture radar image data of each container terminal in the target port by using a threshold method;

[0032] The measurement and evaluation module is used to measure the congestion situation of the target port by taking the ratio of container pixels to the total pixels of the terminal as the congestion monitoring indicator of the target port.

[0033] In the third aspect, a method for predicting a freight rate index using a port congestion index is provided. The prediction method uses a vector autoregression model (VAR) to predict a future freight rate index using historical port congestion indicators and historical freight rate indices. The method includes the following steps:

[0034] Step 1: Port congestion indicators R t Freight Index P t Difference, obtain the difference series of port congestion index and freight rate index ΔR t and ΔP t .

[0035] Step 2: Use the vector autoregression model (VAR) to fit the port congestion index and freight rate index after differentiation. The fitting equation used is:

[0036] ,

[0037] in, ΔP t-k and ΔR t-k are the freight rate index and port congestion index with a lag of k periods, ε t is the error term, K is the maximum lag order, c is the constant term, and They are the coefficients of the freight rate index and the port congestion index respectively.

[0038] Step 3: Use the Akaike Information Criterion (AIC) to determine the optimal order k of the vector autoregression model (VAR) * .

[0039] Step 4: Use the optimal order k obtained in step 3 * , use the following equation to calculate the change value of the freight rate index in the next period Make predictions:

[0040] ,

[0041] Step 5: Calculate the forecast value of the freight rate index for the next period .

[0042] In a fourth aspect, an electronic device is provided, including:

[0043] Memory for storing computer programs;

[0044] A processor is used to implement the steps of the method described above when executing the computer program.

[0045] According to a fifth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps of the method described above are implemented.

[0046] Compared with the prior art, the present invention has the following significant advantages: the present invention utilizes the advantages of synthetic aperture radar for all-weather monitoring, combines the high conductivity and high reflectivity characteristics of metal containers, and uses the threshold method to achieve all-weather monitoring of port container terminal congestion, thereby being able to continuously construct container terminal congestion indicators. This indicator solves the difficulties of the prior art that it is susceptible to cloud interference, has low recognition accuracy, and cannot be continuously monitored. The port container terminal congestion indicator constructed using synthetic aperture radar can provide strong support for port management and decision-making, and achieve accurate all-weather monitoring of port congestion conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 It is a flowchart of a method in one embodiment of the present invention.

[0048] Figure 2 It is a schematic diagram of the structure of a system in one embodiment of the present invention.

[0049] Figure 3 This is an example of container pixels identified using a threshold method in one embodiment of the present invention.

[0050] Figure 4 yes Figure 3 Examples of optical satellite images from the same period. DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the following will be described clearly and completely in combination with the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are partial embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work belong to the protection scope of the present invention.

[0052] Unless otherwise defined, all technical and scientific terms used in the present invention have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0053] like Figure 1 As shown, the present invention provides a method for all-weather monitoring of port congestion using synthetic aperture radar, the method comprising the following steps:

[0054] S1, constructing a synthetic aperture radar image database, the image database includes the regional boundary contour vector data of the target port, the regional boundary contour vector data of each container terminal in the target port, the time-series original synthetic aperture radar image data of the location of the target port, and the time-series original synthetic aperture radar image data of each container terminal in the target port.

[0055] Specifically, the regional boundary contour vector data of the target port includes the latitude and longitude values ​​of the target port, the number of container terminals in the target port, the latitude and longitude values ​​of each container terminal in the target port, and the regional area of ​​each container terminal.

[0056] Specifically, the time-series original synthetic aperture radar image data of the target port location is obtained, and the regional boundary contour vector data of the target port and the regional boundary contour vector data of each container terminal in the target port are combined to perform vector cutting on the time-series original synthetic aperture radar image data of the target port location to determine the time-series original synthetic aperture radar image data of each container terminal in the target port.

[0057] S2, vertically polarize (VV) the time-series original synthetic aperture radar image data of each container terminal in the target port to obtain the time-series polarized synthetic aperture radar image data of each container terminal in the target port.

[0058] Specifically, vertical polarization (VV) is performed on the time-series raw synthetic aperture radar image data. The microwave signal vibrates in the vertical direction, and the receiver also receives the echo signal in a vertical structure. VV polarization is performed on the time-series raw synthetic aperture radar image data to characterize the vertical component of ground object scattering.

[0059] S3, using the threshold method to identify container pixels in the time-series polarimetric synthetic aperture radar image data of each container terminal in the target port. First, cloud-free optical satellite images of the same period are used as control samples, and containers are manually annotated in the cloud-free optical satellite images. A certain threshold is selected to identify container pixels in polarimetric synthetic aperture radar images, and the correlation between the identified container pixels and manually annotated pixels under different thresholds is evaluated, so as to select the optimal threshold, and then identify the container pixels in the polarimetric time-series synthetic aperture radar images according to the optimal threshold.

[0060] The specific steps are as follows:

[0061] Step 1: Obtain optical cloud-free satellite image data that is contemporaneous with the time-series polarimetric synthetic aperture radar image data of each container terminal in the target port, and manually annotate the container pixels in the optical cloud-free satellite image data of the same period;

[0062] Step 2: Time-series polarimetric synthetic aperture radar image data set of the container terminal in the target port Q , statistics show Q The minimum pixel value of all the time-series polarized synthetic aperture radar image data m and maximum value M ,by As the initial threshold, Q Identify container pixels in all time-series polarized synthetic aperture radar image data:

[0063] When the pixel in the synthetic aperture radar image data after time series polarization i The pixel value P i >K l When i Identify it as a container pixel, otherwise the pixel i Identify as non-container pixel;

[0064] Step 3: Based on the recognition results of step 2, calculate Q The ratio of the number of container pixels to the total number of pixels in all the time-series polarized synthetic aperture radar image data is obtained to obtain the radar container pixel ratio set { B q l} q∈Q ;in, B q l express Q Medium time series polarimetric synthetic aperture radar image data q The ratio of the number of container pixels to the total number of pixels;

[0065] Step 4: Calculate the optical cloud-free satellite image data set for the same period R The ratio of the number of container pixels to the total number of pixels in each optical cloud-free satellite image data is used to obtain the optical container pixel ratio set { β r} r∈R ;in, β r express R China Optical Cloud-free Satellite Image Data r The ratio of container pixels to total pixels

[0066] Step 5: Calculate { B q l} q∈Q and{ β r} r∈R Pearson correlation coefficient Pl ;

[0067] Step 6: Order l = l +1, return to step 2 and recalculate K l , and recalculate the Pearson correlation coefficient P l , until l Reaching the set maximum value L (In this embodiment, set L = 100), and obtain the correlation coefficient set { P l} l∈[1,100] ;

[0068] Step 7: Select { P l} l∈[1,L] The maximum value corresponding to l The value is the optimal value l * ,by As the optimal threshold, the container pixels in the time-series polarization synthetic aperture radar image data of each container terminal in the selected target port are identified. The identification example is as follows: Figure 3 , Figure 4 shown.

[0069] Specifically, Q Medium time series polarimetric synthetic aperture radar image data q The ratio of container pixels to total pixels B q l The expression is as follows:

[0070] ,

[0071] In the formula, C q l express Q Medium time series polarimetric synthetic aperture radar image data q By threshold K l The number of container pixels identified, A q Represents the time series polarization synthetic aperture radar image data q The total number of pixels.

[0072] Specifically, R China Optical Cloud-free Satellite Image Data r The ratio of container pixels to total pixels β r The expression is as follows:

[0073] ,

[0074] In the formula, C r express R China Optical Cloud-free Satellite Image Data r The number of manually labeled container pixels, A r Represents optical cloud-free satellite image data r The total number of pixels.

[0075] S4, taking the ratio of container pixels to total dock pixels as the target port congestion monitoring index, the target port congestion monitoring index is measured. The calculation formula of the target port congestion monitoring index is:

[0076] ,

[0077] Where: R t Represents the target port in t The congestion rate at the time, N Represents the number of container terminals in the target port, C n,t Representing container terminals n exist t The number of container pixels at the time, A n Representing container terminals n The total number of pixels.

[0078] Specifically, after obtaining the congestion index of the target port, the future freight rate index can be predicted in combination with the historical freight rate index. The prediction process is as follows:

[0079] Step 1: Congestion indicators for target ports R t and freight index P t Perform differentiation to obtain the time series of congestion index and freight index differential value ΔR t and ΔP t ， in ΔR t= R t -R t-1 , ΔP t= P t -P t-1 .

[0080] Step 2: Get the target port ΔR t and ΔP t , using the following vector autoregression model (VAR) for fitting:

[0081] ,

[0082] in, ΔP t-k and ΔR t-k are the freight rate index and port congestion index with a lag of k periods, ε t is the error term, K is the maximum lag order, c is the constant term, and They are the coefficients of the freight rate index and the port congestion index respectively.

[0083] Step 3: Calculate the Akaike Information Criterion (AIC) for different lag orders in the above steps, and select the lag order k that minimizes the AIC value. * As the best model. The specific calculation formula of AIC is:

[0084] ,

[0085] Here, L is the maximum likelihood value of the model.

[0086] Step 4: Use the optimal lag order k * , use the following equation to calculate the change value of the freight rate index in the next period Make predictions:

[0087] ,

[0088] Step 5: Calculate the forecast value of the freight rate index for the next period .

[0089] Specifically, when the congestion status monitoring index of the target port exceeds a preset congestion determination threshold, it is determined that the target port is currently congested.

[0090] like Figure 2 As shown, the present invention also provides a system for monitoring port congestion around the clock using synthetic aperture radar, the system comprising:

[0091] A database construction module is used to construct a synthetic aperture radar image database, wherein the image database includes regional boundary contour vector data of the target port, regional boundary contour vector data of each container terminal in the target port, time-series original synthetic aperture radar image data of the location of the target port, and time-series original synthetic aperture radar image data of each container terminal in the target port;

[0092] An image processing module is used to vertically polarize the time-series original synthetic aperture radar image data of each container terminal in the target port, and obtain the time-series polarized synthetic aperture radar image data of each container terminal in the target port;

[0093] A pixel recognition module is used to recognize container pixels in the time-series polarization synthetic aperture radar image data of each container terminal in the target port by using a threshold method;

[0094] The measurement and evaluation module is used to measure the congestion situation of the target port by taking the ratio of container pixels to the total pixels of the terminal as the congestion monitoring indicator of the target port.

[0095] The technical solution of the above system is similar to the above method and will not be repeated here.

[0096] Based on the same technical solution, the present invention also provides an electronic device, including:

[0097] Memory for storing computer programs;

[0098] The processor is used to implement the steps of the method for monitoring port congestion around the clock by using synthetic aperture radar when executing the computer program.

[0099] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of a method for monitoring port congestion around the clock using synthetic aperture radar are implemented.

[0100] It should be noted that the above-mentioned sequence of the embodiments of the present application is for description only and does not represent the advantages and disadvantages of the embodiments. The above-mentioned specific embodiments of the present application are described. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0101] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device, equipment and storage medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0102] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0103] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for all-weather monitoring of port congestion using synthetic aperture radar, characterized in that: The method comprises the following steps: Constructing a synthetic aperture radar image database, which includes the regional boundary contour vector data of the target port, the regional boundary contour vector data of each container terminal in the target port, and the time-series original synthetic aperture radar image data of the location of the target port; Perform vertical polarization and normalization processing on the time-series raw synthetic aperture radar image data of the target port location; Combine the regional boundary contour vector data of the target port and the regional boundary contour vector data of each container terminal in the target port, perform vector cutting on the normalized processing result, and obtain the time-series polarization synthetic aperture radar image data of each container terminal in the target port; The threshold method is used to identify container pixels in the time-series polarimetric synthetic aperture radar image data of each container terminal in the target port. The ratio of container pixels to total dock pixels is used as the congestion monitoring indicator of the target port to measure the congestion of the target port. The method of using a threshold method to identify container pixels in the time-series polarization synthetic aperture radar image data of each container terminal in the target port includes: Step 1: Obtain optical cloud-free satellite image data that is contemporaneous with the time-series polarimetric synthetic aperture radar image data of each container terminal in the target port, and manually annotate the container pixels in the optical cloud-free satellite image data of the same period; Step 2: Traverse the time-series polarimetric synthetic aperture radar image data set of the container terminal in the target port Q , statistics show Q The minimum pixel value of all the time-series polarized synthetic aperture radar image data m and maximum value M ,by As the initial threshold, Q Identify container pixels in all time-series polarized synthetic aperture radar image data: When the pixel in the synthetic aperture radar image data after time series polarization i The pixel value P i >K l When i Identify it as a container pixel, otherwise the pixel i Identified as non-container pixels; among them, l Represents the number of iterations; Step 3: Based on the recognition results of step 2, calculate Q The ratio of the number of container pixels to the total number of pixels in all the time-series polarized synthetic aperture radar image data is obtained to obtain the radar container pixel ratio set { B q l } q∈Q ;in, B q l express Q Medium time series polarimetric synthetic aperture radar image data q The ratio of the number of container pixels to the total number of pixels; Step 4: Calculate the optical cloud-free satellite image data set for the same period R The ratio of the number of container pixels to the total number of pixels in each optical cloud-free satellite image data is used to obtain the optical container pixel ratio set { β r } r∈R ;in, β r express R China Optical Cloud-free Satellite Image Data r The ratio of the number of container pixels to the total number of pixels; Step 5: Calculate { B q l } q∈Q and{ β r } r∈R Pearson correlation coefficient P l ； Step 6: Order l = l +1, return to step 2 and recalculate K l , and recalculate the Pearson correlation coefficient P l , until l Reaching the set maximum value L , get the correlation coefficient set { P l } l∈[1,L] ; Step 7: Select { P l } l∈[1,L] The maximum value corresponding to l The value is the optimal value l * ,by As the optimal threshold, the container pixels in the time-series polarimetric synthetic aperture radar image data of each container terminal in the selected target port are identified.

2. The method according to claim 1, characterized in that: When the congestion monitoring index of the target port exceeds the preset congestion determination threshold, it is determined that the target port is currently congested.

3. The method according to claim 1, characterized in that: The regional boundary outline vector data of the target port includes the latitude and longitude values ​​of the target port, the number of container terminals in the target port, the latitude and longitude values ​​of each container terminal in the target port, and the regional area of ​​each container terminal.

4. The method according to claim 1, characterized in that: The calculation formula of the congestion monitoring index of the target port is: ， Where: R t Represents the target port in t The congestion rate at the time, N Represents the number of container terminals in the target port, C n,t Representing container terminals n exist t The number of container pixels at the time, A n Representing container terminals n The total number of pixels.

5. The method according to claim 1, characterized in that: B q l = C q l / A q ,in, C q l express Q Medium time series polarimetric synthetic aperture radar image data q By threshold K l The number of container pixels identified, A q Represents the time series polarization synthetic aperture radar image data q The total number of pixels; β r = C r / A r ,in, C r express R China Optical Cloud-free Satellite Image Data r The number of manually labeled container pixels, A r Represents optical cloud-free satellite image data r The total number of pixels.

6. A system for monitoring port congestion based on the method according to any one of claims 1 to 5, characterized in that: The system comprises: A database construction module is used to construct a synthetic aperture radar image database, wherein the image database includes regional boundary contour vector data of the target port, regional boundary contour vector data of each container terminal in the target port, time-series original synthetic aperture radar image data of the location of the target port, and time-series original synthetic aperture radar image data of each container terminal in the target port; An image processing module is used to vertically polarize the time-series original synthetic aperture radar image data of each container terminal in the target port, and obtain the time-series polarized synthetic aperture radar image data of each container terminal in the target port; A pixel recognition module is used to recognize container pixels in the time-series polarization synthetic aperture radar image data of each container terminal in the target port by using a threshold method; The measurement and evaluation module is used to measure the congestion situation of the target port by taking the ratio of container pixels to the total pixels of the terminal as the congestion monitoring indicator of the target port.

7. An electronic device, characterized in that: include: Memory for storing computer programs; A processor, configured to implement the steps of the method according to any one of claims 1 to 5 when executing the computer program.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images