CN117037547A - Congestion degree evaluation method, system and storage medium for channel key nodes - Google Patents
Congestion degree evaluation method, system and storage medium for channel key nodes Download PDFInfo
- Publication number
- CN117037547A CN117037547A CN202311279279.7A CN202311279279A CN117037547A CN 117037547 A CN117037547 A CN 117037547A CN 202311279279 A CN202311279279 A CN 202311279279A CN 117037547 A CN117037547 A CN 117037547A
- Authority
- CN
- China
- Prior art keywords
- ship
- channel
- channel key
- congestion degree
- acquiring
- 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
- 238000011156 evaluation Methods 0.000 title claims abstract description 24
- 230000006399 behavior Effects 0.000 claims abstract description 39
- 230000008447 perception Effects 0.000 claims abstract description 31
- 238000000034 method Methods 0.000 claims abstract description 29
- 238000012544 monitoring process Methods 0.000 claims abstract description 19
- 238000013528 artificial neural network Methods 0.000 claims abstract description 11
- 238000012216 screening Methods 0.000 claims abstract description 11
- 238000005457 optimization Methods 0.000 claims abstract description 10
- 230000035772 mutation Effects 0.000 claims description 18
- 230000008569 process Effects 0.000 claims description 12
- 230000003068 static effect Effects 0.000 claims description 12
- 230000009467 reduction Effects 0.000 claims description 10
- 238000004891 communication Methods 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 7
- 230000002776 aggregation Effects 0.000 claims description 6
- 238000004220 aggregation Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 238000005452 bending Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000001105 regulatory effect Effects 0.000 abstract description 2
- 238000011161 development Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000011144 upstream manufacturing Methods 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
- G06V20/50—Context or environment of the image
- G06V20/52—Surveillance or monitoring of activities, e.g. for recognising suspicious objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/0464—Convolutional networks [CNN, ConvNet]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/762—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using clustering, e.g. of similar faces in social networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/766—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using regression, e.g. by projecting features on hyperplanes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G3/00—Traffic control systems for marine craft
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Ocean & Marine Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Traffic Control Systems (AREA)
Abstract
A congestion degree evaluation method, system and storage medium for channel key nodes belong to the technical field of channel monitoring, and comprise the following steps: obtaining channel characteristics and historical navigation conditions of a target channel, and evaluating channel passing force screening channel key points; acquiring ship perception information of a channel key point area, identifying navigation behaviors of the ship, setting tag information of the ship based on the navigation behaviors, and judging the passing time of the ship at the channel key point; evaluating the current congestion degree of the channel key points; and carrying out graph representation on the channel key points by using a graph convolution neural network, carrying out dynamic prediction according to the current congestion degree of the channel key points, obtaining the predicted congestion degree of the target channel key points, and carrying out ship scheduling optimization of the target key points based on the predicted congestion degree. According to the method, the congestion state of the channel is judged through the navigation behavior of the ship, the channel network traffic flow is dynamically analyzed by combining channel association, the fast and accurate prediction of the channel traffic state is realized, and the ship is effectively regulated and controlled.
Description
Technical Field
The application relates to the technical field of channel monitoring, in particular to a method, a system and a storage medium for evaluating congestion degree of key nodes of a channel.
Background
With the rapid development of economy and trade, international and domestic shipping business demands are vigorous, and shipping industry has become one of the most active and growing markets in the global market. With the development of shipping industry, the number of ships in the coming and going direction is gradually increased, the problem of channel congestion is increasingly serious, and the problems of marine traffic safety, long ship navigation time and the like also occur. The navigation channel is taken as an infrastructure for shipping development, the construction of the intelligent navigation channel is greatly promoted, the global perception of hydrological monitoring, water level remote measurement and report, video monitoring and flow monitoring is realized, and the intelligent navigation channel is particularly important for providing services such as accurate navigation assistance, efficient passing, water transport information and the like for ships. The monitoring of the channel has great significance for accelerating the construction of the intelligent channel, improving the management efficiency of the channel and enhancing the intelligent information service.
With the continuous increase of the traffic volume of ships, traffic stagnation conditions facing each channel frequently occur, and particularly, sporadic traffic jams caused by sudden events (ultra-large ships entering and leaving ports, navigation with poor visibility, ship accidents and the like) are more and more vigorous. At present, the congestion degree of the channel is still determined manually and afterwards, and the efficiency requirement of real-time determination cannot be met. And although the VTS base station and the AIS system are widely used, the data utilization degree is not high, and each VTS base station and the AIS system only carry out data statistics aiming at a single base station or system and cannot carry out channel comprehensive analysis. Therefore, how to quickly and accurately determine the traffic state of the channel is a problem to be solved.
Disclosure of Invention
In order to solve the technical problems, the application provides a congestion degree evaluation method, a congestion degree evaluation system and a storage medium for channel key nodes.
The first aspect of the application provides a congestion degree evaluation method for channel key nodes, which comprises the following steps:
obtaining channel characteristics and historical navigation conditions of a target channel, evaluating channel passing force according to the channel characteristics and the historical navigation conditions, and screening channel key points through the channel passing force;
acquiring ship perception information of a region to which a channel key point belongs, identifying navigation behaviors of a ship according to the ship perception information, setting tag information of the ship based on the navigation behaviors, and judging the passing time of the ship at the channel key point through the tag information;
estimating the current congestion degree of the channel key points according to the transit time of each ship in the area where the channel key points belong;
and carrying out graph representation on the channel key points by using a graph convolution neural network, carrying out dynamic prediction according to the current congestion degree corresponding to the channel key points, obtaining the predicted congestion degree of the target channel key points, and carrying out scheduling optimization of the ship of the target key points based on the predicted congestion degree.
In this scheme, according to channel characteristics and history navigation situation evaluation channel through-force, through channel through-force screening channel key point specifically does:
selecting a target channel, extracting the channel width, depth and bending radius of the target channel to generate channel characteristics, and dynamically updating by combining time sequence and meteorological factors;
presetting different monitoring step sizes, acquiring the ship passing number and the ship average passing time corresponding to each monitoring device of a target channel under different monitoring step sizes through data retrieval, generating a historical navigation condition, and matching the historical navigation condition with channel characteristics according to time sequences;
acquiring a matched historical navigation condition sequence, judging mutation points in the historical navigation condition sequence, and acquiring position information corresponding to the mutation points and meteorological features corresponding to time stamps;
generating weather tags according to the weather features, clustering position information corresponding to the mutation points according to the weather tags, acquiring mutation point sets under different weather tags, judging occurrence frequencies of the position information under the different weather tags, and setting weight information according to the occurrence frequencies;
acquiring reference values of channel characteristics, judging deviation between the channel characteristics of the corresponding time stamps of all the mutation points under different meteorological tags and the reference values, screening the mutation points with the deviation larger than a preset threshold value, extracting corresponding position information, and sequencing according to weight information;
and acquiring the position information of the preset quantity under different meteorological tags for integration, and taking the integrated position information as a channel key point.
In the scheme, the ship perception information of the region of the channel key point is acquired, and the navigation behavior of the ship is identified according to the ship perception information, specifically:
carrying out grid division according to two-dimensional map information corresponding to a target channel, obtaining a corresponding grid region of channel key points, and selecting a neighborhood grid of the grid region as a region of the channel key points according to a preset range;
acquiring multi-source ship perception information of an area where channel key points belong, extracting area frame image information and ship bank communication data of the multi-source ship perception information, and carrying out ship identification according to the area frame image information;
carrying out dynamic monitoring on the ship by utilizing multi-frame regional frame image information, acquiring ship navigation dynamic data, and judging the ship state of the ship in the region where the channel key point belongs through the navigation dynamic data;
extracting navigation demand information of a ship according to ship shore communication data, combining the ship state with the navigation demand information, judging navigation behaviors of the ship in an area where a navigation channel key point belongs, and setting tag information of the ship based on the navigation behaviors;
and carrying out big data retrieval according to the static data of the label information ship, obtaining the historical average transit time of the standard ship in different navigation behaviors, converting the ship in the area where the navigation channel key point belongs into the standard ship parameter, and obtaining the transit time of the ship in the motion state in the navigation channel key point by combining the historical average transit time.
In the scheme, the ship is identified according to the regional frame image information, and the method specifically comprises the following steps:
acquiring regional frame image information according to a monitoring video frame of a region where a channel key point belongs, preprocessing the regional frame image information, and constructing a ship identification model based on a central Net network;
extracting feature images by taking the preprocessed regional frame image information as input of a ship identification model, introducing feature pyramids into the ship identification model, and introducing the feature images into the feature pyramids to obtain feature images of different levels;
introducing an ECA attention mechanism into the feature map of the highest level to enhance the channel features, transmitting the channel dependence relationship to the feature pyramid, and carrying out feature fusion through scale equalization convolution to obtain final identification features;
and acquiring the position, offset and width and height information of the central point of the target according to the final identification characteristics, and generating an anchor frame of the ship through regression to realize the identification of the ship.
In the scheme, the current congestion degree of the channel key points is estimated according to the passing time of each ship in the area where the channel key points are located, and specifically comprises the following steps:
acquiring anchor frame parameters in a ship identification process in a region where a channel key point belongs, generating a ship state description according to the anchor frame parameters, updating the ship state to generate a track through a Kalman filtering algorithm, acquiring the updated ship anchor frame parameters, and matching the updated ship anchor frame parameters with the anchor frame parameters in the identification process to track the ship;
identifying the number of existing ships in the area of each channel key point of the current time stamp through anchor frame regression, acquiring the number of predicted ships entering the area of each channel key point of the next time stamp according to ship tracking, and marking the corresponding ships by utilizing the passing time of the ships in a motion state;
presetting a time step of a channel congestion evaluation task, constructing a channel congestion judgment model, setting a corresponding congestion judgment threshold system according to channel characteristics of the area where each channel key point belongs, acquiring channel occupation ratios of stationary ships in the area where each channel key point belongs, and adjusting the congestion judgment threshold system through the channel occupation ratios;
acquiring the reduction rate of the number of existing ships in each time stamp in the time step according to the passing time, acquiring the growth rate according to the predicted number of the ships in the area of each channel key point, and acquiring the difference value between the reduction rate and the growth rate;
and combining the difference value with the current number of ships with the current time stamp, judging the congestion degree of the current time stamp according to the adjusted congestion judgment threshold system, and integrating the congestion degree of each time stamp in the time step to obtain the current congestion degree of the area where each channel key point belongs.
In the scheme, dynamic prediction is carried out according to the current congestion degree corresponding to the channel key points, and the predicted congestion degree of the target channel key points is obtained, specifically:
generating a topological structure according to the connection relation of the channel key points, carrying out graph representation on the topological structure, taking the channel key points as graph nodes, taking the connection relation as an edge structure, and learning the graph representation by using a graph convolution neural network;
acquiring historical navigation conditions of each node under different meteorological tags in the graph representation as additional features of the nodes, selecting target channel key points, performing similarity calculation according to the additional features to acquire other channel key points related to the target channel key points, and generating an adjacency matrix of the target channel key points;
setting initial weights of the channel key points through channel occupation ratios of static ships in the area where the channel key points belong, and introducing a self-attention mechanism to acquire self-attention weights of the channel key points corresponding to the adjacent matrix in the aggregation process;
carrying out neighbor aggregation according to the initial weight and the attention weight to update vector representation of a target channel key point, carrying out dimension transformation on the updated vector representation, and obtaining space-time characteristics of channel congestion by utilizing time convolution;
and importing the time characteristics of channel congestion into a full-connection layer, and obtaining the predicted congestion degree of the target channel key point after the preset time.
The second aspect of the present application also provides a congestion degree evaluation system for a channel key node, the system comprising: the system comprises a memory and a processor, wherein the memory comprises a congestion degree evaluation method program of channel key nodes, and the congestion degree evaluation method program of the channel key nodes realizes the following steps when being executed by the processor:
obtaining channel characteristics and historical navigation conditions of a target channel, evaluating channel passing force according to the channel characteristics and the historical navigation conditions, and screening channel key points through the channel passing force;
acquiring ship perception information of a region to which a channel key point belongs, identifying navigation behaviors of a ship according to the ship perception information, setting tag information of the ship based on the navigation behaviors, and judging the passing time of the ship at the channel key point through the tag information;
estimating the current congestion degree of the channel key points according to the transit time of each ship in the area where the channel key points belong;
and carrying out graph representation on the channel key points by using a graph convolution neural network, carrying out dynamic prediction according to the current congestion degree corresponding to the channel key points, obtaining the predicted congestion degree of the target channel key points, and carrying out scheduling optimization of the ship of the target key points based on the predicted congestion degree.
The third aspect of the present application also provides a computer-readable storage medium, including therein a congestion degree evaluation method program for a channel key node, which when executed by a processor, implements the steps of the congestion degree evaluation method for a channel key node as described in any one of the above.
The application discloses a congestion degree evaluation method, a system and a storage medium of channel key nodes, which comprise the steps of obtaining channel characteristics and historical navigation conditions of a target channel, and evaluating channel passing force to screen channel key points; acquiring ship perception information of a region to which a channel key point belongs, identifying navigation behavior of a ship, setting tag information of the ship based on the navigation behavior, and judging the passing time of the ship at the channel key point; the current congestion degree of the channel key points is evaluated by the root; and carrying out graph representation on the channel key points by using a graph convolution neural network, carrying out dynamic prediction according to the current congestion degree corresponding to the channel key points, obtaining the predicted congestion degree of the target channel key points, and carrying out scheduling optimization of the ship of the target key points based on the predicted congestion degree. According to the method, the congestion state of the channel is judged through the navigation behavior of the ship, the channel network traffic flow is dynamically analyzed by combining channel association, the fast and accurate prediction of the channel traffic state is realized, and the ship is effectively regulated and controlled.
Drawings
FIG. 1 shows a flow chart of a congestion degree evaluation method of a channel key node of the present application;
FIG. 2 shows a flow chart of the present application for identifying the sailing behaviour of a ship based on ship awareness information;
FIG. 3 shows a flow chart of the present application for estimating the current congestion level of a channel keypoint based on transit time;
fig. 4 shows a block diagram of a congestion degree evaluation system for channel key nodes according to the present application.
Detailed Description
In order that the above-recited objects, features and advantages of the present application will be more clearly understood, a more particular description of the application will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, without conflict, the embodiments of the present application and features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flow chart of a congestion degree evaluation method of a channel key node.
As shown in fig. 1, the first aspect of the present application provides a method for evaluating congestion degree of a channel key node, including:
s102, obtaining channel characteristics and historical navigation conditions of a target channel, evaluating channel passing force according to the channel characteristics and the historical navigation conditions, and screening channel key points through the channel passing force;
s104, acquiring ship perception information of a region to which the channel key points belong, identifying the navigation behavior of the ship according to the ship perception information, setting the tag information of the ship based on the navigation behavior, and judging the passing time of the ship at the channel key points through the tag information;
s106, evaluating the current congestion degree of the channel key points according to the passing time of each ship in the area where the channel key points belong;
and S108, carrying out graph representation on the channel key points by using a graph convolution neural network, carrying out dynamic prediction according to the current congestion degree corresponding to the channel key points, obtaining the predicted congestion degree of the target channel key points, and carrying out scheduling optimization of the ship of the target key points based on the predicted congestion degree.
It should be noted that, selecting a target channel, and extracting a suitable longitude and latitude range as an effective area, while for a curved channel, it is not easy to accurately calculate the whole channel, and a small channel within a certain longitude and latitude range can be selected as the target channel; extracting channel width, depth and bending radius of a target channel to generate channel characteristics, and dynamically updating by combining time sequence and meteorological factors; presetting different monitoring step sizes, acquiring the ship passing number and the ship average passing time corresponding to each monitoring device of a target channel under different monitoring step sizes through data retrieval, generating a historical navigation condition, and matching the historical navigation condition with channel characteristics according to time sequences; acquiring a matched historical navigation condition sequence, judging mutation points in the historical navigation condition sequence, and acquiring position information corresponding to the mutation points and meteorological features corresponding to time stamps; generating weather tags according to the weather features, clustering position information corresponding to the mutation points according to the weather tags, acquiring mutation point sets under different weather tags, judging occurrence frequencies of the position information under the different weather tags, and setting weight information according to the occurrence frequencies; acquiring reference values of channel characteristics, judging deviation between the channel characteristics of the corresponding time stamps of all the mutation points under different meteorological tags and the reference values, screening the mutation points with the deviation larger than a preset threshold value, extracting corresponding position information, and sequencing according to weight information; and acquiring the position information of the preset quantity under different meteorological tags for integration, and taking the integrated position information as a channel key point.
Fig. 2 shows a flow chart of the application for identifying the sailing behaviour of a ship on the basis of ship awareness information.
According to the embodiment of the application, the ship perception information of the region to which the channel key point belongs is obtained, and the navigation behavior of the ship is identified according to the ship perception information, specifically:
s202, carrying out grid division according to two-dimensional map information corresponding to a target channel, obtaining a corresponding grid region of channel key points, and selecting a neighborhood grid of the grid region as a region of the channel key points according to a preset range;
s204, multi-source ship perception information of an area where the channel key points belong is obtained, area frame image information and shore communication data of the multi-source ship perception information are extracted, and ship identification is carried out according to the area frame image information;
s206, carrying out dynamic monitoring on the ship by utilizing multi-frame regional frame image information, acquiring ship navigation dynamic data, and judging the ship state of the ship in the region where the channel key point belongs through the navigation dynamic data;
s208, extracting navigation demand information of the ship according to the ship shore communication data, combining the ship state with the navigation demand information, judging navigation behaviors of the ship in the area where the navigation channel key points belong, and setting tag information of the ship based on the navigation behaviors;
and S210, carrying out big data retrieval according to the static data of the tag information ship, obtaining the historical average transit time of the standard ship in different sailing behaviors, converting the ship in the area where the channel key point belongs into the standard ship parameter, and obtaining the transit time of the ship in the motion state in the channel key point by combining the historical average transit time.
The center net network models the ship as a center point, a center point offset and width and height information of a target, obtains the center point position of the ship by taking a local peak point from the feature map, and obtains the center point offset and the width and height information of the ship through two parallel branches and then fuses the information, thereby obtaining the ship anchor frame.
Acquiring regional frame image information according to a monitoring video frame of a region where a channel key point belongs, preprocessing the regional frame image information, and constructing a ship identification model based on a central Net network; extracting feature images by taking the preprocessed regional frame image information as input of a ship identification model, introducing feature pyramids into the ship identification model, and introducing the feature images into the feature pyramids to obtain feature images of different levels; introducing an ECA attention mechanism into the highest-level feature graph to enhance the channel features, wherein the ECA attention mechanism enables the channel with high key information correlation degree to have larger weight, and improves the identification capability of the features; the channel dependence relationship is transmitted to the feature pyramid, and feature fusion is carried out through scale equalization convolution, so that final identification features are obtained; and acquiring the position, offset and width and height information of the central point of the target according to the final identification characteristics, and generating an anchor frame of the ship through regression to realize the identification of the ship.
The static data and the dynamic data of the ship can be acquired through an AIS system, the ship of the AIS can acquire the ship static data such as the ship name, call sign, captain, cargo type and the like of the ship with the AIS installed and used on the periphery in real time, and the ship navigation dynamic data comprise heading, navigational speed, position, relative distance and the like. And extracting navigation demand information of the ship according to the ship shore communication data, wherein the navigation demand information comprises ship berthing, ship passing and the like, and the demand of ship berthing comprises cargo loading and unloading, ship maintenance, personnel transferring and the like. The ship state is divided into a moving ship and a static ship, and the dynamic ship is attached with information such as real-time heading, navigational speed, position, relative distance and the like. And judging the sailing behavior of the ship in the area where the navigation channel key points belong according to the sailing demand information and the ship state, acquiring the historical average transit time of the standard ship in different sailing behaviors, and setting standard ship information, for example, acquiring the historical average transit time of the standard captain ship in the unloading behavior, including the unloading time and the transit time. And transforming the ship data of the area where the channel key points belong into standard ship parameters based on the conversion coefficient, and acquiring the passing time of the ship in the channel key points in a motion state according to the historical average passing time as a reference.
Fig. 3 shows a flow chart of the present application for estimating the current congestion level of a channel key point based on the transit time.
According to the embodiment of the application, the current congestion degree of the channel key points is estimated according to the passing time of each ship in the area where the channel key points belong, specifically:
s302, acquiring anchor frame parameters in a ship identification process in a region where a channel key point belongs, generating a ship state description according to the anchor frame parameters, updating the ship state through a Kalman filtering algorithm to generate a track, acquiring the updated ship anchor frame parameters, and matching the updated ship anchor frame parameters with the anchor frame parameters in the identification process to track the ship;
s304, identifying the number of existing ships in the area of each channel key point of the current time stamp through anchor frame regression, obtaining the number of predicted ships entering the area of each channel key point of the next time stamp according to ship tracking, and marking the corresponding ships by utilizing the running time of the ships in a motion state;
s306, presetting a time step of a channel congestion evaluation task, constructing a channel congestion judgment model, setting a corresponding congestion judgment threshold system according to channel characteristics of the region where each channel key point belongs, acquiring channel occupation ratios of stationary ships in the region where each channel key point belongs, and adjusting the congestion judgment threshold system according to the channel occupation ratios;
s308, obtaining the reduction rate of the number of existing ships in each time stamp in the time step according to the passing time, obtaining the growth rate according to the predicted number of the ships in the area where each channel key point belongs, and obtaining the difference value between the reduction rate and the growth rate;
and S310, combining the difference value with the number of the current ships with the current time stamp, judging the congestion degree of the current time stamp according to the adjusted congestion judgment threshold system, and integrating the congestion degree of each time stamp in the time step to obtain the current congestion degree of the area where each channel key point belongs.
It should be noted that, the ship state is updated through the kalman filtering algorithm to generate a track, and is described as an 8-dimensional space, wherein the first 4-dimensional parameter is determined through the anchor frame parameter, and the second 4-dimensional parameter represents the speed information of the anchor frame of the ship. And matching the updated anchor frame parameters of the ship with anchor frame parameters in the identification process through the Manhattan distance, and considering that the ship leaves the area where the key points of the channel belong when proper identification anchor frames are not matched within the preset maximum time range.
The channel congestion degree is divided into smooth, general congestion, serious congestion and the like. Unblocked means that the ships in the navigation channel can navigate at normal speed, and the number of the ships is small; the general congestion means that the ship can navigate at a low speed, and the number of the ships is general; severe congestion refers to stopping or completely stopping the ship when it moves, and the number of vessels is large. And constructing a congestion judgment threshold system according to a judgment principle by combining the corresponding threshold, combining the difference value of the reduction rate and the increase rate with the current ship quantity of the current time stamp, and calculating the ship channel area density to judge the congestion, wherein the ship channel area density refers to the ship quantity existing in a unit rectangular area.
Generating a topological structure according to the connection relation of the channel key points, carrying out graph representation on the topological structure, taking the channel key points as graph nodes, taking the connection relation as an edge structure, and learning the graph representation by using a graph convolution neural network; acquiring historical navigation conditions of each node under different meteorological tags in the graph representation as additional features of the nodes, selecting target channel key points, performing similarity calculation according to the additional features to acquire other channel key points related to the target channel key points, and generating an adjacency matrix of the target channel key points; setting initial weights of the channel key points through channel occupation ratios of static ships in the area where the channel key points belong, and introducing a self-attention mechanism to acquire self-attention weights of the channel key points corresponding to the adjacent matrix in the aggregation process; generating an initial vector representation according to the current congestion degree and the climate characteristics of the key points of the target channel; carrying out neighbor aggregation according to the initial weight and the attention weight to update vector representation of a target channel key point, carrying out dimension transformation on the updated vector representation, and obtaining space-time characteristics of channel congestion by utilizing time convolution; and importing the time characteristics of channel congestion into a full-connection layer, and obtaining the predicted congestion degree of the target channel key point after the preset time.
According to the embodiment of the application, the scheduling optimization of the ship at the target key point is performed based on the predicted congestion degree, specifically:
acquiring the current congestion degree of a time step corresponding to a current channel congestion evaluation task, predicting the predicted congestion degree after preset time according to the current congestion degree, and judging whether to perform scheduling optimization according to the predicted congestion degree;
when the predicted congestion degree is greater than a preset congestion threshold value, generating early warning information of a target channel key point, acquiring a difference absolute value of a ship quantity reduction rate and a ship quantity increase rate of the target channel key point, and marking a time stamp with the difference absolute value greater than a preset standard;
performing channel control on an upstream key point of the target channel key point according to the marked time stamp, reducing the number growth rate of the target key point ships, and obtaining the channel occupation ratio of the static ship in the area where the target key point belongs;
and when the channel occupation ratio is larger than a preset ratio threshold, scheduling the berth of the ship, and transferring the static ship to the neighborhood idle key point.
Fig. 4 shows a block diagram of a congestion degree evaluation system for channel key nodes according to the present application.
The second aspect of the present application also provides a congestion degree evaluation system 4 for a channel key node, the system comprising: the memory 41 and the processor 42, wherein the memory comprises a congestion degree evaluation method program of a channel key node, and the congestion degree evaluation method program of the channel key node realizes the following steps when being executed by the processor:
obtaining channel characteristics and historical navigation conditions of a target channel, evaluating channel passing force according to the channel characteristics and the historical navigation conditions, and screening channel key points through the channel passing force;
acquiring ship perception information of a region to which a channel key point belongs, identifying navigation behaviors of a ship according to the ship perception information, setting tag information of the ship based on the navigation behaviors, and judging the passing time of the ship at the channel key point through the tag information;
estimating the current congestion degree of the channel key points according to the transit time of each ship in the area where the channel key points belong;
and carrying out graph representation on the channel key points by using a graph convolution neural network, carrying out dynamic prediction according to the current congestion degree corresponding to the channel key points, obtaining the predicted congestion degree of the target channel key points, and carrying out scheduling optimization of the ship of the target key points based on the predicted congestion degree.
The third aspect of the present application also provides a computer-readable storage medium, including therein a congestion degree evaluation method program for a channel key node, which when executed by a processor, implements the steps of the congestion degree evaluation method for a channel key node as described in any one of the above.
In the several embodiments provided by the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present application may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present application may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (10)
1. The congestion degree evaluation method for the channel key nodes is characterized by comprising the following steps of:
obtaining channel characteristics and historical navigation conditions of a target channel, evaluating channel passing force according to the channel characteristics and the historical navigation conditions, and screening channel key points through the channel passing force;
acquiring ship perception information of a region to which a channel key point belongs, identifying navigation behaviors of a ship according to the ship perception information, setting tag information of the ship based on the navigation behaviors, and judging the passing time of the ship at the channel key point through the tag information;
estimating the current congestion degree of the channel key points according to the transit time of each ship in the area where the channel key points belong;
and carrying out graph representation on the channel key points by using a graph convolution neural network, carrying out dynamic prediction according to the current congestion degree corresponding to the channel key points, obtaining the predicted congestion degree of the target channel key points, and carrying out scheduling optimization of the ship of the target key points based on the predicted congestion degree.
2. The method for evaluating the congestion degree of channel key nodes according to claim 1, wherein the channel passing force is evaluated according to the channel characteristics and the historical navigation conditions, and channel key points are screened through the channel passing force, specifically:
selecting a target channel, extracting the channel width, depth and bending radius of the target channel to generate channel characteristics, and dynamically updating by combining time sequence and meteorological factors;
presetting different monitoring step sizes, acquiring the ship passing number and the ship average passing time corresponding to each monitoring device of a target channel under different monitoring step sizes through data retrieval, generating a historical navigation condition, and matching the historical navigation condition with channel characteristics according to time sequences;
acquiring a matched historical navigation condition sequence, judging mutation points in the historical navigation condition sequence, and acquiring position information corresponding to the mutation points and meteorological features corresponding to time stamps;
generating weather tags according to the weather features, clustering position information corresponding to the mutation points according to the weather tags, acquiring mutation point sets under different weather tags, judging occurrence frequencies of the position information under the different weather tags, and setting weight information according to the occurrence frequencies;
acquiring reference values of channel characteristics, judging deviation between the channel characteristics of the corresponding time stamps of all the mutation points under different meteorological tags and the reference values, screening the mutation points with the deviation larger than a preset threshold value, extracting corresponding position information, and sequencing according to weight information;
and acquiring the position information of the preset quantity under different meteorological tags for integration, and taking the integrated position information as a channel key point.
3. The method for evaluating the congestion degree of a channel key node according to claim 1, wherein the method is characterized in that the ship perception information of the region to which the channel key node belongs is obtained, and the navigation behavior of the ship is identified according to the ship perception information, specifically:
carrying out grid division according to two-dimensional map information corresponding to a target channel, obtaining a corresponding grid region of channel key points, and selecting a neighborhood grid of the grid region as a region of the channel key points according to a preset range;
acquiring multi-source ship perception information of an area where channel key points belong, extracting area frame image information and ship bank communication data of the multi-source ship perception information, and carrying out ship identification according to the area frame image information;
carrying out dynamic monitoring on the ship by utilizing multi-frame regional frame image information, acquiring ship navigation dynamic data, and judging the ship state of the ship in the region where the channel key point belongs through the navigation dynamic data;
extracting navigation demand information of a ship according to ship shore communication data, combining the ship state with the navigation demand information, judging navigation behaviors of the ship in an area where a navigation channel key point belongs, and setting tag information of the ship based on the navigation behaviors;
and carrying out big data retrieval according to the tag information and the static data of the ship, obtaining the historical average transit time of the standard ship in different sailing behaviors, converting the ship in the area where the channel key point belongs into the standard ship parameter, and obtaining the transit time of the ship in the motion state in the channel key point by combining the historical average transit time.
4. The method for evaluating the congestion degree of a channel key node according to claim 3, wherein the ship identification is performed according to regional frame image information, specifically:
acquiring regional frame image information according to a monitoring video frame of a region where a channel key point belongs, preprocessing the regional frame image information, and constructing a ship identification model based on a central Net network;
extracting feature images by taking the preprocessed regional frame image information as input of a ship identification model, introducing feature pyramids into the ship identification model, and introducing the feature images into the feature pyramids to obtain feature images of different levels;
introducing an ECA attention mechanism into the feature map of the highest level to enhance the channel features, transmitting the channel dependence relationship to the feature pyramid, and carrying out feature fusion through scale equalization convolution to obtain final identification features;
and acquiring the position, offset and width and height information of the central point of the target according to the final identification characteristics, and generating an anchor frame of the ship through regression to realize the identification of the ship.
5. The method for evaluating the congestion degree of a channel key node according to claim 1, wherein the current congestion degree of the channel key node is evaluated according to the transit time of each ship in the area to which the channel key node belongs, specifically:
acquiring anchor frame parameters in a ship identification process in a region where a channel key point belongs, generating a ship state description according to the anchor frame parameters, updating the ship state to generate a track through a Kalman filtering algorithm, acquiring the updated ship anchor frame parameters, and matching the updated ship anchor frame parameters with the anchor frame parameters in the identification process to track the ship;
identifying the number of existing ships in the area of each channel key point of the current time stamp through anchor frame regression, acquiring the number of predicted ships entering the area of each channel key point of the next time stamp according to ship tracking, and marking the corresponding ships by utilizing the passing time of the ships in a motion state;
presetting a time step of a channel congestion evaluation task, constructing a channel congestion judgment model, setting a corresponding congestion judgment threshold system according to channel characteristics of the area where each channel key point belongs, acquiring channel occupation ratios of stationary ships in the area where each channel key point belongs, and adjusting the congestion judgment threshold system through the channel occupation ratios;
acquiring the reduction rate of the number of existing ships in each time stamp in the time step according to the passing time, acquiring the growth rate according to the predicted number of the ships in the area of each channel key point, and acquiring the difference value between the reduction rate and the growth rate;
and combining the difference value with the current number of ships with the current time stamp, judging the congestion degree of the current time stamp according to the adjusted congestion judgment threshold system, and integrating the congestion degree of each time stamp in the time step to obtain the current congestion degree of the area where each channel key point belongs.
6. The method for evaluating the congestion degree of a channel key node according to claim 1, wherein the method is characterized in that the method dynamically predicts according to the current congestion degree corresponding to the channel key point to obtain the predicted congestion degree of the target channel key point, specifically comprises the following steps:
generating a topological structure according to the connection relation of the channel key points, carrying out graph representation on the topological structure, taking the channel key points as graph nodes, taking the connection relation as an edge structure, and learning the graph representation by using a graph convolution neural network;
acquiring historical navigation conditions of each node under different meteorological tags in the graph representation as additional features of the nodes, selecting target channel key points, performing similarity calculation according to the additional features to acquire other channel key points related to the target channel key points, and generating an adjacency matrix of the target channel key points;
setting initial weights of the channel key points through channel occupation ratios of static ships in the area where the channel key points belong, and introducing a self-attention mechanism to acquire self-attention weights of the channel key points corresponding to the adjacent matrix in the aggregation process;
carrying out neighbor aggregation according to the initial weight and the attention weight to update vector representation of a target channel key point, carrying out dimension transformation on the updated vector representation, and obtaining space-time characteristics of channel congestion by utilizing time convolution;
and importing the time characteristics of channel congestion into a full-connection layer, and obtaining the predicted congestion degree of the target channel key point after the preset time.
7. A congestion degree evaluation system for a channel key node, the system comprising: the system comprises a memory and a processor, wherein the memory comprises a congestion degree evaluation method program of channel key nodes, and the congestion degree evaluation method program of the channel key nodes realizes the following steps when being executed by the processor:
obtaining channel characteristics and historical navigation conditions of a target channel, evaluating channel passing force according to the channel characteristics and the historical navigation conditions, and screening channel key points through the channel passing force;
acquiring ship perception information of a region to which a channel key point belongs, identifying navigation behaviors of a ship according to the ship perception information, setting tag information of the ship based on the navigation behaviors, and judging the passing time of the ship at the channel key point through the tag information;
estimating the current congestion degree of the channel key points according to the transit time of each ship in the area where the channel key points belong;
and carrying out graph representation on the channel key points by using a graph convolution neural network, carrying out dynamic prediction according to the current congestion degree corresponding to the channel key points, obtaining the predicted congestion degree of the target channel key points, and carrying out scheduling optimization of the ship of the target key points based on the predicted congestion degree.
8. The system for evaluating the congestion degree of a channel key node according to claim 7, wherein the ship perception information of the region to which the channel key node belongs is obtained, and the navigation behavior of the ship is identified according to the ship perception information, specifically:
carrying out grid division according to two-dimensional map information corresponding to a target channel, obtaining a corresponding grid region of channel key points, and selecting a neighborhood grid of the grid region as a region of the channel key points according to a preset range;
acquiring multi-source ship perception information of an area where channel key points belong, extracting area frame image information and ship bank communication data of the multi-source ship perception information, and carrying out ship identification according to the area frame image information;
carrying out dynamic monitoring on the ship by utilizing multi-frame regional frame image information, acquiring ship navigation dynamic data, and judging the ship state of the ship in the region where the channel key point belongs through the navigation dynamic data;
extracting navigation demand information of a ship according to ship shore communication data, combining the ship state with the navigation demand information, judging navigation behaviors of the ship in an area where a navigation channel key point belongs, and setting tag information of the ship based on the navigation behaviors;
and carrying out big data retrieval according to the tag information and the static data of the ship, obtaining the historical average transit time of the standard ship in different sailing behaviors, converting the ship in the area where the channel key point belongs into the standard ship parameter, and obtaining the transit time of the ship in the motion state in the channel key point by combining the historical average transit time.
9. The system for evaluating the congestion degree of a channel key node according to claim 7, wherein the current congestion degree of the channel key node is evaluated according to the transit time of each ship in the area to which the channel key node belongs, specifically:
acquiring anchor frame parameters in a ship identification process in a region where a channel key point belongs, generating a ship state description according to the anchor frame parameters, updating the ship state to generate a track through a Kalman filtering algorithm, acquiring the updated ship anchor frame parameters, and matching the updated ship anchor frame parameters with the anchor frame parameters in the identification process to track the ship;
identifying the number of existing ships in the area of each channel key point of the current time stamp through anchor frame regression, acquiring the number of predicted ships entering the area of each channel key point of the next time stamp according to ship tracking, and marking the corresponding ships by utilizing the passing time of the ships in a motion state;
presetting a time step of a channel congestion evaluation task, constructing a channel congestion judgment model, setting a corresponding congestion judgment threshold system according to channel characteristics of the area where each channel key point belongs, acquiring channel occupation ratios of stationary ships in the area where each channel key point belongs, and adjusting the congestion judgment threshold system through the channel occupation ratios;
acquiring the reduction rate of the number of existing ships in each time stamp in the time step according to the passing time, acquiring the growth rate according to the predicted number of the ships in the area of each channel key point, and acquiring the difference value between the reduction rate and the growth rate;
and combining the difference value with the current number of ships with the current time stamp, judging the congestion degree of the current time stamp according to the adjusted congestion judgment threshold system, and integrating the congestion degree of each time stamp in the time step to obtain the current congestion degree of the area where each channel key point belongs.
10. A computer-readable storage medium, characterized by: the computer readable storage medium includes a congestion degree evaluation method program for channel key nodes, which when executed by a processor, implements the congestion degree evaluation method steps for channel key nodes according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311279279.7A CN117037547B (en) | 2023-10-07 | 2023-10-07 | Congestion degree evaluation method, system and storage medium for channel key nodes |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311279279.7A CN117037547B (en) | 2023-10-07 | 2023-10-07 | Congestion degree evaluation method, system and storage medium for channel key nodes |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117037547A true CN117037547A (en) | 2023-11-10 |
| CN117037547B CN117037547B (en) | 2023-12-19 |
Family
ID=88632076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311279279.7A Active CN117037547B (en) | 2023-10-07 | 2023-10-07 | Congestion degree evaluation method, system and storage medium for channel key nodes |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117037547B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117634926A (en) * | 2023-12-08 | 2024-03-01 | 交通运输部水运科学研究所 | Comprehensive port operation prediction method and system based on big data analysis |
| CN117975769A (en) * | 2024-03-29 | 2024-05-03 | 交通运输部水运科学研究所 | Intelligent navigation safety management method and system based on multi-source data fusion |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200054543A (en) * | 2018-11-12 | 2020-05-20 | 삼성중공업 주식회사 | A system for optimizing the ship's route |
| CN111339229A (en) * | 2020-02-24 | 2020-06-26 | 交通运输部水运科学研究所 | Ship autonomous navigation aid decision-making system |
| CN114565124A (en) * | 2022-01-12 | 2022-05-31 | 武汉理工大学 | Ship traffic flow prediction method based on improved graph convolution neural network |
| CN115081825A (en) * | 2022-05-31 | 2022-09-20 | 浙江省交通运输科学研究院 | Maritime channel safety risk assessment method based on multi-state fuzzy Bayesian network |
| CN115640873A (en) * | 2022-09-21 | 2023-01-24 | 上海汇航捷讯网络科技有限公司 | Port congestion degree quantification method based on ship AIS big data |
| CN115965144A (en) * | 2022-12-30 | 2023-04-14 | 武汉理工大学 | Ship traffic flow prediction method, system, device and storage medium |
| CN116402846A (en) * | 2022-12-26 | 2023-07-07 | 武汉珞珈智绘科技有限公司 | Inland waterway ship situation analysis and prediction method based on AIS big data |
-
2023
- 2023-10-07 CN CN202311279279.7A patent/CN117037547B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20200054543A (en) * | 2018-11-12 | 2020-05-20 | 삼성중공업 주식회사 | A system for optimizing the ship's route |
| CN111339229A (en) * | 2020-02-24 | 2020-06-26 | 交通运输部水运科学研究所 | Ship autonomous navigation aid decision-making system |
| CN114565124A (en) * | 2022-01-12 | 2022-05-31 | 武汉理工大学 | Ship traffic flow prediction method based on improved graph convolution neural network |
| CN115081825A (en) * | 2022-05-31 | 2022-09-20 | 浙江省交通运输科学研究院 | Maritime channel safety risk assessment method based on multi-state fuzzy Bayesian network |
| CN115640873A (en) * | 2022-09-21 | 2023-01-24 | 上海汇航捷讯网络科技有限公司 | Port congestion degree quantification method based on ship AIS big data |
| CN116402846A (en) * | 2022-12-26 | 2023-07-07 | 武汉珞珈智绘科技有限公司 | Inland waterway ship situation analysis and prediction method based on AIS big data |
| CN115965144A (en) * | 2022-12-30 | 2023-04-14 | 武汉理工大学 | Ship traffic flow prediction method, system, device and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117634926A (en) * | 2023-12-08 | 2024-03-01 | 交通运输部水运科学研究所 | Comprehensive port operation prediction method and system based on big data analysis |
| CN117975769A (en) * | 2024-03-29 | 2024-05-03 | 交通运输部水运科学研究所 | Intelligent navigation safety management method and system based on multi-source data fusion |
| CN117975769B (en) * | 2024-03-29 | 2024-06-07 | 交通运输部水运科学研究所 | Intelligent navigation safety management method and system based on multi-source data fusion |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117037547B (en) | 2023-12-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117037547B (en) | Congestion degree evaluation method, system and storage medium for channel key nodes | |
| Agrawal et al. | Machine learning for precipitation nowcasting from radar images | |
| US11721191B1 (en) | Method and system for flood early warning in smart city based on internet of things | |
| Duca et al. | A K-nearest neighbor classifier for ship route prediction | |
| CN104660993B (en) | Maritime affairs intelligent control method and system based on AIS and CCTV | |
| US11893883B2 (en) | Short-term traffic speed prediction and forecasting using machine learning analysis of spatiotemporal traffic speed dependencies in probe and weather data | |
| CN116758744B (en) | Smart city operation and maintenance management method, system and storage medium based on artificial intelligence | |
| Tu et al. | Modeling historical AIS data for vessel path prediction: A comprehensive treatment | |
| Ristic | Detecting anomalies from a multitarget tracking output | |
| Millefiori et al. | A distributed approach to estimating sea port operational regions from lots of AIS data | |
| CN113553682A (en) | Data-driven multi-level ship route network construction method | |
| CN112668846A (en) | Intelligent ship lock scheduling system | |
| CN114743401B (en) | Data visualization bus dispatching management platform based on bus digital transformation | |
| US20230140289A1 (en) | Traffic accident prediction systems and methods | |
| CN115456474B (en) | Port operation scheduling method and system based on artificial intelligence | |
| CN117610734A (en) | Deep learning-based user behavior prediction method, system and electronic equipment | |
| Nishizaki et al. | Development of navigation support system to predict new course of ship | |
| CN108052629A (en) | A kind of quick extra large land determination methods based on high accuracy DEM data | |
| CN117077846A (en) | Passenger flow volume prediction method, equipment, storage medium and device | |
| CN115424276B (en) | Ship license plate number detection method based on deep learning technology | |
| CN116597693A (en) | Inland navigation monitoring system and method | |
| CN116630907A (en) | Ship navigation digital twin method, system, terminal and storage medium based on remote sensing | |
| CN111639585A (en) | Self-adaptive crowd counting system and self-adaptive crowd counting method | |
| CN116384597A (en) | Dynamic prediction method and system for port entering and exiting of fishing port ship based on geographic information system | |
| KR102429235B1 (en) | System and method for predicting maritime traffic congestion |
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 |