A multi-scale hierarchical organization method for electronic nautical chart data

Abstract

The present invention discloses a multi-scale hierarchical organization method for electronic nautical chart data, belonging to the technical field of electronic nautical chart processing. The present invention solves the problem that traditional multi-scale hierarchical display methods generally rely on predefined scale data and are difficult to dynamically adjust the resolution to adapt to different navigation needs. By presetting a weight distribution scheme according to different navigation scenarios and dynamically adjusting the weights of different features according to the specific needs of the navigation mission, the present invention ensures that the convolutional neural network model can automatically adjust the importance of features in different navigation scenarios to better adapt to the needs of the navigation mission. By establishing a priority mechanism for the weights assigned to coastline features, water depth features, and navigation obstacle features, the present invention enables the method to handle complex navigation scenarios more flexibly, thereby significantly improving the safety and efficiency of navigation.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic nautical chart processing, and in particular to a multi-scale hierarchical organization method for electronic nautical chart data. Background Art

[0002] Electronic nautical chart data is digital nautical chart information used for marine navigation and related applications. It is stored and displayed in electronic form, providing mariners with detailed data on the marine environment, navigation conditions, and geographic information. As an important tool in the field of navigation, the multi-scale hierarchical organization of electronic nautical charts is a key technology in marine navigation and has a significant impact on navigation safety and efficiency.

[0003] Traditional multi-scale layered display methods usually rely on predefined scale data and are difficult to dynamically adjust the resolution to suit different navigation needs.

[0004] Therefore, it does not meet the existing needs. We propose a multi-scale hierarchical organization method for electronic nautical chart data. Summary of the Invention

[0005] The object of the present invention is to provide a multi-scale hierarchical organization method for electronic nautical chart data, which pre-sets a weight distribution scheme according to different navigation scenarios and dynamically adjusts the weights of different features according to the specific needs of the navigation mission; ensures that the convolutional neural network model can automatically adjust the importance of features in different navigation scenarios, thereby better adapting to the needs of the navigation mission; and establishes a priority mechanism for the weights assigned to coastline features, water depth features, and navigation obstacle features, so that the method can handle complex navigation scenarios more flexibly, thereby significantly improving the safety and efficiency of navigation, improving the efficiency of electronic nautical chart processing, and solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A multi-scale hierarchical organization method for electronic nautical chart data, comprising the following steps:

[0008] Extract feature information from historical electronic nautical chart data based on a convolutional neural network model, including coastline features, water depth, and navigation obstacles;

[0009] Multi-scale fusion of the extracted feature information can simultaneously capture obstacle details with different accuracies;

[0010] A weight distribution scheme is pre-set based on different navigation scenarios, and the weights of different features are dynamically adjusted according to the specific needs of the navigation mission. The weight adjustment process includes: dynamically adjusting the feature weights by monitoring the ship's yaw and changes in attribute information of the current location, as well as the changes in the current location's coastline data, water depth, navigation obstacles and weather information;

[0011] A reward function is used to divide historical electronic nautical chart data into multiple layers of skeleton data based on their intended use. The resolution of different features is dynamically adjusted based on feature weights. The resolution adjustment process involves real-time monitoring of the number of emergency events in navigation scenarios. When a threshold is exceeded, the current feature weight and historical feature weight are combined to calculate a weight ratio coefficient, and the resolution of the chart data at different layers in the multi-layer skeleton data is adjusted accordingly.

[0012] The verified convolutional neural network model is applied to actual navigation.

[0013] Furthermore, feature information from historical electronic nautical chart data is extracted based on the convolutional neural network model, including:

[0014] Collect historical electronic nautical chart data, including high-resolution remote sensing images and associated annotation data;

[0015] Preprocess historical electronic chart data for training convolutional neural network models;

[0016] Construct a multi-scale convolutional neural network model, using convolutional kernels of different scales in the convolutional and pooling layers to automatically identify coastline features, water depth features, and navigation obstacle features of different scales in historical electronic nautical chart data;

[0017] Different types of coastline features, water depth features, and navigation obstacle features are adaptively classified and located through the fully connected layer.

[0018] Furthermore, the extracted feature information is subjected to multi-scale fusion, including:

[0019] The coastline features, water depth features and navigation obstacle features extracted at different scales are spliced ​​together to form a multi-scale feature map;

[0020] Through upsampling and downsampling operations, feature maps of different scales are adjusted to the same size and then fused for subsequent classification and segmentation tasks.

[0021] Furthermore, a weight distribution scheme is pre-set according to different navigation scenarios, and the weights of different features are dynamically adjusted according to the specific needs of the navigation mission, including:

[0022] Assign different navigation scenarios to the extracted coastline features, water depth features and navigation obstacle features;

[0023] Different weights are assigned based on the importance of the corresponding navigation scenarios of coastline characteristics, water depth characteristics and navigation obstacle characteristics;

[0024] Establish a priority mechanism for assigning weights to coastline characteristics, water depth characteristics, and navigation obstacle characteristics based on maritime navigation needs;

[0025] Combined with the real-time feedback mechanism, the feature weights are dynamically adjusted according to the execution of the navigation mission.

[0026] Furthermore, combined with the real-time feedback mechanism, the feature weights are dynamically adjusted according to the execution of the navigation mission, including:

[0027] collecting first feedback information in real time, the first feedback information including real-time positioning of the current position information of the vessel during navigation, and comparing the current position information of the vessel with a preset navigation route to determine whether there is deviation and the degree of deviation;

[0028] When the ship deviates and the degree of deviation is greater than a preset deviation threshold, it is determined that the attribute information of the current position of the ship has changed, and the attribute information of the ship's position includes features of being close to a coastline, close to a shallow water area, close to a port, or close to a deep water area. The first feature weight is adjusted based on the change in the attribute information of the ship's position;

[0029] During the adjustment of the first feature weight, the corresponding weight assignment interval is retrieved according to the preset attribute information of the ship;

[0030] The second feedback information includes coastline data information, water depth information, navigation obstacle information and weather information under the current position information of the ship in real time.

[0031] At the same time, the coastline data information, water depth information, navigation obstacle information and weather information under the current location information are compared with the reference coastline data information, reference water depth information and reference navigation obstacle information when formulating the preset navigation route, and the change amplitude values ​​are compared. Based on the change amplitude value, the second feature weight is adjusted within the weight assignment range to obtain the adjusted feature weight value.

[0032] Furthermore, a priority mechanism is established to assign weights to coastline characteristics, water depth characteristics, and navigation obstacle characteristics based on HNA requirements, including:

[0033] Analyze the content of the current navigation mission, prioritize the weights based on the content, and dynamically adjust the feature weights;

[0034] Analyze the changes in the current navigation scene and divide the weight priorities according to the changes in the navigation scene.

[0035] Furthermore, a reward function is used to divide historical electronic chart data into multiple layers of skeleton data according to their usage, including:

[0036] By introducing a reward function into the convolutional neural network model, we evaluate whether the behavior of the convolutional neural network model meets the requirements of the current navigation task;

[0037] Analyze the importance of different feature information according to the current navigation scenario as the basis for dividing weight priorities;

[0038] The reward function is used to divide the historical electronic nautical chart data into multiple layers of skeleton data according to the current navigation scene and navigation mission purpose.

[0039] Furthermore, based on the feature weights, the resolution of different features is dynamically adjusted, including:

[0040] Based on the dynamically adjusted feature weights and the specific needs of the current navigation mission, the resolution of the chart data at different levels in the multi-layer skeleton data is dynamically adjusted;

[0041] Then, according to the specific needs of the navigation mission, the resolution of the chart data at different scales is dynamically adjusted;

[0042] According to the adaptability of the adjusted chart data resolution to the task, a reward signal is sent based on the reward function, and the convolutional neural network model updates the adjustment strategy according to the reward signal.

[0043] Furthermore, after dynamically adjusting the resolution of the chart data at different levels in the multi-layer skeleton data, the number of emergencies occurring in different navigation scenarios is monitored in real time, and compensation is performed based on the dynamically adjusted resolution according to the number of emergencies, including:

[0044] Real-time monitoring of the number of emergency events occurring in different navigation scenarios; wherein the emergency events include coastline mutation events, rapid water depth change events, sudden appearance of navigation obstacles events, and emergency avoidance events caused by incorrect navigation obstacle location information; and the coastline mutation events are related to the coastline characteristics; the rapid water depth change events are related to the water depth characteristics; the sudden appearance of navigation obstacles events and emergency avoidance events caused by incorrect navigation obstacle location information are related to the navigation obstacle characteristics;

[0045] When the number of emergency events exceeds the preset emergency event threshold, the current feature weight corresponding to each feature is retrieved in real time;

[0046] Obtain the real-time weights and values ​​corresponding to all features according to the current feature weight corresponding to each feature;

[0047] Performing a ratio processing on the current feature weight corresponding to each feature and the real-time weight sum value corresponding to all features to obtain a first weight ratio coefficient corresponding to each feature;

[0048] Extract the historical feature weight corresponding to each feature;

[0049] Obtain weight standard deviation and weight average using the historical feature weight corresponding to each feature;

[0050] Performing ratio processing using the weighted standard deviation and the weighted average value to obtain a second weight ratio coefficient;

[0051] The first weight ratio coefficient and the second weight ratio coefficient corresponding to each feature are used to adjust the resolution of the nautical chart data at the multi-layer skeleton data level where the feature is located to obtain the adjusted nautical chart data resolution.

[0052] Furthermore, the convolutional neural network model updates and adjusts its strategy based on the reward signal, including:

[0053] The reward signal is quantified through a symbolic function and fed back into the convolutional neural network model;

[0054] The convolutional neural network model dynamically adjusts the weights of different features based on the reward signal;

[0055] Based on the adjustment of feature weights, the convolutional neural network model further dynamically adjusts the resolution of chart data under different features.

[0056] Furthermore, the convolutional neural network model updates and adjusts the strategy based on the reward signal, including:

[0057] Manually correct the decisions of the convolutional neural network model through the human-computer collaborative intervention interface;

[0058] The convolutional neural network model updates and adjusts its strategy based on the modified intervention behavior.

[0059] Furthermore, the historical electronic chart data is pre-processed, including:

[0060] Convert historical electronic nautical chart data into a unified coordinate system and rasterize them into standardized images of 512×512 pixels;

[0061] Normalize historical electronic chart data and adjust pixel values ​​to an appropriate range;

[0062] Fuse radar image data and achieve spatial registration with electronic nautical charts through affine transformation to generate annotated multimodal training sets;

[0063] The multimodal training set is divided into training set and test set. The convolutional neural network model is trained with the training set, and the performance of the convolutional neural network model is verified with the test set.

[0064] Compared with the prior art, the present invention has the following beneficial effects:

[0065] 1. In the present invention, by pre-setting the weight distribution scheme according to different navigation scenarios and dynamically adjusting the weights of different features according to the specific requirements of the navigation mission, it is ensured that the convolutional neural network model can automatically adjust the importance of features in different navigation scenarios, thereby better adapting to the needs of the navigation mission.

[0066] 2. In the present invention, by establishing a priority mechanism for the weights assigned to coastline characteristics, water depth characteristics, and navigation obstacle characteristics, the method can handle complex navigation scenarios more flexibly, thereby significantly improving the safety and efficiency of navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] Figure 1 This is a flow chart of the multi-scale hierarchical organization method of electronic nautical chart data of the present invention. DETAILED DESCRIPTION

[0068] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0069] In order to solve the technical problem that the traditional multi-scale layered display method in the existing technology usually relies on predefined scale data and is difficult to dynamically adjust the resolution to adapt to different navigation needs, please refer to Figure 1 , this embodiment provides the following technical solutions:

[0070] A multi-scale hierarchical organization method for electronic nautical chart data comprises the following steps:

[0071] Based on the convolutional neural network model, feature information is extracted from historical electronic nautical chart data, including coastline characteristics, water depth and navigation obstacles, including:

[0072] Collect historical electronic nautical chart data, including: high-resolution remote sensing images and related annotation data, which are used to provide detailed coastline features, water depth and navigation obstacles information; pre-process the historical electronic nautical chart data for training the convolutional neural network model, including: converting the historical electronic nautical chart data into a unified WGS-84 coordinate system and rasterizing it into a standardized image of 512×512 pixels; Channel 1 (water depth): Water depth data represents the water depth information at different locations on the chart, usually presented in the form of isobaths or point water depth annotations; it is intended to help mariners assess the water depth conditions in the navigation area and ensure that the ship navigates within a safe water depth to avoid running aground; it is normalized to the range of 0-1, and extreme values ​​(>100m) are truncated; Channel 2 (shoreline): The coastline is the dividing line between land and sea, and is one of the most important geographical information in the electronic nautical chart; it is intended to help mariners determine the relative position of the ship The system identifies the position of navigation obstacles on land to avoid grounding and collision; performs binary processing on it, marking the coastline area as 1 and the rest as 0; Channel 3 (Obstacles): Navigation obstacles include reefs, shipwrecks, shoals, buoys and other objects that may affect the safe navigation of ships; it aims to help sailors identify potential navigation risks and take avoidance measures in advance; the coordinates of navigation obstacles are marked based on the IHOS-57 standard; historical electronic nautical chart data are normalized and the pixel values ​​are adjusted to an appropriate range to improve the efficiency of convolutional neural network model training; radar image data are fused and spatially aligned with the electronic nautical chart through affine transformation to generate a multimodal training set with annotations; the multimodal training set is divided into: training set and test set, the convolutional neural network model is trained with the training set, and the performance of the convolutional neural network model is verified with the test set to ensure the generalization ability and reliability of the convolutional neural network model.

[0073] A multi-scale convolutional neural network model is constructed, utilizing convolutional kernels of varying scales in the convolutional and pooling layers to automatically identify coastline, depth, and navigation obstacle features at varying scales in historical electronic nautical chart data. Feature information at varying scales is crucial for maritime safety and navigation. For example, high-resolution coastline details are crucial for near-shore navigation, while low-resolution depth and obstacle information is suitable for ocean voyages. Fully connected layers are used to adaptively classify and locate different types of coastline, depth, and navigation obstacle features, significantly improving navigation safety and efficiency. Multi-scale fusion of the extracted feature information simultaneously captures obstacle details at varying degrees of precision. This involves concatenating the extracted coastline, depth, and navigation obstacle features at varying scales to form a multi-scale feature map. This allows for the simultaneous capture of both global information and local details, significantly improving the richness and accuracy of feature representation. Feature maps at varying scales are resized to the same size through upsampling and downsampling operations before being fused for subsequent classification and segmentation tasks. This ensures spatial consistency between the feature maps and further optimizes the fusion effect.

[0074] A weight distribution scheme is pre-set based on different navigation scenarios, and the weights of different features are dynamically adjusted according to the specific needs of the navigation mission. The weight adjustment process includes: dynamically adjusting the feature weights by monitoring the ship's yaw and changes in attribute information of the current location, as well as the changes in the current location's coastline data, water depth, navigation obstacles, and weather information. Specifically, it includes:

[0075] Different navigation scenarios are assigned to the extracted coastline features, water depth features, and navigation obstacle features. Different weights are assigned to the coastline features, water depth features, and navigation obstacle features based on their importance to the navigation scenarios. For example, in an emergency collision avoidance mission, the weight of the obstacle feature is increased. Based on maritime navigation needs, a priority mechanism is established for the weights assigned to the coastline features, water depth features, and navigation obstacle features. This includes analyzing the content of the current navigation mission, prioritizing the weights based on the content, and dynamically adjusting the feature weights. For example, in low visibility conditions, the weight of the obstacle feature in the electronic chart data is increased. Analyze the changes in the current navigation scene and divide the weight priority according to the changes in the navigation scene; for example: in the port area, the weight priority of the coastline and obstacle features is higher; when the ship enters the ocean area from the nearshore area, the weight of the water depth feature should be gradually increased; combined with the real-time feedback mechanism, dynamically adjust the feature weight according to the execution of the navigation mission; for example: if it is found that the weight setting of the obstacle feature is unreasonable during a certain voyage, it can be adjusted in time through the feedback mechanism to optimize the effect of feature fusion, ensure that the convolutional neural network model can maintain the best performance in different scenarios, and improve the safety and efficiency of navigation.

[0076] The beneficial effects achieved by the above content are: by dynamically adjusting the feature weights, the convolutional neural network model can more accurately identify and respond to potential risks in navigation; by dynamically adjusting the weights according to different navigation scenarios, the convolutional neural network model can better adapt to the complex navigation environment and improve its robustness and reliability; combined with the real-time feedback mechanism, it ensures that the dynamic adjustment of feature weights can promptly reflect the actual needs of the navigation mission, thereby optimizing the effect of feature fusion; through the above operations, the electronic nautical chart data processing method can flexibly adjust the feature weights according to different navigation scenarios and mission requirements, significantly improving the safety and efficiency of navigation.

[0077] Among them, combined with the real-time feedback mechanism, the feature weights are dynamically adjusted according to the execution of the navigation mission, including:

[0078] collecting first feedback information in real time, the first feedback information including real-time positioning of the current position information of the vessel during navigation, and comparing the current position information of the vessel with a preset navigation route to determine whether there is deviation and the degree of deviation;

[0079] When the ship deviates and the degree of deviation is greater than a preset deviation threshold, it is determined that the attribute information of the current position of the ship has changed, and the attribute information of the ship's position includes features of being close to a coastline, close to a shallow water area, close to a port, or close to a deep water area. The first feature weight is adjusted based on the change in the attribute information of the ship's position;

[0080] During the adjustment of the first feature weight, the corresponding weight assignment interval is retrieved according to the preset attribute information of the ship;

[0081] The second feedback information includes coastline data information, water depth information, navigation obstacle information and weather information under the current position information of the ship in real time.

[0082] At the same time, the coastline data information, water depth information, navigation obstacle information and weather information under the current location information are compared with the reference coastline data information, reference water depth information and reference navigation obstacle information when formulating the preset navigation route, and the change amplitude values ​​are compared. Based on the change amplitude value, the second feature weight is adjusted within the weight assignment range to obtain the adjusted feature weight value.

[0083] The above technical solution is: during the execution of the navigation mission, the navigation route may deviate from the preset route due to changes in the environment or weather. Therefore, after the preset navigation route, a feedback mechanism needs to be set. The first feedback information is the current position information of the ship. The change of the ship's position information is the most important factor in navigation. There are many cases where the position deviates from the preset route during navigation. Some are active deviations, and some are passive or accidental deviations. In either case, the weight distribution of the features set based on the preset route will be biased or problematic. Therefore, when the current position information of the ship deviates from the preset route, it is first necessary to determine whether the ship's attribute information has changed. The ship's attribute information generally includes features close to the coastline, close to shallow waters, close to ports or close to deep waters, etc. Different The attribute information of the ship will cause the weight value of the pre-set feature to change. For example, if it is sailing close to the coastline, the weight of the coastline feature will increase. If it is close to the deep water area, the weight of the water depth feature and the obstacle feature will increase. The attribute information of the ship and the weight range of the general feature are pre-set. If the attribute information of the ship changes, the first feature weight adjustment is performed first. The first feature weight adjustment is to adjust the approximate weight emphasis direction of each feature based on the attribute information of the ship. At this time, the weight assignment range of each feature can be obtained. That is to say, the attribute information of the ship determines the approximate weight emphasis direction of each feature, but does not determine the specific weight value of each feature. Only a weight assignment range is given. The adjustment of the specific weight value of each feature needs to consider more factors.

[0084] Under this premise, the second feedback information is collected in real time, including coastline data information, water depth information, navigation obstacle information and weather information under the current position information of the ship. If the change range of this information is large compared with the reference coastline data information, reference water depth information and reference navigation obstacle information when formulating the preset navigation route, it is necessary to adjust the second feature weight within the weight assignment range based on the magnitude of the change to obtain the adjusted feature weight value. The adjusted feature weight value is the result value of the dynamic adjustment. The above technical solution can monitor the preset navigation route in real time through the feedback mechanism, dynamically adjust the feature weight value based on the actual navigation situation, adapt to changes in the environment and tasks, and has good flexibility.

[0085] A reward function is used to divide historical electronic nautical chart data into multiple layers of skeleton data according to their usage. Based on feature weights, the resolution of different features is dynamically adjusted. The resolution adjustment process includes real-time monitoring of the number of emergency events in the navigation scene. When the threshold is exceeded, the weight ratio coefficient is calculated by combining the current feature weight and the historical feature weight. The resolution of the chart data at different layers in the multi-layer skeleton data is adjusted accordingly. Specifically,

[0086] By introducing a reward function into the convolutional neural network model, it is evaluated whether the behavior of the convolutional neural network model meets the needs of the current navigation mission; for example, for key channel obstacles, the reward function can be designed to give positive rewards when the obstacles are upgraded to a higher precision level, and negative rewards otherwise; according to the current navigation scenario, the importance of different feature information is analyzed as the basis for dividing weight priorities; for example, when sailing near the coast, the weights of coastline and obstacle features should be higher; and when sailing in the open ocean, the weight of water depth features should be higher; using the reward function, historical electronic nautical chart data is divided into multiple layers of skeleton data according to the current navigation scenario and the purpose of the navigation mission; for example, high-precision coastline data can be used as one layer, medium-precision water depth data as another layer, and low-precision obstacle data as the third layer; based on the dynamically adjusted feature weights, combined with the specific needs of the current navigation mission, the resolution of the chart data at different levels in the multi-layer skeleton data is dynamically adjusted; for example, the resolution is adjusted from 1:500,000 to 1:10,000 to adapt to different navigation scenarios; and then according to the specific needs of the navigation mission, the resolution of the chart data at different scales is dynamically adjusted; for example, in When sailing near the coast, the resolution of the coastline data is increased; when sailing in the open ocean, the model can reduce the resolution of the coastline data while increasing the resolution of the water depth data. Based on the adaptability of the adjusted chart data resolution to the task, a reward signal is issued based on the reward function, and the convolutional neural network model updates and adjusts the strategy according to the reward signal, including: quantizing the reward signal through a sign function and feeding it back to the convolutional neural network model. For example, if the adjusted chart data resolution is closer to the task requirements, a positive reward is given; if the adjusted chart data resolution deviates from the task requirements, a negative reward is given. Based on the reward signal, the convolutional neural network model dynamically adjusts the weights of different features, such as coastline features, water depth, and navigation obstacles. For example, if the convolutional neural network model finds that increasing the weight of a certain feature can obtain a higher reward, it will automatically adjust the weight of that feature. Based on the adjustment of feature weights, the convolutional neural network model further dynamically adjusts the chart data resolution under different features. For example, if the reward signal indicates that increasing the resolution of key waterway obstacles can better adapt to the task requirements, the convolutional neural network model will automatically increase the resolution of that feature.

[0087] Also includes:

[0088] Through the human-machine collaborative intervention interface, the decisions of the convolutional neural network model can be manually corrected. For example, if the seafarer finds that the model has improperly adjusted the resolution of a key obstacle, the seafarer can manually correct it. The convolutional neural network model updates its adjustment strategy based on the modified intervention behavior to improve the accuracy of future decisions. Based on this, not only the adaptability and flexibility of the convolutional neural network model are improved, but also the seafarers' trust and understanding of the model's decisions are enhanced. At the same time, through real-time feedback and manual corrections, the convolutional neural network model can continuously optimize its decision-making process to ensure reliability and safety in complex navigation environments.

[0089] The verified convolutional neural network model is applied to actual navigation.

[0090] The beneficial effects achieved by the above content are: by pre-setting weight distribution schemes according to different navigation scenarios and dynamically adjusting the weights of different features according to the specific needs of the navigation mission; ensuring that the convolutional neural network model can automatically adjust the importance of features in different navigation scenarios to better adapt to the needs of the navigation mission; and by establishing a priority mechanism for the weights assigned to coastline characteristics, water depth characteristics and navigation obstacle characteristics, the method can handle complex navigation scenarios more flexibly, thereby significantly improving the safety and efficiency of navigation.

[0091] Working principle: By constructing a multi-scale convolutional neural network model, it automatically identifies and splices the coastline features, water depth features and navigation obstacle features in historical electronic nautical chart data to form a multi-scale feature map; pre-set weight distribution schemes according to different navigation scenarios, and assign different weights to coastline features, water depth features and navigation obstacle features; dynamically adjust the weights of different features according to the specific needs of the navigation mission; and dynamically adjust the chart data resolution of different levels in the multi-layer skeleton data in combination with the specific needs of the current navigation mission; thereby ensuring that the method can effectively adapt to different navigation scenarios and mission requirements, and significantly improve the safety and efficiency of navigation.

[0092] It also includes: after dynamically adjusting the resolution of different layers of chart data in the multi-layer skeleton data, real-time monitoring of the number of emergency events in different navigation scenarios, and compensation based on the dynamically adjusted resolution according to the number of emergency events, including:

[0093] Real-time monitoring of the number of emergency events occurring in different navigation scenarios; wherein the emergency events include coastline mutation events, rapid water depth change events, sudden appearance of navigation obstacles events, and emergency avoidance events caused by incorrect navigation obstacle location information; and the coastline mutation events are related to the coastline characteristics; the rapid water depth change events are related to the water depth characteristics; the sudden appearance of navigation obstacles events and emergency avoidance events caused by incorrect navigation obstacle location information are related to the navigation obstacle characteristics;

[0094] When the number of emergency events exceeds the preset emergency event threshold, the current feature weight corresponding to each feature is retrieved in real time;

[0095] Obtain the real-time weights and values ​​corresponding to all features according to the current feature weight corresponding to each feature;

[0096] Performing a ratio processing on the current feature weight corresponding to each feature and the real-time weight sum value corresponding to all features to obtain a first weight ratio coefficient corresponding to each feature;

[0097] Extract the historical feature weight corresponding to each feature;

[0098] Obtain weight standard deviation and weight average using the historical feature weight corresponding to each feature;

[0099] Performing ratio processing using the weighted standard deviation and the weighted average value to obtain a second weight ratio coefficient;

[0100] Adjusting the resolution of the nautical chart data at the multi-layer skeleton data level where the feature is located using the first weight ratio coefficient and the second weight ratio coefficient corresponding to each feature to obtain an adjusted nautical chart data resolution;

[0101] The adjusted chart data resolution is obtained by the following formula:

[0102]

[0103] Among them, R represents the adjusted chart data resolution; R b represents the resolution of the chart data before adjustment; n represents the number of features contained in each layer of skeleton data; W 01i Represents the first weight ratio coefficient corresponding to the i-th feature; W 02i represents the second weight ratio coefficient corresponding to the i-th feature; a represents the resolution sensitivity coefficient, and the value range of the resolution sensitivity coefficient is 0.6-1.2; b represents the emergency gain coefficient, and the value range of the emergency gain coefficient is 0.38-0.53; S i Indicates the number of times the i-th feature participates in all emergency events; Sz Indicates the total number of emergency events. The greater the effect of this part on the resolution adjustment, the greater the effect of this part on the resolution adjustment. The overall part represents the additional gain of the resolution adjustment under the consideration of emergency events and feature-related weight factors. This calculation step is to take the first weight ratio coefficient Perform a power operation to magnify or reduce the influence of the first weight ratio coefficient on the final chart data resolution adjustment. The formula comprehensively considers the current weight of the feature (through W 01i ), the historical discreteness of feature weights (through ), the participation of features in emergency events (through S i and S z ) as well as multiple factors such as sensitivity coefficient a and gain coefficient b. Resolution compensation adjustment is not based on a single factor, but rather comprehensively weighs the impact of various factors on the navigation mission, resulting in more reasonable adjustments that better meet practical needs. Adjustments are made flexibly by setting the value ranges for the resolution sensitivity coefficient a and the emergency gain coefficient b, and by utilizing different weighting coefficients and the number of feature participation correlations. Parameters can be appropriately set based on different navigation scenarios, mission requirements, and desired resolution adjustments, effectively controlling the degree of resolution compensation adjustment to meet diverse application requirements.

[0104] The technical effect of the above-mentioned technical solution is as follows: During navigation, the resolution of the chart data at different levels within the multi-layer skeleton data is first dynamically adjusted. This is a basic adjustment, setting an appropriate resolution for general navigation conditions. The system continuously monitors the number of emergency events in different navigation scenarios in real time, including sudden coastline changes, rapid changes in water depth, the sudden appearance of navigation obstacles, and emergency avoidance due to erroneous obstacle location information. These emergency events can have a significant impact on navigation safety and require a timely system response. The number of monitored emergency events is compared with a preset emergency event threshold. If the number of emergency events does not exceed the threshold, the system maintains the current resolution and other conditions. If it does, the current navigation situation is complex and requires compensatory resolution adjustments, entering the subsequent adjustment process. First weight ratio coefficient calculation: The current feature weight corresponding to each feature is retrieved in real time, the real-time weight sum of all features is calculated, and the current weight of each feature is then compared with the real-time weight sum to obtain the first weight ratio coefficient corresponding to each feature. This coefficient reflects the relative proportion of each feature weight in the overall weight, reflecting the importance of the current feature. The historical feature weight corresponding to each feature is extracted. The weight standard deviation and weight average are calculated based on the historical weights. The weight standard deviation is then compared with the weight average to obtain a second weight ratio coefficient. This coefficient reflects the degree of dispersion of the feature's historical weight and reflects the stability of the feature weight. Using the obtained first and second weight ratio coefficients, the chart data resolution of the multi-layer skeleton data layer where the feature resides is adjusted. Taking into account factors such as the current importance of the feature and the stability of the historical weight, the adjusted chart data resolution is obtained, allowing the chart data to be presented at a more appropriate resolution, assisting navigation decision-making and ensuring navigation safety. Among the aforementioned emergencies, sudden shoreline changes refer to sudden changes in shoreline shape during navigation due to natural disasters such as earthquakes, tsunamis, and landslides. These changes can include shoreline collapse, the formation of new islands, or the disappearance of existing islands. These events are directly related to shoreline characteristics, and such changes can render previously safe waterways dangerous. Rapid water depth changes refer to sudden, short-term changes in water depth in a specific sea area due to changes in seafloor topography (such as submarine volcanic eruptions and mudslides) or abnormal tides. These changes can include sudden deepening of shallow waters or shallowing of deep waters. These events are directly related to water depth characteristics. Changes in water depth can directly impact ship navigation safety, such as increased grounding risk or changes in navigation resistance. Sudden navigation obstacle appearances refer to the sudden discovery of previously nonexistent obstacles during navigation, such as sunken ships, floating debris, unmarked reefs, or submerged rocks. These events are directly related to the characteristics of the obstacles. The appearance of these obstacles can pose a serious threat to ship navigation safety, requiring immediate avoidance measures. An emergency avoidance incident caused by incorrect navigation obstacle location information refers to inaccurate navigation obstacle location information due to errors or untimely updates of electronic nautical chart data.When approaching these obstacles, vessels discover that the actual situation does not match the nautical chart, and they need to make an emergency avoidance, which is directly related to the characteristics of the navigation obstacle. This emergency situation requires the ship to respond quickly, and may require re-planning the route based on the characteristics of the coastline and water depth.

[0105] The above technical solution can dynamically adjust the resolution of the chart data based on whether the number of emergency events exceeds the threshold and the feature weight. When an emergency occurs, the system can be adjusted according to the specific needs of the navigation task, taking into account the participation of different features in the emergency, thereby improving the system's adaptability to complex and changeable navigation scenes and better meeting the actual task requirements. By calculating various ratio coefficients of feature weights (first weight ratio coefficient, second weight ratio coefficient), the resolution is adjusted based on multiple factors. Compared with fixed resolution or simple adjustment methods, the resolution of the chart data can be adjusted more accurately according to the importance of features and the situation of emergency events, so that the chart data presentation is more in line with the actual task and the accuracy of data use is improved. Retrieve feature weights in real time and make adjustments based on them to ensure that the system can respond to changes in emergency events and feature weights in a timely manner, quickly adjust the resolution of the chart data, meet the real-time requirements of navigation tasks, and enable navigation decisions to be based on more timely and accurate data. Compensate for resolution using the dynamic weight coefficients corresponding to the emergency events combined with the features. According to the participation of different features in the emergency (through S i and S z The system uses a combination of feature weights (first and second weight ratio coefficients) to optimize and scientifically adjust resolution compensation, avoiding over- or under-adjustment. Resolution adjustments are made to chart data at different levels within the multi-layer skeleton data, taking into account the data's hierarchical structure. Combined with feature weights, this allows for more refined resolution adjustments at each level, ensuring that data at all levels is presented at the appropriate resolution during emergencies, improving overall data display and usability.

[0106] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "including," "having," or any other variations thereof are intended to cover non-exclusive possessors, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or includes elements that are inherent to such process, method, article, or apparatus.

[0107] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that changes, modifications, substitutions, and alterations may be made to the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A multi-scale hierarchical organization method for electronic nautical chart data, characterized in that: The method comprises the following steps: Extract feature information from historical electronic nautical chart data based on a convolutional neural network model, including coastline features, water depth, and navigation obstacles; Perform multi-scale fusion on the extracted feature information to capture obstacle details with different accuracies at the same time; A weight distribution scheme is pre-set based on different navigation scenarios, and the weights of different features are dynamically adjusted according to the specific needs of the navigation mission. The weight adjustment process includes: dynamically adjusting the feature weights by monitoring the ship's yaw and changes in attribute information of the current location, as well as the changes in the current location's coastline data, water depth, navigation obstacles and weather information; A reward function is used to divide historical electronic nautical chart data into multiple layers of skeleton data based on their intended use. The resolution of different features is dynamically adjusted based on feature weights. The resolution adjustment process involves real-time monitoring of the number of emergency events in navigation scenarios. When a threshold is exceeded, the current feature weight and historical feature weight are combined to calculate a weight ratio coefficient, and the resolution of the chart data at different layers in the multi-layer skeleton data is adjusted accordingly. After dynamically adjusting the resolution of chart data at different levels in the multi-layer skeleton data, the number of emergencies in different navigation scenarios is monitored in real time, and compensation is made based on the dynamically adjusted resolution according to the number of emergencies, including: Real-time monitoring of the number of emergency events occurring in different navigation scenarios; wherein the emergency events include coastline mutation events, rapid water depth change events, sudden appearance of navigation obstacles events, and emergency avoidance events caused by incorrect navigation obstacle location information; and the coastline mutation events are related to the coastline characteristics; the rapid water depth change events are related to the water depth characteristics; the sudden appearance of navigation obstacles events and emergency avoidance events caused by incorrect navigation obstacle location information are related to the navigation obstacle characteristics; When the number of emergency events exceeds the preset emergency event threshold, the current feature weight corresponding to each feature is retrieved in real time; Obtain the real-time weights and values ​​corresponding to all features according to the current feature weight corresponding to each feature; Performing a ratio processing on the current feature weight corresponding to each feature and the real-time weight sum value corresponding to all features to obtain a first weight ratio coefficient corresponding to each feature; Extract the historical feature weight corresponding to each feature; Obtain weight standard deviation and weight average using the historical feature weight corresponding to each feature; Performing ratio processing using the weighted standard deviation and the weighted average value to obtain a second weight ratio coefficient; Adjusting the resolution of the nautical chart data at the multi-layer skeleton data level where the feature is located using the first weight ratio coefficient and the second weight ratio coefficient corresponding to each feature to obtain an adjusted nautical chart data resolution; The verified convolutional neural network model is applied to actual navigation.

2. The multi-scale hierarchical organization method for electronic nautical chart data according to claim 1, characterized in that: Extract feature information from historical electronic chart data based on the convolutional neural network model, including: Collect historical electronic nautical chart data, including high-resolution remote sensing images and associated annotation data; Preprocess historical electronic chart data for training convolutional neural network models; including: Convert historical electronic nautical chart data into a unified coordinate system and rasterize them into standardized images of 512×512 pixels; Normalize historical electronic chart data and adjust pixel values ​​to an appropriate range; Fuse radar image data and achieve spatial registration with electronic nautical charts through affine transformation to generate annotated multimodal training sets; Divide the multimodal training set into a training set and a test set. Use the training set to train the convolutional neural network model, and use the test set to verify the performance of the convolutional neural network model. Construct a multi-scale convolutional neural network model, using convolutional kernels of different scales in the convolutional and pooling layers to automatically identify coastline features, water depth features, and navigation obstacle features of different scales in historical electronic nautical chart data; Different types of coastline features, water depth features, and navigation obstacle features are adaptively classified and located through the fully connected layer.

3. The multi-scale hierarchical organization method for electronic nautical chart data according to claim 2, characterized in that: The extracted feature information is fused at multiple scales, including: The coastline features, water depth features and navigation obstacle features extracted at different scales are spliced ​​together to form a multi-scale feature map; Through upsampling and downsampling operations, feature maps of different scales are adjusted to the same size and then fused for subsequent classification and segmentation tasks.

4. The multi-scale hierarchical organization method for electronic nautical chart data according to claim 3, characterized in that: Preset weight distribution schemes based on different navigation scenarios, and dynamically adjust the weights of different features based on the specific needs of the navigation mission, including: Assign different navigation scenarios to the extracted coastline features, water depth features and navigation obstacle features; Different weights are assigned based on the importance of the corresponding navigation scenarios of coastline characteristics, water depth characteristics and navigation obstacle characteristics; Establish a priority mechanism for assigning weights to coastline characteristics, water depth characteristics, and navigation obstacle characteristics based on maritime navigation needs; Combined with the real-time feedback mechanism, the feature weights are dynamically adjusted according to the execution of the navigation mission.

5. The multi-scale hierarchical organization method for electronic nautical chart data according to claim 4, characterized in that: Combined with the real-time feedback mechanism, the feature weights are dynamically adjusted according to the execution of the navigation mission, including: collecting first feedback information in real time, the first feedback information including real-time positioning of the current position information of the vessel during navigation, and comparing the current position information of the vessel with a preset navigation route to determine whether there is deviation and the degree of deviation; When the ship deviates and the degree of deviation is greater than a preset deviation threshold, it is determined that the attribute information of the current position of the ship has changed, and the attribute information of the ship's position includes features of being close to a coastline, close to a shallow water area, close to a port, or close to a deep water area. The first feature weight is adjusted based on the change in the attribute information of the ship's position; During the adjustment of the first feature weight, the corresponding weight assignment interval is retrieved according to the preset attribute information of the ship; collecting second feedback information in real time, the second feedback information including coastline data information, water depth information, navigation obstacle information, and weather information under the current position information of the ship; At the same time, the coastline data information, water depth information, navigation obstacle information and weather information under the current location information are compared with the reference coastline data information, reference water depth information and reference navigation obstacle information when formulating the preset navigation route, and the change amplitude values ​​are compared. Based on the change amplitude value, the second feature weight is adjusted within the weight assignment range to obtain the adjusted feature weight value.

6. The multi-scale hierarchical organization method for electronic nautical chart data according to claim 4, characterized in that: Based on HNA requirements, a priority mechanism is established to assign weights to coastline characteristics, water depth characteristics, and navigation obstacle characteristics, including: Analyze the content of the current navigation mission, prioritize the weights based on the content, and dynamically adjust the feature weights; Analyze the changes in the current navigation scene and divide the weight priorities according to the changes in the navigation scene.

7. The multi-scale hierarchical organization method for electronic nautical chart data according to claim 4, characterized in that: The reward function is used to divide the historical electronic chart data into multiple layers of skeleton data according to their usage, including: By introducing a reward function into the convolutional neural network model, we evaluate whether the behavior of the convolutional neural network model meets the requirements of the current navigation task; Analyze the importance of different feature information according to the current navigation scenario as the basis for dividing weight priorities; The reward function is used to divide the historical electronic nautical chart data into multiple layers of skeleton data according to the current navigation scene and navigation mission purpose.

8. The multi-scale hierarchical organization method for electronic nautical chart data according to claim 7, characterized in that: Based on feature weights, the resolution of different features is dynamically adjusted, including: Based on the dynamically adjusted feature weights and the specific needs of the current navigation mission, the resolution of the chart data at different levels in the multi-layer skeleton data is dynamically adjusted; Then, according to the specific needs of the navigation mission, the resolution of the chart data at different scales is dynamically adjusted; According to the adaptability of the adjusted chart data resolution to the task, a reward signal is sent based on the reward function, and the convolutional neural network model updates the adjustment strategy according to the reward signal.

9. The multi-scale hierarchical organization method for electronic nautical chart data according to claim 8, characterized in that: The convolutional neural network model updates and adjusts its strategy based on the reward signal, including: The reward signal is quantified through a symbolic function and fed back into the convolutional neural network model; The convolutional neural network model dynamically adjusts the weights of different features based on the reward signal; Based on the adjustment of feature weights, the convolutional neural network model further dynamically adjusts the resolution of chart data under different features; Also includes: Manually correct the decisions of the convolutional neural network model through the human-computer collaborative intervention interface; The convolutional neural network model updates and adjusts its strategy based on the modified intervention behavior.

Images