Beacon light optical signal intelligent adjusting method and system

Abstract

The invention relates to the technical field of beacon light light intelligent adjustment, in particular to a beacon light light signal intelligent adjustment method and system, and the method comprises the following steps: collecting environment brightness, ship approaching conditions and ship size data in real time through a sensor, and connecting the sensor to a central control board; sensor data are integrated, and the current environment brightness and the existence and size of ships are analyzed; based on the obtained size data of the ships, the sizes of the ships are classified, and based on a neural network model, the sizes of the ships are classified; ship position and speed information collected by radar data is synchronized with data of an image recognition system and an ambient light sensor; and combining the ship position information, the speed information, the ship size information and the current light intensity information to intelligently adjust the light signal of the beacon light. The environment brightness is monitored in real time, the light intensity can be automatically adjusted, and it is ensured that the light of the beacon light is clearly visible in various illumination environments.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent regulation of navigation beacon lights, and in particular to a method and system for intelligent regulation of navigation beacon light signals. Background Art

[0002] Navigation lights are usually installed in or near navigable waters to indicate the size, direction, wiring and various underwater or surface obstacles of navigable waters. They are used for ship positioning, navigation and other special purposes. They provide reliable navigation safety conditions for water transportation, fisheries, marine development, and the establishment of safe and economic channels on the sea and inland rivers.

[0003] As an important aid to navigation at sea, traditional beacon lights have a fixed luminous intensity. In order to meet the farthest effective distance, the beacon lights always emit the set light intensity according to the farthest effective distance, which is not conducive to energy conservation and will also cause light pollution to the surrounding environment, especially at night. For large ships, due to their large inertia and high bridge, they need to obtain light signals at a farther distance to make corresponding actions in advance to ensure the safe navigation of the ship. Therefore, large ships have higher requirements for the sight distance of beacon lights and stronger beacon lights. For small ships, due to their small inertia, flexible navigation and low bridge, lights with a large range are prone to glare, which is not conducive to ship navigation. The demand for beacon light intensity is not as high as that of large ships. In order to meet the farthest effective distance, traditional beacon light signals always emit light according to the set range when they are working. They still work normally even when there are no ships passing by, which is not conducive to energy conservation. Summary of the invention

[0004] The present invention aims at the technical problems existing in the prior art and provides a method and system for intelligently adjusting a navigation light signal.

[0005] The technical solution of the present invention to solve the above technical problems is as follows: a method for intelligently adjusting a navigation light signal, comprising the following steps:

[0006] S101, collect data on ambient brightness, vessel approach and vessel size in real time through sensors, and connect the sensors to a central console;

[0007] S102, integrating sensor data and analyzing the current environment brightness, the presence and size of ships;

[0008] S103, based on the acquired ship size data, classifying the ship sizes according to the number of pixels occupied by the ship in the image, and classifying the ship sizes based on a neural network model;

[0009] S104, synchronizing the ship position and speed information collected by the radar data with the data of the image recognition system and the ambient light sensor;

[0010] S105, intelligently adjust the navigation light signal based on the ship's position information, speed information, ship size information, and current light intensity information.

[0011] In a preferred embodiment, in S101, an ambient light sensor, an image recognition system and a radar device are installed in the monitoring area, and the ambient light sensor, the image recognition system and the radar device are connected to the central control console. The ambient brightness is monitored by the ambient light sensor, and the ships approaching the monitoring area and their sizes are identified and tracked by the image recognition system. The position and speed information of the ships are monitored by the radar. The collected ambient brightness data, the ship image and the position and speed information of the ship are transmitted to the central control console, and the central control console receives and stores the data transmitted from the ambient light sensor, the image recognition system and the radar device in real time, and performs real-time data analysis.

[0012] In a preferred embodiment, in S102, data streams from the ambient light sensor, the image recognition system, and the radar are received, data synchronization is ensured, and timestamps are used to align data from different sources. The light intensity is calculated based on the data from the ambient light sensor using the following formula:

[0013]

[0014] Where L represents the light intensity, L max and L min Respectively represent the maximum and minimum light intensity, I represents the ambient brightness, I0 represents the intermediate brightness value, and k represents the adjustment parameter. By receiving the image information transmitted by the image recognition system, the image information is first binarized, and the image after the binarization operation is subjected to noise reduction processing to improve the image quality, adjust the image contrast, ensure that the ship is distinguished from the background, and use the non-local mean denoising algorithm to reduce image noise by using the self-similarity in the image. The specific steps are as follows:

[0015] For any pixel i in the image, its grayscale value is represented as v(i). First, the similarity between pixel i and pixel j is calculated. The specific calculation formula is as follows:

[0016]

[0017] Among them, N i and N j denote the neighborhoods centered on pixels i and j, respectively, ||·|| denotes the square of the Euclidean distance between two neighborhoods, and h denotes the parameter that controls the decay speed of the exponential function;

[0018] The calculated similarity weights are normalized. For each pixel i, the calculated weight w(i, j) is normalized so that the sum of all weights is 1. The specific calculation formula is as follows:

[0019]

[0020] Using the normalized weights, the denoised pixel values ​​are calculated by weighted average. The specific calculation formula is as follows:

[0021]

[0022] Where NL(v)(i) represents the value of pixel i after denoising, and v(j) represents the value of pixel j in the original image;

[0023] The denoised image data is subjected to contrast enhancement processing. The denoised image is evenly divided into several blocks. Histogram equalization is performed on each block to enhance the local contrast. The specific calculation formula is as follows:

[0024] s=(L-1)·CDF(r)

[0025] Among them, r represents the pixel value of the original image, s represents the pixel value after transformation, and L represents the number of possible pixel levels. The histogram of each block is clipped to limit the number of occurrences of the maximum pixel value. A threshold T is set and the pixel values ​​exceeding the threshold are clipped. The specific calculation formula is as follows:

[0026] H'(i)=min(H(i),T)

[0027] Among them, H(i) represents the number of pixel values ​​in the original histogram, H'(i) represents the cropped histogram, and bilinear interpolation is performed on the processed block boundaries to ensure the visual coherence of the image. The specific calculation formula is as follows:

[0028]

[0029] Where x, y represent the coordinates of the target pixel, (x0, y0)(x1, y0)(x0, y1)(x1, y1) represent the coordinates of the four neighboring pixels surrounding the target pixel, f(x, y) represents the value of the target pixel, and f(x0, y0)(x1, y0)(x0, y1)(x1, y1) represent the values ​​of the four neighboring pixels. The value of the target pixel is obtained by calculating the weighted average of the four known pixels around the target pixel. Bilinear interpolation can effectively smooth the image and reduce the pixelation effect when the image is reduced.

[0030] The Canny edge detection algorithm is used to identify the edge of the ship, and the Sobel operator is used to calculate the gradient amplitude M and direction θ of the image. The specific calculation formula is as follows:

[0031]

[0032] Among them, G x and G y Represent the gradients along the x and y directions respectively, retain the local maximum value in the gradient amplitude to refine the edge, and use a high threshold t high and the low threshold t low To determine the edge, the specific calculation formula is as follows:

[0033]

[0034] Among them, when M is greater than the high threshold t high , then the pixel is considered to be a strong edge and is marked as an edge pixel. When M is less than the low threshold t low , then the pixel is considered not to be an edge and is excluded from the edge candidates. low and t high If the pixel is between , the pixel is a weak edge candidate. Connect the pixel points detected as edge pixels to obtain the edge pixels of the ship.

[0035] According to the number of pixels of the segmented ship image, the camera calibration parameters are used to convert the number of pixels into the actual area. The specific calculation formula is as follows:

[0036]

[0037] Among them, reality represents the actual area, pixel area Indicates pixel area, prime number Indicates the total number of pixels, actual area It indicates the actual navigation area. According to the position and viewing angle of the ship in the image, the viewing angle correction is performed to accurately estimate the actual size of the ship.

[0038] In a preferred embodiment, in S103, an image dataset containing ships of different sizes is obtained and input into a neural network model to predict the size of the ship, which specifically includes the following steps:

[0039] In the forward propagation stage, the image data set is forward propagated through each layer of the neural network to obtain the predicted output. For each neuron, its input is the weighted sum of the output of the previous layer plus the bias term, and the output is obtained through the activation function. The specific calculation formula is as follows:

[0040] z [l+1] =W [l] a[l] +b [l]

[0041] a [l+1] =σ(z [l+1] )

[0042] Among them, a [l] represents the output of the lth layer, W [l] and b [l] are the weight matrix and bias vector of the lth layer, σ represents the activation function;

[0043] According to the difference between the predicted output and the true label, the loss function is calculated. The specific calculation formula is as follows:

[0044]

[0045] Among them, C represents the number of categories, yi represents the true label, represents the predicted probability;

[0046] The gradient of the loss with respect to each parameter is calculated by the back-propagation algorithm. For the gradient of weights and biases, the calculation formula is:

[0047]

[0048] Among them, L represents the loss function, which measures the difference between the model prediction and the true label, and W [l] represents the weight matrix of the lth layer, z [l+1] represents the weighted input of the l+1th layer, δ [l+1] represents the error term of the l+1th layer, a [l] represents the output of layer l, (a [l] ) T represents the transpose of the output of layer l, b [l] Represents the bias vector of the lth layer;

[0049] Use the optimization algorithm to update the neural network parameters. The specific calculation formula is as follows:

[0050]

[0051] Among them, W [l] represents the weight matrix of the lth layer, η represents the learning rate, represents the gradient of the loss function with respect to the weight of the lth layer, b [l] represents the bias vector of the lth layer, Represents the gradient of the loss function with respect to the bias of the lth layer.

[0052] In a preferred embodiment, in S104, the position of the vessel is obtained by using a radar signal transmitted to the vessel by a radar, and the specific calculation formula is as follows:

[0053]

[0054] Among them, length represents the pulse length. A short pulse length means a short distance to the ship. Light represents the speed of light, which is used to calculate the time it takes for the radar wave to travel to and from the ship target. The speed at which the radar wave propagates in the air is used to calculate the distance to the ship. The specific calculation formula is as follows:

[0055]

[0056] Where C is the speed of light, t is the round trip time of the signal, and the speed of the ship is calculated by using the difference between two consecutive measurements of the ship's distance. The specific calculation formula is as follows:

[0057]

[0058] Among them, R current The currently measured distance, R previous It represents the distance of the previous measurement, and time represents the distance difference between two consecutive measurements, which reflects the moving distance of the target in the time interval between two measurements. The ship position and speed information monitored by the radar is matched with the ship size data in the image recognition system to obtain the ship size data and ship operation information.

[0059] In a preferred embodiment, in S105, the vessel position information, speed information, vessel size information and current light intensity are integrated in the central console, and the light warning required for the vessel is evaluated according to the vessel's position, speed and size. The risk score of each vessel is calculated using the collected data, and the specific calculation formula is as follows:

[0060]

[0061] Among them, D max represents the maximum distance, α, β, γ, δ represent the weight coefficients of each factor, D represents the distance of the ship, V represents the speed of the ship, S represents the size of the ship, W represents the weather conditions, C represents the sea conditions, V represents the crit represents the critical speed threshold, which is used to determine whether the speed of the ship exceeds the safety threshold. η represents the attenuation factor, which is used to control the growth rate of the risk of the speed exceeding the critical value. The risk assessment result is input into the lighting adjustment algorithm to automatically adjust the intensity and color of the navigation mark light. The specific calculation formula of the lighting adjustment algorithm is as follows:

[0062]

[0063] Among them, if R<0.3 means that the risk score of the ship is less than 0.3, which is a low risk; if 0.3≤R<0.7 means that the risk score of the ship is greater than or equal to 0.3 and less than 0.7, which is a medium risk; if R≥0.7 means that the risk score of the ship is greater than or equal to 0.7, which is a high risk. According to the warning level, the corresponding light intensity is determined, and the determined light intensity is sent to the central console for execution. The central console is monitored, real-time feedback information is collected, and the light intensity is adjusted.

[0064] The present invention also provides a navigation beacon light signal intelligent adjustment system, comprising:

[0065] Data collection module: collects ambient brightness, vessel approach and vessel size data in real time through sensors, and connects the sensors to the central console;

[0066] Data analysis module: integrates sensor data and analyzes the current environment brightness, the presence and size of ships;

[0067] Data classification module: Based on the acquired ship size data, the ship size is classified according to the number of pixels occupied by the ship in the image, and the ship size is classified based on the neural network model;

[0068] Speed ​​Detection Module: Synchronizes the ship position and speed information collected by radar data with the data from the image recognition system and ambient light sensor;

[0069] Intelligent adjustment module: intelligently adjusts the navigation light signal based on the ship's position information, speed information, ship size information and current light intensity information.

[0070] The beneficial effects of the present invention are as follows: by monitoring the ambient brightness, the present invention can automatically adjust the light intensity to ensure that the navigation light is clearly visible in various lighting environments; according to the approach of the ship and the size of the ship, the light warning level is dynamically adjusted to warn the ship in advance of possible risks; combined with the position, speed and size information of the ship, the system can more accurately assess the risk, adjust the light signal in time, and remind the ship to take appropriate action; through the automatic adjustment of the light, the links requiring human intervention are reduced, and the risks caused by improper human operation are reduced; through the intelligent adjustment of the light intensity, the brightness is increased only when necessary, and energy waste is reduced; remote monitoring and management are achieved through the central control console, which improves management efficiency, and provides more timely and accurate navigation assistance for sailing ships, thereby improving the overall safety and efficiency of navigation. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] Figure 1 is a flow chart of the present invention;

[0072] Figure 2It is a system block diagram of the present invention. DETAILED DESCRIPTION

[0073] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0074] In the description of this application, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of this application, "plurality" means two or more, unless otherwise clearly and specifically defined.

[0075] In the description of the present application, the term "for example" is used to mean "used as an example, illustration or description". Any embodiment described as "for example" in the present application is not necessarily to be construed as being more preferred or advantageous than other embodiments. The following description is given to enable any technician in the field to implement and use the present invention. In the following description, details are listed for the purpose of explanation. It should be understood that a person of ordinary skill in the art can recognize that the present invention can be implemented without using these specific details. In other examples, well-known structures and processes will not be elaborated in detail to avoid unnecessary details to obscure the description of the present invention. Therefore, the present invention is not intended to be limited to the embodiments shown, but is consistent with the widest scope consistent with the principles and features disclosed in the present application.

[0076] like Figure 1 This embodiment provides: a method for intelligently adjusting a navigation light signal, which specifically includes the following steps:

[0077] S101, collect data on ambient brightness, vessel approach and vessel size in real time through sensors, and connect the sensors to a central console;

[0078] Furthermore, an ambient light sensor, an image recognition system and a radar device are installed in the monitoring area, and the ambient light sensor, the image recognition system and the radar device are connected to the central control console. The ambient brightness is monitored by the ambient light sensor, and the ships approaching the monitoring area and their sizes are identified and tracked by the image recognition system. The position and speed information of the ships are monitored by the radar. The collected ambient brightness data, the ship image and the position and speed information of the ship are transmitted to the central control console, which receives and stores the data transmitted from the ambient light sensor, the image recognition system and the radar device in real time, and performs real-time data analysis.

[0079] It should be noted that the ambient light sensor is installed at a position that can represent the overall light level of the monitoring area, the camera is installed at a high place that can cover the entire monitoring area, and the radar is installed in an area that can capture the movement trajectory of the ship.

[0080] S102, integrating sensor data and analyzing the current environment brightness, the presence and size of ships;

[0081] Furthermore, the data streams from the ambient light sensor, image recognition system, and radar are received to ensure data synchronization. The data from different sources are aligned using timestamps. The light intensity is calculated based on the data from the ambient light sensor using the following formula:

[0082]

[0083] Where L represents the light intensity, L max and L min Respectively represent the maximum and minimum light intensity, I represents the ambient brightness, I0 represents the intermediate brightness value, and k represents the adjustment parameter. By receiving the image information transmitted by the image recognition system, the image information is first binarized, and the image after the binarization operation is subjected to noise reduction processing to improve the image quality, adjust the image contrast, ensure that the ship is distinguished from the background, and use the non-local mean denoising algorithm to reduce image noise by using the self-similarity in the image. The specific steps are as follows:

[0084] For any pixel i in the image, its grayscale value is represented as v(i). First, the similarity between pixel i and pixel j is calculated. The specific calculation formula is as follows:

[0085]

[0086] Among them, N i and N j denote the neighborhoods centered on pixels i and j, respectively, ||·|| denotes the square of the Euclidean distance between two neighborhoods, and h denotes the parameter that controls the decay speed of the exponential function;

[0087] The calculated similarity weights are normalized. For each pixel i, the calculated weight w(i, j) is normalized so that the sum of all weights is 1. The specific calculation formula is as follows:

[0088]

[0089] Using the normalized weights, the denoised pixel values ​​are calculated by weighted average. The specific calculation formula is as follows:

[0090]

[0091] Where NL(v)(i) represents the value of pixel i after denoising, and v(j) represents the value of pixel j in the original image;

[0092] The denoised image data is subjected to contrast enhancement processing. The denoised image is evenly divided into several blocks. Histogram equalization is performed on each block to enhance the local contrast. The specific calculation formula is as follows:

[0093] s=(L-1)·CDF(r)

[0094] Among them, r represents the pixel value of the original image, s represents the pixel value after transformation, and L represents the number of possible pixel levels. The histogram of each block is clipped to limit the number of occurrences of the maximum pixel value. A threshold T is set and the pixel values ​​exceeding the threshold are clipped. The specific calculation formula is as follows:

[0095] H'(i)=min(H(i),T)

[0096] Among them, H(i) represents the number of pixel values ​​in the original histogram, H'(i) represents the cropped histogram, and bilinear interpolation is performed on the processed block boundaries to ensure the visual coherence of the image. The specific calculation formula is as follows:

[0097]

[0098] Where x, y represent the coordinates of the target pixel, (x0, y0)(x1, y0)(x0, y1)(x1, y1) represent the coordinates of the four neighboring pixels surrounding the target pixel, f(x, y) represents the value of the target pixel, and f(x0, y0)(x1, y0)(x0, y1)(x1, y1) represent the values ​​of the four neighboring pixels. The value of the target pixel is obtained by calculating the weighted average of the four known pixels around the target pixel. Bilinear interpolation can effectively smooth the image and reduce the pixelation effect when the image is reduced.

[0099] The Canny edge detection algorithm is used to identify the edge of the ship, and the Sobel operator is used to calculate the gradient amplitude M and direction θ of the image. The specific calculation formula is as follows:

[0100]

[0101] Among them, G x and G y Represent the gradients along the x and y directions respectively, retain the local maximum value in the gradient amplitude to refine the edge, and use a high threshold t high and the low threshold t low To determine the edge, the specific calculation formula is as follows:

[0102]

[0103] Among them, when M is greater than the high threshold t high , then the pixel is considered to be a strong edge and is marked as an edge pixel. When M is less than the low threshold t low , then the pixel is considered not to be an edge and is excluded from the edge candidates. low and t high If the pixel is between , the pixel is a weak edge candidate. Connect the pixel points detected as edge pixels to obtain the edge pixels of the ship.

[0104] According to the number of pixels of the segmented ship image, the camera calibration parameters are used to convert the number of pixels into the actual area. The specific calculation formula is as follows:

[0105]

[0106] Among them, reality represents the actual area, pixel area Indicates pixel area, prime number Indicates the total number of pixels, actual area It indicates the actual navigation area. According to the position and viewing angle of the ship in the image, the viewing angle correction is performed to accurately estimate the actual size of the ship.

[0107] S103, based on the acquired ship size data, classifying the ship sizes according to the number of pixels occupied by the ship in the image, and classifying the ship sizes based on a neural network model;

[0108] Furthermore, an image dataset containing ships of different sizes is obtained and input into a neural network model to predict the size of the ship, which specifically includes the following steps:

[0109] In the forward propagation stage, the image data set is forward propagated through each layer of the neural network to obtain the predicted output. For each neuron, its input is the weighted sum of the output of the previous layer plus the bias term, and the output is obtained through the activation function. The specific calculation formula is as follows:

[0110] z [l+1] =W [l] a [l] +b [l]

[0111] a [l+1] =σ(z [l+1] )

[0112] Among them, a [l] represents the output of the lth layer, W [l] and b [l] are the weight matrix and bias vector of the lth layer, σ represents the activation function;

[0113] According to the difference between the predicted output and the true label, the loss function is calculated. The specific calculation formula is as follows:

[0114]

[0115] Among them, C represents the number of categories, yi represents the true label, represents the predicted probability;

[0116] The gradient of the loss with respect to each parameter is calculated by the back-propagation algorithm. For the gradient of weights and biases, the calculation formula is:

[0117]

[0118] Among them, L represents the loss function, which measures the difference between the model prediction and the true label, and W [l] represents the weight matrix of the lth layer, z [l+1] represents the weighted input of the l+1th layer, δ [l+1] represents the error term of the l+1th layer, a [l] represents the output of layer l, (a [l] ) T represents the transpose of the output of layer l, b [l] Represents the bias vector of the lth layer;

[0119] Use the optimization algorithm to update the neural network parameters. The specific calculation formula is as follows:

[0120]

[0121] Among them, W [l] represents the weight matrix of the lth layer, η represents the learning rate, represents the gradient of the loss function with respect to the weight of the lth layer, b [l] represents the bias vector of the lth layer, Represents the gradient of the loss function with respect to the bias of the lth layer.

[0122] S104, synchronizing the ship position and speed information collected by the radar data with the data of the image recognition system and the ambient light sensor;

[0123] Furthermore, the position of the ship is obtained by using the radar signal transmitted to the ship by the radar. The specific calculation formula is as follows:

[0124]

[0125] Among them, length represents the pulse length. A short pulse length means a short distance to the ship. Light represents the speed of light, which is used to calculate the time it takes for the radar wave to travel to and from the ship target. The speed at which the radar wave propagates in the air is used to calculate the distance to the ship. The specific calculation formula is as follows:

[0126]

[0127] Where C is the speed of light, t is the round trip time of the signal, and the speed of the ship is calculated by using the difference between two consecutive measurements of the ship's distance. The specific calculation formula is as follows:

[0128]

[0129] Among them, R current The currently measured distance, R previous It represents the distance of the previous measurement, and time represents the distance difference between two consecutive measurements, which reflects the moving distance of the target in the time interval between two measurements. The ship position and speed information monitored by the radar is matched with the ship size data in the image recognition system to obtain the ship size data and ship operation information.

[0130] S105, intelligently adjusting the navigation light signal based on the ship's position information, speed information, ship size information, and current light intensity information;

[0131] Furthermore, the ship's location information, speed information, ship size information and current light intensity are integrated into the central console. According to the ship's location, speed and size, the light warning required for the ship is evaluated, and the risk score of each ship is calculated using the collected data. The specific calculation formula is as follows:

[0132]

[0133] Among them, D maxrepresents the maximum distance, α, β, γ, δ represent the weight coefficients of each factor, D represents the distance of the ship, V represents the speed of the ship, S represents the size of the ship, W represents the weather conditions, C represents the sea conditions, V represents the crit represents the critical speed threshold, which is used to determine whether the speed of the ship exceeds the safety threshold. η represents the attenuation factor, which is used to control the growth rate of the risk of the speed exceeding the critical value. The risk assessment result is input into the lighting adjustment algorithm to automatically adjust the intensity and color of the navigation mark light. The specific calculation formula of the lighting adjustment algorithm is as follows:

[0134]

[0135] Among them, if R<0.3 means that the risk score of the ship is less than 0.3, which is a low risk; if 0.3≤R<0.7 means that the risk score of the ship is greater than or equal to 0.3 and less than 0.7, which is a medium risk; if R≥0.7 means that the risk score of the ship is greater than or equal to 0.7, which is a high risk. According to the warning level, the corresponding light intensity is determined, and the determined light intensity is sent to the central console for execution. The central console is monitored, real-time feedback information is collected, and the light intensity is adjusted.

[0136] Exemplary:

[0137] According to the risk score, different risk levels are defined, and each level corresponds to a set of light intensity and light color. For example, the following rules can be defined:

[0138] Risk Level Light Color Light intensity Low green 50％ middle yellow 75％ high red 100％

[0139] The light intensity can be further adjusted to take into account visibility conditions such as fog, rain or night time. For example, in foggy weather, even at a low risk level, the light intensity may need to be increased to 75% to ensure visibility of the lights to vessels.

[0140] Example 2

[0141] like Figure 2 This embodiment provides: a navigation light signal intelligent adjustment system, including:

[0142] Data collection module: collects ambient brightness, vessel approach and vessel size data in real time through sensors, and connects the sensors to the central console;

[0143] Data analysis module: integrates sensor data and analyzes the current environment brightness, the presence and size of ships;

[0144] Data classification module: Based on the acquired ship size data, the ship size is classified according to the number of pixels occupied by the ship in the image, and the ship size is classified based on the neural network model;

[0145] Speed ​​Detection Module: Synchronizes the ship position and speed information collected by radar data with the data from the image recognition system and ambient light sensor;

[0146] Intelligent adjustment module: intelligently adjusts the navigation light signal based on the ship's position information, speed information, ship size information and current light intensity information;

[0147] It should be noted that in the above embodiments, the description of each embodiment has its own emphasis, and for parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0148] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0149] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded computer, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0150] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0151] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0152] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0153] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for intelligently adjusting navigation light signals, characterized in that: The following steps are involved: S101, collect data on ambient brightness, vessel approach and vessel size in real time through sensors, and connect the sensors to a central console; S102, integrating sensor data and analyzing the current environment brightness, the presence and size of ships; S103, based on the acquired ship size data, classifying the ship sizes according to the number of pixels occupied by the ship in the image, and classifying the ship sizes based on a neural network model; S104, synchronizing the ship position and speed information collected by the radar data with the data of the image recognition system and the ambient light sensor; S105, intelligently adjust the navigation light signal based on the ship's position information, speed information, ship size information, and current light intensity information.

2. The method for intelligently adjusting navigation light signals according to claim 1, characterized in that: In the S101, an ambient light sensor, an image recognition system and a radar device are installed in the monitoring area, and the ambient light sensor, the image recognition system and the radar device are connected to the central control console. The ambient brightness is monitored by the ambient light sensor, and the ships approaching the monitoring area and their sizes are identified and tracked by the image recognition system. The position and speed information of the ships are monitored by the radar. The collected ambient brightness data, the ship image and the position and speed information of the ships are transmitted to the central control console. The central control console receives and stores the data transmitted from the ambient light sensor, the image recognition system and the radar device in real time, and performs real-time data analysis.

3. A navigation light signal intelligent adjustment system is applied to a navigation light signal intelligent adjustment method as claimed in claim 1-2, comprising: Data collection module: collects ambient brightness, vessel approach and vessel size data in real time through sensors, and connects the sensors to the central console; Data analysis module: integrates sensor data and analyzes the current environment brightness, the presence and size of ships; Data classification module: Based on the acquired ship size data, the ship size is classified according to the number of pixels occupied by the ship in the image, and the ship size is classified based on the neural network model; Speed ​​Detection Module: Synchronizes the ship position and speed information collected by radar data with the data from the image recognition system and ambient light sensor; Intelligent adjustment module: intelligently adjusts the navigation light signal based on the ship's position information, speed information, ship size information and current light intensity information.

Images