A ship detection method, device and electronic equipment

Abstract

Embodiments of the present application provide a ship detection method and device and electronic equipment. In the embodiments, the ship information of the target ship in the image captured by the pan-tilt camera is used to correct the target ship information obtained based on the radar, thereby realizing radar-cloud linkage, solving the problem that when only the radar is used to detect the ship, the spray caused by the trailing of the ship is attached to the ship, resulting in inaccurate ship detection information, and obtaining more accurate ship detection data. Further, the collection parameters of the pan-tilt camera are adjusted by using the ship information of the target ship, and the camera based on the determined collection parameters captures the ship in the camera detection range, thereby solving the problem that the night ship snapshot focusing is not clear and the focusing time is long, and the problem that the ship does not meet the fast motion.

Description

Technical Field

[0001] This application relates to detection technology, and more particularly to a method, apparatus and electronic equipment for ship detection. Background Technology

[0002] Currently, radar is commonly used to detect vessels in the water to ensure their safety. However, when using radar for detection, the range extension effect of the vessel signal, the trailing spray, and other factors can interfere with the signal, affecting the radar cross-section and leading to inaccurate vessel coordinates detected by the radar. Inaccurate vessel coordinates, in turn, result in off-target vessel feature images and low precision. Summary of the Invention

[0003] In view of this, embodiments of this application provide a ship detection method, apparatus, and electronic device to obtain more accurate ship detection information and improve the accuracy of ship detection.

[0004] According to a first aspect of the embodiments of this application, a ship detection method is provided. This method is applied to a radar-cloud integrated machine, which integrates at least radar, a main unit, and a gimbal camera. The method includes:

[0005] The radar detects ships entering its detection range, and the acquisition parameters of the gimbal camera are adjusted based on the target ships detected by the radar.

[0006] The gimbal camera acquires images of the target vessel entering the camera's detection range based on the acquisition parameters.

[0007] Based on the vessel information of the target vessel collected by the gimbal camera, the vessel information of the target vessel detected by the radar is adjusted.

[0008] According to a second aspect of the embodiments of this application, a ship detection device is provided, which is applied to a radar-cloud integrated machine, wherein the radar-cloud integrated machine integrates at least a radar, a main unit, and a gimbal camera, and the device includes:

[0009] The acquisition parameter determination module is used to detect ships entering the radar detection range through the radar and adjust the acquisition parameters of the gimbal camera based on the target ships detected by the radar.

[0010] The image acquisition module is used to acquire images of the target vessel entering the camera's detection range using the gimbal camera based on the acquisition parameters;

[0011] The adjustment module is used to adjust the ship information of the target ship detected by the radar based on the ship information of the target ship collected by the gimbal camera.

[0012] According to a third aspect of the present application, an electronic device is provided, the electronic device including a machine-readable storage medium and a processor; the machine-readable storage medium stores machine-executable instructions that can be executed by the processor; the processor is configured to read the machine-executable instructions to implement the steps of the ship detection method as described in the first aspect.

[0013] The technical solutions provided in this application embodiment may include the following beneficial effects:

[0014] In this embodiment of the application, the target ship information obtained based on radar is corrected by the ship information of the target ship in the image captured by the gimbal camera, realizing the linkage between radar and cloud, and solving the problem that the ship detection information obtained is inaccurate when only radar is used to detect ships because the waves brought up by the ship's tail stick to the ship. More accurate ship detection data is obtained.

[0015] Furthermore, by adjusting the acquisition parameters of the gimbal camera using the target vessel's information, the camera can capture images of vessels within its detection range based on the determined acquisition parameters. This solves the problems of unclear focus, long focus time, and inability to capture fast-moving vessels at night. Attached Figure Description

[0016] Figure 1 This is an example diagram of the RayCloud all-in-one machine provided in the embodiments of this application.

[0017] Figure 2 This is an example diagram of the deployment of the RayCloud all-in-one machine provided in the embodiments of this application.

[0018] Figure 3 This is a flowchart of the method provided in the embodiments of this application.

[0019] Figure 4 This is an example diagram of ship navigation channel determination provided in the embodiments of this application.

[0020] Figure 5 This is a diagram of the apparatus provided in the embodiments of this application.

[0021] Figure 6 This is a schematic diagram of the hardware structure of the device according to an embodiment of this application. Detailed Implementation

[0022] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0023] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0024] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0025] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of this application, and to make the above-mentioned objectives, features and advantages of the embodiments of this application more apparent and understandable, the technical solutions in the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0026] See Figure 1 , Figure 1 Example diagram of the Raycloud all-in-one machine provided in the embodiments of this application, such as Figure 1 As shown, the radar P0, laser fill light P4, white light camera module P3, and host P2 are connected. The radar P0, laser fill light P4, and white light camera module P3 are connected to the host P2 via a switch. The host P2 connects to the host via the first port (…). Figure 1 Host P2 interacts with the switch via the eth1 port, and host P2 interacts via the second port (eth1 port). Figure 1 The radar P0 interacts with the user interface P1 via its eth0 port. User interface P1 is used to connect to external management devices. The host P2 includes a microcontroller for processing the data acquired by the radar. The scanning range of radar P0 can be 1 kilometer, but this embodiment is not specifically limited to this range.

[0027] It should be noted that, in addition to the components mentioned above, the aforementioned Razer All-in-One Machine also includes a gimbal. The white light camera module P3 is mounted on the gimbal, and together they are referred to as the gimbal camera. It is connected to the host P2 via a switch.

[0028] In this embodiment, there are many ways to deploy the RayCloud integrated machine, which can be determined according to the actual application scenario. For example, if it is necessary to count the number of ships at a ship checkpoint, such as... Figure 2As shown, the radar-cloud integrated machine can be set on one side of the river, with the angle between the radar's central axis and the riverbank being a specified angle (e.g., 45°), and the installation height of the radar-cloud integrated machine being a specified height (e.g., 20m). For example, if it is necessary to provide early warning of ship collisions with bridges, the radar-cloud integrated machine can be set on the bridge. The embodiments of this application are not specifically limited.

[0029] In this embodiment, after the RayCloud all-in-one machine is deployed and powered on, the host P2 acquires the radar's identification information and radar parameter information from the RayCloud all-in-one machine. Here, the radar's identification information may include the radar's model and the program version number in the radar.

[0030] In this embodiment, if the radar parameter information does not meet the detection requirements, the radar parameter information can be modified, and the modified radar parameter information can be sent to the radar using the configured interface protocol. Here, the radar parameter information includes, but is not limited to: Doppler value, constant false alarm rate (CFAR), track threshold, number of radar reporting frames, radar frequency, and moving filtering distance, etc.

[0031] The method provided in the embodiments of this application is described below:

[0032] See Figure 3 , Figure 3 This is a flowchart illustrating a method provided in an embodiment of this application. The method is applied to the aforementioned Raycloud all-in-one machine, such as... Figure 3 As shown, the process may include the following steps:

[0033] S310: Detects ships entering the radar detection range using radar, and adjusts the acquisition parameters of the gimbal camera based on the target ships detected by the radar.

[0034] For example, in this embodiment, the radar detection range can be the radar's own scanning area or a predefined target scanning area. Here, the target scanning area is a part of the radar's own scanning area. This application embodiment does not specifically limit the radar detection range.

[0035] For example, in this embodiment, the number of vessels detected by the radar entering the radar detection range is at least one. Here, at least one vessel is a moving vessel operating on water. The vessel information of each vessel may include: the vessel's coordinate information, vessel size information, vessel speed, distance from the vessel to the radar, etc. This embodiment of the application does not specifically limit the information. Here, the vessel's coordinate information refers to the vessel's coordinates in the radar coordinate system.

[0036] In this embodiment, the target vessel can be at least one vessel within the radar detection range. There are many methods for determining the target vessel, and this embodiment does not specifically limit the methods.

[0037] For example, the direction of travel can be determined based on external commands or based on the direction of travel of each vessel within the radar detection range. As for how to determine the direction of travel based on external commands or based on the direction of travel of each vessel within the radar detection range, examples are given below, which will not be elaborated here.

[0038] In this embodiment, the acquisition parameters of the gimbal camera may include: the left and right movement distance of the gimbal, the up and down movement distance of the gimbal, the zoom of the camera lens, and the focal length of the camera, etc., which are not specifically limited in this embodiment.

[0039] In this embodiment, the specific method for adjusting the acquisition parameters of the gimbal camera based on the target vessel detected by the radar in step S310 can be found in the description of the following embodiment, and will not be repeated here.

[0040] In this embodiment, after obtaining the scanning results of each ship entering the radar detection range (here, the scanning results are point cloud data), the radar detection range is divided into multiple grid areas. The ship information of each ship within the radar detection range is determined based on the scanning results. Specifically, this can be done by using a conventional clustering method to aggregate the data in multiple grids to obtain the point cloud data of each ship, and then determining the ship information of each ship within the radar detection range based on the scanning results of each ship.

[0041] S320: The gimbal camera acquires data on target vessels entering the camera's detection range based on the acquisition parameters.

[0042] For example, in this embodiment, the camera detection range can be the camera's field of view or a predefined target field of view. Here, the target field of view can be a part of the camera's field of view. This application embodiment does not specifically limit the camera detection range.

[0043] In this embodiment, a gimbal camera collects data on vessels entering the camera's detection range based on the acquisition parameters. Here, vessels within the camera's detection range can include stationary vessels on the shore or moving vessels on the water; this embodiment is not specifically limited to these categories.

[0044] In this embodiment, before performing step S320, after the gimbal camera collects images of ships entering the camera's detection range based on the acquisition parameters, the ship images collected by the gimbal camera are input into the trained recognition model to obtain the ship information of each ship. Alternatively, conventional machine vision methods can be used to obtain the ship information of each ship. This embodiment of the application is not specifically limited.

[0045] In this embodiment, the vessel information may include: vessel coordinates, vessel size, distance from the vessel to the gimbal camera, etc., and this embodiment is not specifically limited. Here, the vessel coordinates refer to the vessel's coordinates in the camera coordinate system.

[0046] In step S320, after obtaining the ship information of each ship, the target ship can be determined based on the distance of each ship to the center of the camera. As for how to determine the target ship, the following embodiments provide examples, which will not be repeated here.

[0047] S330: Adjusts the information of target vessels detected by radar based on the vessel information collected by the gimbal camera.

[0048] For example, in this embodiment, the ship information of the target ship collected by the gimbal camera is adjusted based on the ship information of the target ship detected by the radar. Specifically, the ship size information, ship coordinate information, etc. in the ship information can be adjusted. This embodiment does not specifically limit the ship that needs to be adjusted, and it can be determined according to the actual situation.

[0049] In this embodiment, in step S330, there are many ways to adjust the ship information of the target ship detected by the radar based on the ship information of the target ship collected by the gimbal camera, and this embodiment of the application is not specifically limited.

[0050] For example, the ship information of the target ship collected by the gimbal camera can be directly replaced with the ship information of the target ship detected by the radar.

[0051] This concludes the process. Figure 3 The process is shown below.

[0052] pass Figure 3 As can be seen from the process shown, in this embodiment of the application, the target ship information obtained based on radar is corrected by the ship information of the target ship in the image captured by the gimbal camera, realizing the linkage between radar and cloud, solving the problem that the ship detection information obtained is inaccurate when only radar is used to detect ships because the waves brought up by the ship's tail stick to the ship, and obtaining more accurate ship detection data.

[0053] Furthermore, by adjusting the acquisition parameters of the gimbal camera using the target vessel's information, the camera can capture images of vessels within its detection range based on the determined acquisition parameters. This solves the problems of unclear focus, long focus time, and inability to capture fast-moving vessels at night.

[0054] As an optional implementation of this application, the above-mentioned adjustment of the gimbal camera's acquisition parameters based on the target vessel detected by radar includes:

[0055] First, based on the ship information of the target vessel detected by radar, the field of view of the gimbal camera is determined.

[0056] For example, in this embodiment, the vessel information of the target vessel detected by radar includes: the length of the target vessel and the distance of the target vessel from the radar; determining the field of view of the gimbal camera based on the vessel information of the target vessel detected by radar includes:

[0057] The field of view of the gimbal camera is determined by the following formula:

[0058]

[0059] Where Fov is the field of view; dis is the distance from the target ship to the radar; shipL is the length of the target ship; and screenRatio is the preset screen ratio, which is set in advance and refers to the proportion of the target ship on the camera screen.

[0060] Secondly, a zoom command is sent to the gimbal camera based on the field of view, so that the gimbal camera adjusts the focal length to the focal length carried in the zoom command.

[0061] For example, in this embodiment, the focal length carried in the zoom command can be determined based on the field of view. There are many specific methods for determining the focal length. For example, the correspondence between the field of view and the focal length can be defined in advance. After obtaining the field of view, the focal length corresponding to the key can be found in the above correspondence using the field of view as the key. Another example is to obtain the focal length using conventional calculation methods. This embodiment of the application is not specifically limited.

[0062] In this embodiment, a zoomed-in gimbal camera is used to capture images of target vessels that have entered the camera's detection range.

[0063] As an optional implementation of this application, after adjusting the ship information of the target ship detected by radar based on the ship information of the target ship collected by the gimbal camera, the ship detection method further includes:

[0064] Based on the adjusted target vessel information and the obtained calibration matrix between the radar and the gimbal camera, the omnidirectional movement of the gimbal camera and the PTZ value for lens magnification and zoom control are determined; the gimbal movement of the gimbal camera is controlled according to the PTZ value so that the gimbal camera can capture target vessels that have entered the camera's detection range.

[0065] For example, in this embodiment, the calibration matrix between the radar and the gimbal camera is obtained in advance. When performing this step, the calibration matrix can be directly called. Here, the advance calibration can be automatically based on the radar's first scan result of the ships within the radar's detection range, or it can be manually calibrated. This embodiment of the application does not specifically limit the calibration.

[0066] Both manual and automatic calibration processes are standard techniques and will not be elaborated upon here.

[0067] In this embodiment, based on the adjusted target vessel information and the obtained calibration matrix between the radar and the gimbal camera, the omnidirectional movement of the gimbal camera and the PTZ value for lens zoom and magnification control are determined. Specifically, the PTZ value can be obtained by calculating the coordinate information of the target vessel and the calibration matrix. The calculation method is a conventional process and will not be described in detail here.

[0068] For example, in this embodiment, after the target vessel is identified, the pan-tilt camera is moved according to the PTZ value so that the pan-tilt camera can capture the target vessel that has entered the camera's detection range.

[0069] This application embodiment achieves radar-cloud linkage through CALIB calibration, enabling large-angle, all-round, multi-vehicle tracking and capture.

[0070] As an optional implementation of this application, the target vessel detected by radar is determined through the following steps:

[0071] At least one vessel is designated as the target vessel based on external instructions.

[0072] For example, in this embodiment, when an external command is received, at least one vessel carried in the external command is selected as the target vessel. Here, the external command may be issued by a management terminal device.

[0073] or

[0074] First, if the radar detects multiple vessels, it determines the direction of travel for each vessel.

[0075] Secondly, when all the ships are traveling in the same direction, at least one ship is identified as the target ship based on the time when each ship enters the radar detection range.

[0076] Furthermore, when the directions of travel of the vessels are inconsistent, at least one vessel is identified as the target vessel based on the speed of each vessel.

[0077] For example, in this embodiment, when the radar detects multiple ships, the direction of travel of each ship is determined. Specifically, the direction of travel of each ship can be determined from the ship information of each ship. The directions of travel of each ship can be the same or different. When the directions of travel of the ships are the same, at least one target ship is determined based on the ship entry time in the ship information of each ship. For example, at least one ship with an earlier entry time is selected as the target ship. When the directions of travel of the ships are different, the target ship is determined based on the ship speed in the ship information of each ship. For example, at least one ship with a faster speed is selected as the target ship.

[0078] As an optional implementation of this application, the adjustment of the target vessel information detected by radar based on the target vessel information collected by the gimbal camera includes:

[0079] First, based on the ship information detected by the radar, the distance from the target ship to the radar is determined.

[0080] For example, in this embodiment, the ship information of the target ship includes at least the coordinate information of the target ship. The distance from the target ship to the radar can be determined based on the ship information of the target ship detected by the radar. Specifically, it can be determined by using the distance calculation method between the two points based on the coordinate information of the target ship and the coordinate information of the radar origin. This will not be elaborated here.

[0081] Secondly, based on the vessel information collected by the gimbal camera, the distance from each vessel to the camera is determined. The vessel information includes at least the vessel's coordinates. Based on the distance from the target vessel to the radar and the distance from each vessel to the camera collected by the gimbal camera, the vessel information of the target vessel is determined from the vessel information collected by the gimbal camera. Based on the vessel information of the target vessel collected by the gimbal camera, the vessel information of the target vessel detected by the radar is adjusted.

[0082] For example, in this embodiment, the distance from each vessel to the camera is determined based on the vessel information collected by the gimbal camera. Specifically, it can be determined by using the distance calculation method between the two points based on the coordinate information of each vessel and the coordinate information of the camera origin. This will not be elaborated here.

[0083] For example, in this embodiment, after obtaining the distance from the target vessel to the radar and the distance from each vessel to the camera, the vessel information of the target vessel is determined from the vessel information collected by the gimbal camera based on the distance from the target vessel to the radar and the distance from each vessel to the camera. Based on the vessel information of the target vessel collected by the gimbal camera, the vessel information of the target vessel detected by the radar is adjusted.

[0084] As an optional implementation of this application, the adjustment of the target vessel information detected by radar based on the target vessel information collected by the gimbal camera includes:

[0085] Based on the ship information of the target ship collected by the gimbal camera, the ship information of the target ship detected by the radar is adjusted so that the adjusted ship information meets the preset matching conditions with the ship information of the target ship collected by the gimbal camera.

[0086] For example, in this embodiment, the preset matching condition can be that the adjusted ship information is consistent with the ship information of the target ship collected by the gimbal camera, or the difference between the adjusted ship information and the ship information of the target ship collected by the gimbal camera is within a preset range. This application embodiment does not specifically limit the preset range, and this application embodiment can determine it according to the actual situation.

[0087] In this embodiment, the ship information of the target ship detected by the radar is adjusted based on the ship information of the target ship collected by the gimbal camera. Specifically, the ship information of the target ship detected by the radar can be directly replaced by the ship information of the target ship collected by the gimbal camera.

[0088] As an optional implementation of this application, the target vessel information detected by radar includes: the target vessel's heading angle; the adjusted target vessel information includes at least: adjusted vessel coordinate information; the vessel detection method further includes:

[0089] First, based on the adjusted vessel coordinates and the obtained channel information for each waterway, determine whether the target vessel is deviating from its course; and / or, based on whether the heading angle exceeds the threshold for the direction of travel in the waterway.

[0090] For example, in this embodiment, the aforementioned channel information can be the coordinate information of each point on the channel. The target vessel's entry channel is determined based on the adjusted vessel coordinate information and the channel information of each channel, and the channel closest to the target vessel is taken as the entry channel.

[0091] In this embodiment of the application, two waterway lines are used as an example for description, such as... Figure 4 As shown, the two channels are referred to as Channel 1 and Channel 2. The channel for the leftmost ship to enter is Channel 1, the channel for the middle ship to enter is Channel 2, and the channel for the rightmost ship to enter is Channel 3.

[0092] For example, in this embodiment, when the vessel is on the waterway or the distance between the vessel and the waterway is less than a preset distance threshold, it is determined whether the target vessel has deviated from its course. The preset distance threshold can be set according to the actual situation, and this embodiment does not specifically limit it.

[0093] For example, in this embodiment, the channel travel direction threshold is preset. This embodiment is not specifically limited and can be determined according to the actual situation.

[0094] Secondly, when the target vessel yaws and / or its heading angle exceeds the threshold for the direction of travel in the channel, a warning message is issued.

[0095] For example, in this embodiment, in this step, when the target vessel veers and / or the adjusted heading angle exceeds the channel direction threshold, a warning message is issued. The warning message for veergence and the warning message for the target vessel's heading angle exceeding the channel direction threshold can be the same. However, to distinguish different error types, the warning message for veergence and the warning message for the target vessel's heading angle exceeding the channel direction threshold can also be different. For example, warning messages with different sound levels or warning messages with different display colors. This embodiment of the application does not specifically limit the specifics.

[0096] The methods provided in the embodiments of this application have been described above. The apparatus provided in the embodiments of this application is described below:

[0097] See Figure 5 , Figure 5 This is a structural diagram of the device provided in an embodiment of this application. The device is applied to a radar-cloud integrated machine, which integrates at least a radar, a main unit, and a gimbal camera. The device may include:

[0098] The parameter acquisition module is used to detect ships entering the radar detection range by radar and adjust the acquisition parameters of the gimbal camera based on the target ships detected by the radar.

[0099] The image acquisition module is used to acquire images of target vessels entering the camera's detection range using a gimbal camera based on acquisition parameters;

[0100] The adjustment module is used to adjust the ship information of the target ship detected by the radar based on the ship information of the target ship collected by the gimbal camera.

[0101] As an optional implementation of this application, the above-mentioned parameter acquisition module is specifically used for:

[0102] Based on the ship information of the target ship detected by radar, the field of view of the gimbal camera is determined.

[0103] A zoom command is sent to the gimbal camera based on the field of view, so that the gimbal camera adjusts its focal length to the focal length specified in the zoom command, which is determined based on the field of view; and / or,

[0104] Based on the target vessel information detected by radar and the calibration matrix between radar and gimbal camera, the omnidirectional movement of gimbal camera and the PTZ value for lens magnification and zoom control are determined; the gimbal movement of gimbal camera is controlled according to the PTZ value so that gimbal camera can capture target vessels entering the camera detection range.

[0105] As an optional implementation of this application, the target vessel detected by radar is determined through the following steps:

[0106] At least one vessel is designated as the target vessel based on external instructions; or

[0107] If the radar detects multiple vessels, it determines the direction of travel for each vessel.

[0108] When all vessels are traveling in the same direction, at least one vessel is identified as the target vessel based on the time when each vessel enters the radar detection range.

[0109] When the ships are traveling in different directions, at least one ship is identified as the target ship based on the speed of each ship.

[0110] As an optional implementation of this application, the above-mentioned adjustment module is specifically used for:

[0111] Based on the target vessel information detected by the radar, determine the distance from the target vessel to the radar; the target vessel information includes at least the target vessel's coordinates.

[0112] Based on the vessel information collected by the gimbal camera, the distance from each vessel to the camera is determined. The vessel information includes at least the vessel's coordinates. Based on the distance from the target vessel to the radar and the distances from each vessel to the camera collected by the gimbal camera, the target vessel information is determined from the vessel information collected by the gimbal camera. Based on the target vessel information collected by the gimbal camera, the target vessel information detected by the radar is adjusted.

[0113] As an optional implementation of this application, the above-mentioned adjustment module is specifically used for:

[0114] Based on the ship information of the target ship collected by the gimbal camera, the ship information of the target ship detected by the radar is adjusted so that the adjusted ship information meets the preset matching conditions with the ship information of the target ship collected by the gimbal camera.

[0115] As an optional implementation of this application, the target vessel information detected by radar includes: the target vessel's heading angle; the adjusted target vessel information includes at least: adjusted vessel coordinate information; and the vessel detection device further includes:

[0116] The yaw determination module is used to determine whether the target vessel is yawed based on the adjusted vessel coordinate information and the obtained channel line information of each channel; and / or, based on whether the heading angle exceeds the channel travel direction threshold.

[0117] The early warning module is used to issue early warning information when the target vessel veers and / or its heading angle exceeds the threshold of the channel's direction of travel.

[0118] As an optional implementation of this application, the vessel information of the target vessel detected by radar includes: the length of the target vessel and the distance of the target vessel from the radar; determining the field of view of the gimbal camera based on the aforementioned vessel information detected by radar includes:

[0119] The field of view of the gimbal camera is determined by the following formula:

[0120]

[0121] Where Fov is the field of view; dis is the distance from the target ship to the radar; shipL is the length of the target ship; and screenRatio is the preset screen ratio, which is set in advance and refers to the proportion of the target ship on the camera screen.

[0122] The specific implementation process of the functions and roles of each unit in the above device can be found in the implementation process of the corresponding steps in the above method, and will not be repeated here.

[0123] This concludes the process. Figure 5 Structural description of the device shown.

[0124] Correspondingly, embodiments of this application also provide Figure 5 The hardware structure diagram of the device shown is as follows: Figure 6 As shown, the electronic device can be a device implementing the above-described method. Figure 6 As shown, the hardware architecture includes a processor and memory.

[0125] Among them, the memory is used to store machine-executable instructions;

[0126] A processor is used to read and execute machine-executable instructions stored in memory to implement the corresponding ship detection method embodiment shown above.

[0127] As one embodiment, the memory can be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, etc. For example, the memory can be volatile memory, non-volatile memory, or similar storage media. Specifically, the memory can be RAM (Random Access Memory), flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or combinations thereof.

[0128] This concludes the process. Figure 6 Description of the electronic device shown.

[0129] The above are merely preferred embodiments of this application and are not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for detecting ships, characterized in that, This method is applied to a Ray-Yun integrated machine, which integrates at least radar, a main unit, and a gimbal camera. The method includes: The radar detects ships entering its detection range. If the radar detects multiple ships, it determines the direction of travel of each ship. If the directions of travel of all ships are the same, the ship that entered the radar earlier is selected as the target ship. If the directions of travel of all ships are different, the ship with the highest speed is selected as the target ship. The acquisition parameters of the gimbal camera are adjusted based on the target ships detected by the radar. The gimbal camera acquires images of the target vessel entering the camera's detection range based on the acquisition parameters. The target vessel information in the image captured by the gimbal camera is used to correct the target vessel information obtained from radar; the corrected target vessel information is more accurate than the original target vessel information. Based on the corrected target vessel information and the obtained calibration matrix between the radar and the gimbal camera, the omnidirectional movement of the gimbal camera and the PTZ value for lens magnification and zoom control are determined; the gimbal movement of the gimbal camera is controlled according to the PTZ value so that the gimbal camera can capture the target vessel that has entered the camera detection range.

2. The method according to claim 1, characterized in that, The adjustment of the acquisition parameters of the gimbal camera based on the target vessel detected by the radar includes: Based on the vessel information of the target vessel detected by the radar, the field of view of the gimbal camera is determined; A zoom command is sent to the gimbal camera based on the field of view, so that the gimbal camera adjusts the focal length to the focal length carried in the zoom command, and the focal length carried in the zoom command is determined based on the field of view.

3. The method according to claim 1 or 2, characterized in that, The correction of the target vessel information in the image captured by the gimbal camera to the target vessel information obtained based on radar includes: Based on the vessel information of the target vessel detected by the radar, the distance from the target vessel to the radar is determined; the vessel information of the target vessel includes at least the coordinate information of the target vessel; Based on the vessel information collected by the gimbal camera, the distance from each vessel to the camera is determined. The vessel information includes at least the vessel's coordinates. Based on the distance from the target vessel to the radar and the distances from each vessel to the camera collected by the gimbal camera, the vessel information of the target vessel is determined from the vessel information collected by the gimbal camera. Based on the vessel information of the target vessel collected by the gimbal camera, the vessel information of the target vessel detected by the radar is adjusted.

4. The method according to claim 3, characterized in that, The adjustment of the target vessel information detected by the radar based on the vessel information collected by the gimbal camera includes: Based on the vessel information of the target vessel collected by the gimbal camera, the vessel information of the target vessel detected by the radar is adjusted so that the adjusted vessel information meets the preset matching conditions with the vessel information of the target vessel collected by the gimbal camera.

5. The method according to claim 1, characterized in that, The target vessel information detected by the radar includes: the target vessel's heading angle; the adjusted target vessel information includes at least: the adjusted vessel coordinates; the method further includes: Based on the adjusted vessel coordinates and the obtained channel information for each waterway, determine whether the target vessel is deviating from its course; and / or, determine whether the heading angle exceeds the waterway travel direction threshold. A warning message is issued when the target vessel veers off course and / or the heading angle exceeds the channel travel direction threshold.

6. The method according to claim 1, characterized in that, The vessel information detected by the radar includes: the length of the target vessel and the distance of the target vessel from the radar; determining the field of view of the gimbal camera based on the vessel information detected by the radar includes: The field of view of the gimbal camera is determined according to the following formula: Where Fov is the field of view angle; dis is the distance from the target vessel to the radar; The length of the target vessel, The preset screen occupancy ratio is a pre-set ratio that refers to the proportion of the target vessel on the camera screen.

7. A ship detection device, characterized in that, This device is used in a radar-cloud integrated machine, which integrates at least a radar, a main unit, and a gimbal camera. The device includes: The acquisition parameter determination module is used to detect ships entering the radar detection range through the radar. If the radar detects multiple ships, it determines the direction of travel of each ship. When the directions of travel of the ships are the same, at least one ship that entered the radar earlier is selected as the target ship. When the directions of travel of the ships are different, at least one ship with a higher speed is selected as the target ship. The acquisition parameters of the gimbal camera are adjusted based on the target ships detected by the radar. The image acquisition module is used to acquire images of the target vessel entering the camera's detection range using the gimbal camera based on the acquisition parameters; The adjustment module is used to correct the target vessel information obtained from radar based on the target vessel information in the image captured by the gimbal camera. The corrected target vessel information is more accurate than the target vessel information before adjustment. Based on the adjusted target vessel information and the obtained calibration matrix between the radar and the gimbal camera, the omnidirectional movement of the gimbal camera and the PTZ value for lens magnification and zoom control are determined; the gimbal movement of the gimbal camera is controlled according to the PTZ value so that the gimbal camera can capture the target vessel that has entered the camera detection range.

8. An electronic device, characterized in that, Electronic devices include machine-readable storage media and processors; The machine-readable storage medium stores machine-executable instructions that can be executed by a processor; The processor is used to read the machine-executable instructions to implement the steps of the ship detection method as described in any one of claims 1-6.

Images