Ship hull detection method, device and equipment based on underwater unmanned vehicle and medium

Abstract

The application relates to a hull detection method, device and equipment based on an underwater unmanned vehicle and a storage medium. The method comprises the following steps: a client presents a hull partition detection interface, and in response to a selection operation of a user on a target detection area, sends a detection instruction to an underwater unmanned vehicle; based on the detection instruction, the underwater unmanned vehicle is controlled to sail to the target detection area of the hull, and a first camera of the underwater unmanned vehicle is used to collect a first image of the target detection area; image analysis is performed on the first image to determine whether the first image meets preset detection requirements; if not, a second camera of the underwater unmanned vehicle is used to collect a second image of the target detection area; the second camera is closer to the target detection area than the first camera; the first image and the second image are stored and associated with corresponding detection task information.

Description

Technical Field

[0001] This application relates to the field of ship hull inspection technology, and in particular to a ship hull inspection method, apparatus, equipment and storage medium based on underwater unmanned aerial vehicles. Background Technology

[0002] Inspection of underwater valve compartments on large vessels is an indispensable part of border inspection. As part of the ship's structure, underwater valve compartments are highly concealed and are easily overlooked in border inspection work. Therefore, how to conduct efficient and cost-effective underwater valve compartment inspections has become a technology that needs to be researched and popularized.

[0003] In the past, ship inspection could be carried out by divers, but in recent years it has gradually been replaced by underwater drone inspection. However, the seabed valve chamber has a protective net and no light source inside. The port seawater has a certain degree of turbidity, and underwater drones cannot see the internal conditions through the protective net. At the same time, the port seawater has a certain flow rate, which also poses a challenge to the underwater drones' ability to resist the current.

[0004] Therefore, it is necessary to provide a method, device, equipment, and storage medium for hull inspection based on underwater drones to better inspect the seabed valves of ships. Summary of the Invention

[0005] In view of the above, this application provides a method, apparatus, equipment and storage medium for hull inspection based on underwater unmanned aerial vehicles, the purpose of which is to solve the above-mentioned technical problems.

[0006] Firstly, this application provides a method for hull inspection based on an underwater unmanned aerial vehicle (UAV), the method comprising:

[0007] The client displays the hull partition detection interface and, in response to the user's selection of the target detection area, sends detection commands to the underwater drone.

[0008] Based on the detection command, the underwater drone is controlled to navigate to the target detection area of ​​the ship's hull, and the first camera of the underwater drone is used to capture the first image of the target detection area.

[0009] Image analysis is performed on the first image to determine whether the first image meets the preset detection requirements;

[0010] If the conditions are not met, a second image of the target detection area is acquired using the second camera of the underwater drone; wherein the second camera is closer to the target detection area than the first camera.

[0011] The first image and the second image are stored and associated with the corresponding detection task information.

[0012] In some embodiments, acquiring a second image of the target detection area using the second camera of the underwater drone includes:

[0013] The telescopic structure of the underwater drone is activated to move the second camera mounted on the end of the telescopic pole to the target detection position;

[0014] The second camera is controlled to acquire a second image of the target detection area at the target detection location.

[0015] In some embodiments, controlling the activation of the telescopic structure of the underwater drone to move the second camera mounted at the end of the telescopic boom to the target detection position includes:

[0016] Based on the first image, extract the environmental features of the target detection area;

[0017] Based on the environmental characteristics, the target detection location is determined;

[0018] Based on the target detection position, the extension length and extension angle of the telescopic rod are determined;

[0019] Based on the telescopic length and the telescopic angle, the telescopic rod is controlled to move the second camera to the target detection position.

[0020] In some embodiments, determining the target detection location based on the environmental features includes:

[0021] Based on the aforementioned environmental characteristics, the structural features of the protective netting in the target detection area are determined;

[0022] Based on the current position of the underwater drone, the parameter characteristics of the telescopic structure, and the structural characteristics of the protective net, it is determined whether the extension of the telescopic rod will collide with the protective net;

[0023] If so, adjust the current position of the underwater drone and repeat the above steps to determine whether it will collide with the protective net.

[0024] If not, the preset distance position inside the protective net shall be used as the target detection position.

[0025] In some embodiments, determining whether the extension of the telescopic rod will collide with the protective net based on the current position of the underwater drone and the parameter characteristics of the telescopic structure includes:

[0026] Based on the structural characteristics of the protective net, the mesh size is determined;

[0027] Based on the parametric characteristics of the telescopic structure, the diameter of the telescopic rod is determined;

[0028] Based on the current position of the underwater drone, determine the angle between the extension of the telescopic rod and the plane where the protective net is located;

[0029] Based on the included angle, the size of the mesh, and the diameter of the telescopic rod, it is determined whether the telescopic rod will collide with the protective net after it extends.

[0030] In some embodiments, performing image analysis on the first image to determine whether the first image meets preset detection requirements includes:

[0031] Evaluate the sharpness and / or brightness of the first image;

[0032] Determine whether the sharpness index is lower than a second threshold, and / or whether the brightness index is lower than a third threshold;

[0033] If the sharpness index is lower than the second threshold or the brightness index is lower than the third threshold, then the first image is determined not to meet the preset requirements.

[0034] and / or;

[0035] Anomaly detection is performed on the image content of the first image;

[0036] In response to the detection of a suspicious item in the image content, it is determined that the first image does not meet the preset requirements.

[0037] In some embodiments, acquiring a second image of the target detection area using the second camera of the underwater drone includes:

[0038] In response to the clarity index falling below a second threshold or the brightness index falling below a third threshold, the fill light integrated with the second camera is turned on to provide fill light to the target detection area;

[0039] Under supplemental lighting conditions, the second image of the target detection area is acquired using the second camera of the underwater drone.

[0040] Secondly, this application provides a hull inspection device based on an underwater drone, the hull inspection device based on an underwater drone comprising:

[0041] The sending module is used to present the hull partition detection interface on the client and send detection commands to the underwater drone in response to the user's selection of the target detection area.

[0042] The first acquisition module is used to control the underwater drone to navigate to the target detection area of ​​the ship's hull based on the detection command, and to acquire a first image of the target detection area using the first camera of the underwater drone.

[0043] The analysis module is used to perform image analysis on the first image to determine whether the first image meets the preset detection requirements;

[0044] The second acquisition module is used to acquire a second image of the target detection area using the second camera of the underwater drone when the first image does not meet the preset detection requirements; wherein the second camera is closer to the target detection area than the first camera.

[0045] The storage module is used to store the first image and the second image and associate them with the corresponding detection task information.

[0046] Thirdly, this application provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus;

[0047] Memory, used to store computer programs;

[0048] When the processor executes a program stored in memory, it implements the steps of the hull detection method based on an underwater unmanned aerial vehicle as described in any embodiment of the first aspect.

[0049] Fourthly, a computer-readable storage medium is provided having a computer program stored thereon, which, when executed by a processor, implements the steps of the hull detection method based on an underwater unmanned aerial vehicle as described in any embodiment of the first aspect.

[0050] The technical solutions provided in this application have the following advantages compared with the prior art:

[0051] By employing a first camera for initial exploration and image quality analysis (such as sharpness and brightness assessment), and automatically activating a retractable second camera for close-up shooting when the image does not meet requirements, the system effectively overcomes the problems of obstructed vision and poor image quality caused by protective netting, internal darkness, and turbid water, ensuring the acquisition of clear and usable images of the valve chamber's interior. Furthermore, by analyzing the environmental characteristics of the first image (such as the structure of the protective netting), the system automatically calculates the path of the telescopic boom to avoid collisions and precisely plans the target position for the second camera, reducing manual intervention and improving operational efficiency and safety. Attached Figure Description

[0052] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0053] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, for those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0054] Figure 1 This is a flowchart illustrating a preferred embodiment of the hull inspection method based on an underwater drone according to this application.

[0055] Figure 2 This is an exemplary structural diagram of the underwater drone of this application;

[0056] Figure 3 This is a schematic diagram of the link between the underwater drone and the client in this application;

[0057] Figure 4 This is a schematic diagram of a preferred embodiment of the hull inspection device based on an underwater drone in this application.

[0058] Figure 5 This is a schematic diagram of a preferred embodiment of the electronic device of this application;

[0059] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0060] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments in this application without inventive effort are within the scope of protection of this application.

[0061] It should be noted that the descriptions using terms such as "first" and "second" in this application are for descriptive purposes only and should not be construed as indicating or implying their relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of those features. Furthermore, the technical solutions of the various embodiments can be combined with each other, but this must be based on the ability of those skilled in the art to implement them. If the combination of technical solutions is contradictory or impossible to implement, such a combination of technical solutions should be considered non-existent and not within the scope of protection claimed in this application.

[0062] Reference Figure 1The diagram shown is a flowchart illustrating an embodiment of the underwater drone-based hull inspection method of this application. The method is executed by an electronic device, which can be implemented by a software system and / or a hardware system. The underwater drone-based hull inspection method includes:

[0063] Step 101: The hull partition detection interface is displayed on the client, and in response to the user's selection of the target detection area, a detection command is sent to the underwater drone.

[0064] The client refers to the terminal device that runs the ship inspection software, such as a mobile application or computer software. The hull section inspection interface refers to the graphical user interface displayed on the client. The interface can include different views of the hull, such as the port side view, starboard side view, and bottom view.

[0065] The target detection area refers to a specific part of the hull selected by the user on the hull partition detection interface, such as the port side, starboard side, or bottom of the hull.

[0066] The selection operation refers to the interactive actions performed by the user on the client interface through touch, click, or gesture to confirm the selection of the target detection area.

[0067] The detection command refers to the control command sent by the client to the underwater drone, which instructs the underwater drone to begin detecting the target detection area.

[0068] In some embodiments, the user selects the target detection area by a selection operation (such as a touch operation), the client generates detection instructions based on the selection operation, and sends the detection instructions to the underwater drone through an application programming interface (API).

[0069] Step 102: Based on the detection command, control the underwater drone to navigate to the target detection area of ​​the ship's hull, and use the first camera of the underwater drone to acquire a first image of the target detection area.

[0070] An underwater drone is a remotely operated underwater vehicle, such as a ROV (Remotely Operated Vehicle). An exemplary underwater drone structure can be seen below. Figure 2 Related descriptions.

[0071] The first camera refers to the main camera installed on the underwater drone. The first image refers to the image data acquired using the first camera, which can be a still photograph or a video stream.

[0072] Step 103: Perform image analysis on the first image to determine whether the first image meets the preset detection requirements.

[0073] Image analysis refers to the process of processing and quality assessment of acquired image data. Image analysis can be performed automatically through algorithms or with user assistance.

[0074] Preset detection requirements refer to pre-defined image quality standards used to determine whether an image is suitable for the detection purpose.

[0075] In some embodiments, image analysis may be performed on the first image. The analysis process may include using image processing algorithms, such as calculating image sharpness, brightness histogram, or object recognition.

[0076] For further explanation on determining whether the first image meets the preset detection requirements, please refer to the relevant description below.

[0077] Step 104: If the conditions are not met, then the second image of the target detection area is acquired using the second camera of the underwater drone.

[0078] The second camera is closer to the target detection area than the first camera.

[0079] The second camera refers to an auxiliary camera installed on an underwater drone. The second camera can be smaller than the first camera. For example, a camera connected via a telescopic rod can have a small diameter, allowing it to penetrate a 3cm mesh opening with an insertion depth of ≥1m, enabling close-up imaging of the valve chamber's interior.

[0080] The second image refers to the image data captured by the second camera.

[0081] In some embodiments, acquiring a second image of the target detection area using the second camera of the underwater drone includes: controlling the telescopic structure of the underwater drone to activate, so as to move the second camera mounted on the end of the telescopic pole to the target detection position; and controlling the second camera to acquire a second image of the target detection area at the target detection position.

[0082] A telescopic structure is a retractable mechanical device installed on an underwater drone. The telescopic structure includes a telescopic rod, a transmission mechanism (such as belt drive, lead screw drive, or friction wheel drive), and a drive motor.

[0083] The end of the telescopic boom refers to the farthest part of the telescopic boom relative to the underwater drone body, i.e., the head of the telescopic boom.

[0084] In some embodiments, after receiving control commands, the underwater drone can control the telescopic structure to start, for example, by activating the drive motor. The transmission mechanism (such as belt drive) converts the rotational motion of the motor into the linear motion of the telescopic rod, causing the telescopic rod to extend from its retracted state. The telescopic rod then moves the second camera at its end to the target detection position.

[0085] Step 105: Store the first image and the second image, and associate them with the corresponding detection task information.

[0086] Storage refers to the process of saving image data to a storage medium, such as saving it to the SD card of an underwater drone or the local database of a client.

[0087] Detection task information refers to relevant data about the detection task, including task identifier, creation time, regional location, user information, etc.

[0088] Association refers to establishing a link between image files and detection task information in the storage system, enabling images to be retrieved and categorized for specific tasks. Association can be achieved through database keys, such as linking image records with detection task records using the record ID (record_id) as a foreign key. Simultaneously, images can be associated with specific regions for easy export or viewing.

[0089] In some embodiments, activating the telescopic structure of the underwater drone to move the second camera mounted at the end of the telescopic pole to the target detection position may include the following operations:

[0090] S11, Based on the first image, extract the environmental features of the target detection area.

[0091] Environmental features refer to the visual attributes identified from the first image that describe the physical environment of the target detection area. Environmental features include the shape, size, and location of obstacles, as well as water conditions (such as turbidity) and spatial structures (such as mesh openings and valve chamber openings).

[0092] In some embodiments, environmental features of the target detection area can be extracted by image processing of the first image. The extraction method can be based on image analysis algorithms, such as edge detection algorithms to identify the outline of obstacles (such as protective nets), texture analysis algorithms to assess water turbidity, or feature point recognition algorithms to locate key structures (such as valve chamber edges).

[0093] S12, Based on the environmental characteristics, determine the target detection location.

[0094] In some embodiments, the target detection location can be determined by performing calculations or logical judgments based on the extracted environmental features.

[0095] In some embodiments, determining the target detection location based on the environmental features may include the following operations:

[0096] S21, Based on the environmental characteristics, determine the structural characteristics of the protective netting in the target detection area.

[0097] Protective nets are mesh structures installed in specific parts of a ship's hull (such as seabed valve compartments) for protection.

[0098] Structural characteristics refer to the physical geometric properties of the protective net, including but not limited to the size, shape, and distribution density of the mesh, as well as the spatial position and orientation of the protective net relative to the hull and underwater drones.

[0099] In some embodiments, visual information related to the protective netting can be further analyzed using image processing algorithms based on the extracted environmental features to quantify its structural characteristics. For example, the outline of the protective netting identified in the first image can be analyzed to measure the average size of its mesh openings (e.g., converted by pixels), the thickness of the mesh lines, and the approximate normal direction (i.e., orientation) of the entire protective netting plane.

[0100] S22, based on the current position of the underwater drone, the parameter characteristics of the telescopic structure, and the structural characteristics of the protective net, determine whether the extension of the telescopic rod will collide with the protective net.

[0101] The current position of an underwater drone refers to its real-time coordinates and attitude angles in three-dimensional space. The current position can be obtained based on the underwater drone's positioning system (such as GPS, depth sensors, or inertial measurement units).

[0102] The parametric characteristics of a telescopic structure refer to the mechanical properties of the telescopic rod itself, including the maximum length, minimum length, diameter, range of motion (angle limitation), and telescopic speed.

[0103] In some embodiments, determining whether the extension of the telescopic rod will collide with the protective net based on the current position of the underwater drone and the parameter characteristics of the telescopic structure may include the following operations:

[0104] S31, Based on the structural characteristics of the protective net, determine the mesh size.

[0105] Mesh size refers to the diameter of a single mesh opening in a protective mesh. In some embodiments, parameters describing the mesh size can be extracted from the acquired structural feature data of the protective mesh to obtain the mesh size.

[0106] S32, Based on the parameter characteristics of the telescopic structure, determine the diameter of the telescopic rod.

[0107] The diameter refers to the outer diameter of the telescopic rod, that is, the width of its cross-section. In some embodiments, the diameter parameter of the telescopic rod can be directly read from the parameter characteristics of the telescopic structure.

[0108] S33, based on the current position of the underwater drone, determine the angle between the extension of the telescopic rod and the plane where the protective net is located.

[0109] The included angle refers to the angle between the central axis of the telescopic pole and the plane containing the protective netting when the pole is fully extended. The included angle reflects the direction in which the telescopic pole approaches the protective netting. For example, if the telescopic pole extends directly towards the center of the netting's mesh, its angle with the normal to the plane of the protective netting is smaller (e.g., close to 0 degrees), while its angle with the plane containing the protective netting is larger.

[0110] In some embodiments, the equation of the plane on which the protective net is located can be calculated and fitted based on the structural characteristics of the protective net (such as the three-dimensional coordinates of the identified corner points of the net). Based on the current position (including position and attitude) of the underwater drone and the fixed connection relationship between the telescopic rod and the main body of the drone, the central axis vector of the telescopic rod in the planned extension direction can be calculated. Through vector operation, the angle between the central axis vector of the telescopic rod and the normal vector of the plane on which the protective net is located can be calculated, or the angle between the axis vector and the plane itself can be calculated.

[0111] S34, based on the included angle, the size of the mesh, and the diameter of the telescopic rod, determine whether the telescopic rod will collide with the protective net after it extends.

[0112] For a telescopic pole to pass through a safety net without collision, its orthographic projection onto the net's plane must fall completely within the effective passage area of ​​one of the net's mesh openings, with a safety margin between the pole and the mesh edge. For example, considering the effect of the included angle, the projection of the telescopic pole onto the net's plane can become an ellipse, with its minor axis length depending on the pole's diameter and the included angle. When the included angle is 90 degrees (i.e., perpendicular incidence), the projection is circular with a diameter equal to the pole's diameter. As the included angle increases, the minor axis of the projection lengthens, and the required minimum mesh size increases.

[0113] Therefore, the calculated projection minor axis length (or equivalent through size) is compared with the mesh size. If the projection minor axis length is less than the mesh size and there is a certain safety margin, it can be determined that a collision will not occur; otherwise, it is determined that a collision will occur.

[0114] S23, If yes, adjust the current position of the underwater drone and repeat the above steps to determine whether it will collide with the protective net.

[0115] The "adjustment-judgment" process can be repeated multiple times until a position for the underwater drone that will not collide with it is found. For example, if the initial judgment is that the telescopic pole will collide with the netting in the upper left corner of the protective net, adjust the underwater drone to move 20 centimeters to the lower right and deflect it by 5 degrees, and repeat the judgment. At this point, the telescopic pole can be directly aligned with and pass through a mesh, thus avoiding a collision.

[0116] S24, if not, use the preset distance position inside the protective net as the target detection position.

[0117] The target detection location is determined as a point or area offset by a preset distance from the plane of the protective net along the direction of the telescopic pole extending into the protective net.

[0118] S13, Based on the target detection position, determine the extension length and extension angle of the telescopic rod.

[0119] The telescopic length refers to the specific length that the telescopic pole needs to extend or retract.

[0120] The extension angle refers to the angle at which the extension boom needs to deflect relative to the main body of the underwater drone. The extension angle determines the direction of the extension boom's extension and can include pitch angle, yaw angle, etc.

[0121] In some embodiments, the telescopic length and telescopic angle can be determined based on the maximum and minimum lengths and the range of active angles of the telescopic rod. For example, if the target detection position can be reached, the telescopic length and telescopic angle that reach the target detection position are used as the final parameters; otherwise, the telescopic parameters and telescopic angle that can reach the closest target detection position are used as the final parameters.

[0122] S14, based on the telescopic length and the telescopic angle, control the telescopic rod to move the second camera to the target detection position.

[0123] In this embodiment, by determining the telescopic length and telescopic angle, the position of the second camera on the telescopic pole can be accurately controlled, thereby capturing a clear second image.

[0124] In some embodiments, the step of performing image analysis on the first image to determine whether the first image meets preset detection requirements includes: evaluating the sharpness index and / or brightness index of the first image; determining whether the sharpness index is lower than a second threshold and / or whether the brightness index is lower than a third threshold; if the sharpness index is lower than the second threshold or the brightness index is lower than the third threshold, then determining that the first image does not meet the preset requirements.

[0125] Evaluation is the process of quantifying image attributes through calculation or measurement.

[0126] The sharpness index is a quantitative parameter used to measure the resolution of image details and the sharpness of edges. The higher the sharpness index value, the sharper the image.

[0127] The brightness index is a quantitative parameter used to measure the overall brightness of an image. The brightness index value reflects the average illumination level of the image.

[0128] Sharpness metrics can be assessed by calculating the gradient magnitude of an image or by performing frequency domain analysis. For example, calculating the rate of change in pixel intensity in edge regions of an image indicates higher sharpness; a larger rate of change indicates higher sharpness. Brightness metrics can be assessed by calculating the average or median grayscale value of all pixels in an image.

[0129] The second threshold is a critical value set for the sharpness index. If the sharpness index is below the second threshold, the image is considered to be insufficiently sharp.

[0130] The third threshold is a critical value set for the brightness index. If the brightness index is below the third threshold, the image is considered to be insufficiently bright.

[0131] In some embodiments, performing image analysis on the first image to determine whether the first image meets preset detection requirements includes: performing anomaly detection on the image content of the first image; and determining that the first image does not meet the preset requirements in response to detecting a suspicious item in the image content.

[0132] The image content refers to the visual elements and scenes presented in the first image, including the ship's structure, protective netting, and any unusual objects that may be present. For example, contraband may be hidden in the ship's underwater valve compartment.

[0133] Anomaly detection refers to the process of identifying whether there are objects or features in the content of an image that do not conform to the normal hull structure or expected state through image analysis technology.

[0134] In some embodiments, object detection or pattern recognition algorithms can be used to scan an image to find specific shapes, textures, or regions that are significantly different from the background. Anomaly detection can be based on comparison with predefined normal templates or can use machine learning models to identify anomalous patterns.

[0135] Suspicious items are objects identified in image content through anomaly detection that may be contraband or improperly carried items.

[0136] For example, the anomaly detection algorithm identifies a regular rectangular object in the shadow of the seabed valve hull in the first image. This object is not a known valve hull component and is marked as a suspicious item. The system determines that a second camera is needed to capture a more detailed second image to confirm whether the object is contraband. Therefore, the first image is determined not to meet the preset requirement of directly completing the evaluation.

[0137] It should be noted that the embodiments described above, which perform image analysis on the first image to determine whether the first image meets the preset detection requirements, can be executed individually or simultaneously. For example, performing image analysis on the first image to determine whether the first image meets the preset detection requirements includes: evaluating the sharpness index and / or brightness index of the first image; determining whether the sharpness index is lower than a second threshold and / or whether the brightness index is lower than a third threshold; if the sharpness index is lower than the second threshold or the brightness index is lower than the third threshold, then determining that the first image does not meet the preset requirements; and / or performing anomaly detection on the image content of the first image; in response to detecting suspicious items in the image content, determining that the first image does not meet the preset requirements.

[0138] In some embodiments, acquiring a second image of the target detection area using the second camera of the underwater drone includes: controlling a supplementary light integrated with the second camera to turn on in response to the sharpness index being lower than a second threshold or the brightness index being lower than a third threshold, so as to provide supplementary lighting to the target detection area; and acquiring a second image of the target detection area using the second camera of the underwater drone in the supplementary lighting environment.

[0139] Integration refers to the simultaneous installation of a supplementary light and a second camera on the telescopic pole.

[0140] A fill light is a light source that provides additional illumination to the second camera to improve lighting conditions in the target detection area, thereby increasing image brightness and detail visibility.

[0141] The supplementary lighting environment refers to the environmental state of the target detection area where the lighting conditions are improved after the supplementary lights are turned on.

[0142] Reference Figure 2 The diagram shown is an exemplary structural diagram of the underwater drone of this application. The underwater drone includes an underwater telescopic camera (second camera), which can be used for the inspection of seabed valve compartments of large ships. The underwater drone has visual inspection capabilities and can transmit images in real time. Its controllable telescopic rod can extend into a 3cm mesh barrier and into the valve compartment to a depth of 1m for observation, enabling the identification of contraband.

[0143] The main camera (first camera) is fixed to the underwater drone body by a mounting bracket. The telescopic rod is extended and retracted by a drive motor and belt. The telescopic rod is equipped with a secondary camera (second camera).

[0144] The main functions of the exemplary underwater drone model P200 PRO are as follows:

[0145] (1) Connects to computer software via ROV data link, and has real-time image transmission and video recording / photo taking functions;

[0146] (2) Equipped with an ROV controllable telescopic rod, the head of the telescopic rod is connected to a camera, the telescopic rod has underwater telescopic function, 50cm in the retracted state and more than 100cm in the extended state;

[0147] (3) The camera, telescopic pole, and cable can extend into the 3cm mesh barrier, and the extension part is ≥1m;

[0148] (4) The entire system can operate in water up to 20m deep;

[0149] (5) Buoyancy balancing;

[0150] (6) 360p or higher resolution, 120° field of view;

[0151] (7) Equipped with supplementary lighting.

[0152] The waterproof sealing of the second camera can be achieved through potting combined with processes such as gaskets and sealing rings. For example, full potting and sealing ring sealing are both possible.

[0153] The second camera has a smaller diameter and is equipped with a supplementary light. It is also retractable. By using a fully encapsulated process and combining it with a split camera and a miniature endoscope camera, it can adapt to underwater working environments.

[0154] The power transmission method of the telescopic pole can be belt drive, screw drive, or friction wheel drive.

[0155] Reference Figure 3 The diagram shown illustrates the link between the underwater drone and the client in this application. The client can be a shore-based computer that connects to the underwater drone's remote controller via Wi-Fi. The remote controller connects to a PLC installed in the underwater drone (ROV), and within the ROV, it connects to an external motherboard via a network port and serial port. Ultimately, the external motherboard controls the telescopic boom via PWM, the supplementary lighting via GPIO, and the camera via USB, thus achieving control and data transmission.

[0156] Reference Figure 4 The diagram shown is a functional module schematic of the hull inspection device 100 based on an underwater drone in this application.

[0157] The underwater drone-based hull inspection device 100 described in this application is installed in an electronic device. Depending on its function, the underwater drone-based hull inspection device 100 includes a transmitting module 110, a first acquisition module 120, an analysis module 130, a second acquisition module 140, and a storage module 150. These modules can also be referred to as units, which are a series of computer program segments that can be executed by the processor of an electronic device and perform a fixed function, and are stored in the memory of the electronic device.

[0158] In this embodiment, the functions of each module / unit are as follows:

[0159] The sending module 110 is used to present the hull partition detection interface on the client and send detection commands to the underwater drone in response to the user's selection of the target detection area.

[0160] The first acquisition module 120 is used to control the underwater drone to navigate to the target detection area of ​​the ship's hull based on the detection command, and to acquire a first image of the target detection area using the first camera of the underwater drone.

[0161] The analysis module 130 is used to perform image analysis on the first image to determine whether the first image meets the preset detection requirements;

[0162] The second acquisition module 140 is used to acquire a second image of the target detection area using the second camera of the underwater drone when the first image does not meet the preset detection requirements; wherein the second camera is closer to the target detection area than the first camera.

[0163] The storage module 150 is used to store the first image and the second image and associate them with the corresponding detection task information.

[0164] The specific implementation of the hull inspection device based on underwater drones in this application is largely the same as the specific implementation of the hull inspection method based on underwater drones described above, and will not be repeated here.

[0165] Reference Figure 5 The diagram shown is a schematic representation of a preferred embodiment of the electronic device of this application.

[0166] The electronic device includes a processor 111, a communication interface 112, a memory 113, and a communication bus 114, wherein the processor 111, the communication interface 112, and the memory 113 communicate with each other through the communication bus 114.

[0167] Memory 113 is used to store computer programs, such as a hull inspection program based on an underwater drone;

[0168] In some embodiments, the processor 111 may be a central processing unit (CPU), a controller, a microcontroller, a microprocessor, or other data processing chip. The processor 111 can be used to control the overall operation of the electronic device, such as performing data interaction or communication-related control and processing. In this embodiment, the processor 111 is used to run program code stored in the memory 113 or process data.

[0169] The communication interface 112 may optionally include a standard wired interface or a wireless interface (such as a Wi-Fi interface). The communication interface 112 may also be used to establish a communication connection between the electronic device and other electronic devices.

[0170] The memory 113 includes at least one type of readable storage medium, including flash memory, hard disk, multimedia card, card-type memory (e.g., SD or DX memory), random access memory (RAM), static random access memory (SRAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), magnetic memory, magnetic disk, optical disk, etc. In some embodiments, the memory 113 may be an internal storage unit of the electronic device, such as the hard disk or memory of the electronic device. In other embodiments, the memory 113 may also be an external storage device of the electronic device, such as a plug-in hard disk, smart media card (SMC), secure digital (SD) card, flash card, etc. of the electronic device. Of course, the memory 113 may include both internal storage units and external storage devices of the electronic device. In this embodiment, the memory 113 can be used to store the operating system and various computer programs installed on the electronic device, such as the program code of a hull inspection program based on an underwater drone. In addition, the memory 113 can also be used to temporarily store various types of data that have been output or will be output.

[0171] Figure 5 Only an electronic device with a processor 111, a communication interface 112, a memory 113, and a communication bus 114 is shown. However, it should be understood that it is not required to implement all of the components shown, and more or fewer components may be implemented instead.

[0172] In one embodiment of this application, the processor 111, when executing the program stored in the memory 113, implements the hull detection method based on an underwater drone provided in any of the foregoing method embodiments, including:

[0173] The client displays the hull partition detection interface and, in response to the user's selection of the target detection area, sends detection commands to the underwater drone.

[0174] Based on the detection command, the underwater drone is controlled to navigate to the target detection area of ​​the ship's hull, and the first camera of the underwater drone is used to capture the first image of the target detection area.

[0175] Image analysis is performed on the first image to determine whether the first image meets the preset detection requirements;

[0176] If the conditions are not met, a second image of the target detection area is acquired using the second camera of the underwater drone; wherein the second camera is closer to the target detection area than the first camera.

[0177] The first image and the second image are stored and associated with the corresponding detection task information.

[0178] For a detailed explanation of the above steps, please refer to the above. Figure 1 Description of the flowchart of an embodiment of a ship hull inspection method based on underwater unmanned aerial vehicles.

[0179] Furthermore, this application also proposes a computer-readable storage medium that is both non-volatile and volatile. This computer-readable storage medium is any one or any combination of several of the following: hard disk, multimedia card, SD card, flash memory card, SMC, read-only memory (ROM), erasable programmable read-only memory (EPROM), portable compact disc read-only memory (CD-ROM), USB memory, etc. The computer-readable storage medium includes a data storage area and a program storage area. The program storage area stores a hull detection program based on an underwater drone. When executed by a processor, the hull detection program based on the underwater drone performs the following operations:

[0180] The client displays the hull partition detection interface and, in response to the user's selection of the target detection area, sends detection commands to the underwater drone.

[0181] Based on the detection command, the underwater drone is controlled to navigate to the target detection area of ​​the ship's hull, and the first camera of the underwater drone is used to capture the first image of the target detection area.

[0182] Image analysis is performed on the first image to determine whether the first image meets the preset detection requirements;

[0183] If the conditions are not met, a second image of the target detection area is acquired using the second camera of the underwater drone; wherein the second camera is closer to the target detection area than the first camera.

[0184] The first image and the second image are stored and associated with the corresponding detection task information.

[0185] The specific implementation of the computer-readable storage medium in this application is largely the same as the specific implementation of the above-described hull detection method based on underwater unmanned aerial vehicles, and will not be repeated here.

[0186] It should be noted that the sequence numbers of the embodiments in this application are merely for descriptive purposes and do not represent the superiority or inferiority of the embodiments. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0187] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware simulation platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device to execute the methods described in the various embodiments of this application.

[0188] The above are merely preferred embodiments of this application and do not limit the patent scope of this application. Any equivalent structural or procedural transformations made using the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A method for hull inspection based on an underwater unmanned aerial vehicle (UAV), characterized in that, The method includes: The client displays the hull partition detection interface and, in response to the user's selection of the target detection area, sends detection commands to the underwater drone. Based on the detection command, the underwater drone is controlled to navigate to the target detection area of ​​the ship's hull, and the first camera of the underwater drone is used to capture the first image of the target detection area. Image analysis is performed on the first image to determine whether the first image meets the preset detection requirements; If the conditions are not met, a second image of the target detection area is acquired using the second camera of the underwater drone, specifically including: Based on the first image, the environmental features of the target detection area are extracted, and the structural features of the protective netting in the target detection area are determined; Based on the current position of the underwater drone, the parameter characteristics of the telescopic structure, and the structural characteristics of the protective net, it is determined whether the second camera mounted on the end of the telescopic pole will collide with the protective net. If so, adjust the current position of the underwater drone and repeat the above steps to determine the collision. If not, a preset distance position inside the protective net is used as the target detection position, and the telescopic rod is controlled to move the second camera to the target detection position according to the range limit of the telescopic structure; wherein, if the target detection position exceeds the upper limit of the telescopic rod's range, the position corresponding to the upper limit of the range is used as the final sampling position to acquire the second image of the target detection area; The second camera is closer to the target detection area than the first camera. The first image and the second image are stored and associated with the corresponding detection task information.

2. The hull inspection method based on underwater unmanned aerial vehicles as described in claim 1, characterized in that, The step of determining whether the extension of the telescopic rod will collide with the protective net based on the current position of the underwater drone and the parameter characteristics of the telescopic structure includes: Based on the structural characteristics of the protective net, the mesh size is determined; Based on the parametric characteristics of the telescopic structure, the diameter of the telescopic rod is determined; Based on the current position of the underwater drone, determine the angle between the extension of the telescopic rod and the plane where the protective net is located; Based on the included angle, the size of the mesh, and the diameter of the telescopic rod, it is determined whether the telescopic rod will collide with the protective net after it extends.

3. The hull inspection method based on underwater unmanned aerial vehicles as described in claim 1, characterized in that, The step of performing image analysis on the first image to determine whether the first image meets preset detection requirements includes: Evaluate the sharpness and / or brightness of the first image; Determine whether the sharpness index is lower than a second threshold, and / or whether the brightness index is lower than a third threshold; If the sharpness index is lower than the second threshold or the brightness index is lower than the third threshold, then the first image is determined not to meet the preset requirements. and / or; Anomaly detection is performed on the image content of the first image; In response to the detection of a suspicious item in the image content, it is determined that the first image does not meet the preset requirements.

4. The hull inspection method based on underwater unmanned aerial vehicles as described in claim 3, characterized in that, The step of acquiring a second image of the target detection area using the second camera of the underwater drone includes: In response to the clarity index falling below a second threshold or the brightness index falling below a third threshold, the fill light integrated with the second camera is turned on to provide fill light to the target detection area; Under supplemental lighting conditions, the second image of the target detection area is acquired using the second camera of the underwater drone.

5. A hull inspection device based on an underwater unmanned aerial vehicle (UAV), characterized in that, The device includes: The sending module is used to present the hull partition detection interface on the client and send detection commands to the underwater drone in response to the user's selection of the target detection area. The first acquisition module is used to control the underwater drone to navigate to the target detection area of ​​the ship's hull based on the detection command, and to acquire a first image of the target detection area using the first camera of the underwater drone. The analysis module is used to perform image analysis on the first image to determine whether the first image meets the preset detection requirements; The second acquisition module is used to acquire a second image of the target detection area using the second camera of the underwater drone when the first image does not meet the preset detection requirements. When acquiring the second image, the second acquisition module performs the following operations: based on the first image, extracts the environmental features of the target detection area and determines the structural features of the protective netting in the target detection area; based on the current position of the underwater drone, the parameter features of the telescopic structure, and the structural features of the protective netting, determines whether the second camera mounted on the end of the telescopic pole will collide with the protective netting; if so, adjusts the current position of the underwater drone and repeats the collision determination; if not, uses a preset distance position inside the protective netting as the target detection position, and controls the telescopic pole to move the second camera to the target detection position according to the range limit of the telescopic structure; if the target detection position exceeds the upper limit of the telescopic pole's range, the position corresponding to the upper limit of the range is used as the final sampling position to acquire the second image of the target detection area; wherein the second camera is closer to the target detection area than the first camera. The storage module is used to store the first image and the second image and associate them with the corresponding detection task information.

6. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; The processor, when executing the program stored in the memory, implements the hull detection method based on any one of claims 1 to 4.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the hull detection method based on an underwater drone as described in any one of claims 1 to 4.

Images