A method for monitoring ship interior coatings based on pixel scanning and laser scanning

Abstract

The present invention relates to the field of corrosion monitoring technology, and specifically discloses a method for monitoring ship interior tank coatings based on pixel scanning and laser scanning. The method comprises: determining multiple composite information collection positions based on structural information of the ship interior tank, wherein the sum of the field of view of all composite information collection positions covers all to-be-detected ranges of the ship interior tank; generating an interior tank image of the ship interior tank based on the column pixel scanning information; generating point cloud information of the ship interior tank based on the two-dimensional laser scanning information; and analyzing the coating corrosion status of the ship interior tank based on the interior tank image and the point cloud information to generate coating monitoring results. The present invention solves the problems of image distortion and detail loss caused by the complex structure of the ship interior tank and insufficient light in ship interior tank coating monitoring through intelligent planning of composite information collection positions and a multimodal data synchronous acquisition mechanism.

Description

Technical Field

[0001] The present invention relates to the technical field of ship monitoring, and in particular to a ship interior tank coating monitoring method based on pixel scanning and laser scanning. Background Art

[0002] Ship interiors (including cargo holds, ballast tanks, and fuel tanks) are constantly exposed to corrosive environments such as moisture, salt spray, and chemicals. This can lead to corrosion of metal structures, posing a threat to ship safety. To protect these critical areas and extend their service life, protective coatings are often applied to the interior surfaces. However, in practice, these coatings can fail due to problems such as rust. Therefore, regular monitoring of ship interior coatings is crucial.

[0003] Traditional coating condition monitoring relies primarily on manual visual inspection or localized sensor testing, which is inefficient, limited in coverage, and highly subjective. Especially in the complex interiors of ships, manual inspections struggle to capture all corrosion conditions.

[0004] With the continuous advancement of image recognition technology, technicians have begun to use this technology to inspect ship interiors. For example, dome cameras are used to capture images of interior cabins and perform corrosion identification. However, in practical applications, existing technologies face several challenges:

[0005] First, because the interior of a ship is a three-dimensional structure, image capture using conventional cameras is prone to distortion or perspective distortion, which can lead to errors in the assessment of the actual corrosion situation and reduce image accuracy. Second, the low light levels in interior cabins can significantly interfere with conventional cameras when capturing images in such conditions, resulting in image clarity and acquisition range that cannot meet actual requirements. Furthermore, some corroded areas are very small, which limits the accuracy and recognition capabilities of coating corrosion monitoring. Summary of the Invention

[0006] In order to overcome the above-mentioned technical problems existing in the prior art, an embodiment of the present invention provides a ship interior cabin coating monitoring method based on pixel scanning and laser scanning, which is applied to a ship cabin coating monitoring device. The method includes: determining multiple composite information collection positions based on the structural information of the ship interior cabin, and the sum of the field of view of all composite information collection positions covers all the to-be-detected ranges of the ship interior cabin; simultaneously collecting column pixel scanning information and two-dimensional laser scanning information at each composite information collection position; generating an interior cabin image of the ship interior cabin based on the column pixel scanning information; generating point cloud information of the ship interior cabin based on the two-dimensional laser scanning information; and analyzing the coating corrosion status of the ship interior cabin based on the interior cabin image and the point cloud information to generate a coating monitoring result.

[0007] Preferably, the method of determining multiple composite information collection positions based on the structural information of the ship's interior cabin includes: determining the spatial parameters and occlusion data of the ship's interior cabin based on the structural information; determining the information collectible area based on the spatial parameters and the occlusion data; determining the aperture of the punching, and determining the intensity impact factor of punching in the information collectible area on the ship's interior cabin based on the aperture; and determining the composite information collection position according to the intensity impact factor, a preset intensity threshold, a preset quantity threshold and a preset position constraint.

[0008] Preferably, the cabin coating monitoring device includes an integrated industrial linear array camera and a two-dimensional laser scanning radar, and the collection of column pixel scanning information and two-dimensional laser scanning information includes: determining the information collection trajectory; determining the preset shooting speed of the industrial linear array camera at the current composite information collection position, and the collection pitch angle of the two-dimensional laser scanning radar at the current composite information collection position; based on the information collection trajectory and the preset shooting speed, controlling the industrial linear array camera to perform corresponding column pixel scanning operations to obtain column pixel scanning information, wherein the column pixel scanning information includes all pixel information of the field of view corresponding to the current composite information collection position; based on the information collection trajectory and the collection pitch angle, controlling the two-dimensional laser scanning radar to perform corresponding laser scanning operations at the current composite information collection position to obtain two-dimensional laser scanning information, wherein the two-dimensional laser scanning information includes all point cloud information of the field of view corresponding to the current composite information collection position.

[0009] Preferably, determining the information acquisition trajectory includes: determining the optical axis direction of the line array camera at the current composite information acquisition position; obtaining a bulkhead normal field, determining a centering position based on the bulkhead normal field, and determining a configuration position of the line array camera based on the centering position; and determining a shooting trajectory of the line array camera based on a field of view of the current composite information acquisition position, the optical axis direction, and the configuration position.

[0010] Preferably, the method also includes: acquiring spatial depth information of the ship's interior cabin based on the two-dimensional laser scanning information; determining a first angle between each point in the ship's interior cabin and the optical axis direction based on the spatial depth information; adjusting the preset shooting speed based on the first angle to generate a first adjusted speed, and the first adjusted speed is inversely proportional to the first angle; controlling the industrial line array camera to perform corresponding column pixel scanning operations based on the information acquisition trajectory and the first adjusted speed.

[0011] Preferably, the method also includes: determining the scanning direction of the two-dimensional laser scanning radar; determining the plane angle of the current scanning surface of the ship's interior cabin based on the two-dimensional laser scanning information; determining a second angle between the scanning direction and the plane angle; judging whether the second angle is greater than a preset angle value; if so, determining a first jitter frequency and a first jitter amplitude based on the second angle; controlling the two-dimensional laser scanning radar to perform a compensation scanning operation on the current scanning surface based on the first jitter frequency and the first jitter amplitude to generate compensated laser scanning information; optimizing the two-dimensional laser scanning information based on the compensated laser scanning information to generate optimized two-dimensional laser scanning information.

[0012] Preferably, the coating corrosion status of the inner cabin of the ship is analyzed based on the inner cabin image and the point cloud information to generate a coating monitoring result, including: fusing the inner cabin image and the point cloud information to obtain fused information; performing coating corrosion status analysis on the inner cabin of the ship based on the fused information to generate corrosion height information and corrosion area information; and generating a coating monitoring result based on the corrosion height information and the corrosion area information.

[0013] Preferably, the fusing of the interior cabin image and the point cloud information to obtain fused information includes: extracting depth information of the interior cabin of the ship based on the point cloud information; performing three-dimensional conversion on the interior cabin image based on the depth information to generate fused information; or: determining multiple scanning planes of the interior cabin of the ship based on the point cloud information; performing corrosion analysis on each scanning plane to generate preliminary corrosion information; and highlighting the interior cabin image based on the preliminary corrosion information to generate fused information.

[0014] Preferably, the method also includes: after generating the coating monitoring results, determining a suspected corrosion area based on the coating monitoring results; adjusting the preset shooting speed based on the suspected corrosion area to generate a second adjustment speed, and determining a second jitter frequency and a second jitter amplitude of the two-dimensional laser scanning radar based on the suspected corrosion area, the second jitter frequency being greater than the first jitter frequency, and the second jitter amplitude being greater than the first jitter amplitude; controlling the industrial linear array camera to perform a corresponding column pixel scanning operation based on the information acquisition trajectory and the second adjustment speed; and controlling the two-dimensional laser scanning radar to perform a compensation scanning operation on the current scanning surface based on the first jitter frequency and the first jitter amplitude.

[0015] Preferably, the method also includes: obtaining historical maintenance measures and their corresponding historical maintenance time and historical maintenance location; determining the maintenance mode effectiveness coefficient based on the historical maintenance measures; determining the maintenance time attenuation coefficient based on the historical maintenance measures and their corresponding historical maintenance time; determining the spatial influence coefficient based on the historical maintenance location; determining the corrosion risk prediction value based on the maintenance mode effectiveness coefficient, the maintenance time attenuation coefficient, the spatial influence coefficient and the coating monitoring results; and generating a corrosion risk prediction map based on the corrosion risk prediction value.

[0016] Through the technical solution provided by the present invention, the present invention has at least the following technical effects: the embodiment of the present invention solves the problems of image distortion, incomplete coverage and loss of details caused by complex three-dimensional structure and insufficient light in traditional ship interior coating monitoring through intelligent planning of composite information collection positions and a synchronous collection mechanism of multimodal data.

[0017] Other features and advantages of the embodiments of the present invention will be described in detail in the subsequent detailed description. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] The accompanying drawings are used to provide a further understanding of the embodiments of the present invention and constitute a part of the specification. Together with the following detailed description, they are used to explain the embodiments of the present invention, but do not constitute a limitation of the embodiments of the present invention. In the accompanying drawings:

[0019] Figure 1 The present invention provides a flowchart of a method for monitoring ship interior coatings based on pixel scanning and laser scanning. DETAILED DESCRIPTION

[0020] The following describes the specific implementation of the embodiment of the present invention in detail with reference to the accompanying drawings. It should be understood that the specific implementation described herein is only used to illustrate and explain the embodiment of the present invention and is not used to limit the embodiment of the present invention.

[0021] The terms "system" and "network" in the embodiments of the present invention can be used interchangeably. "Multiple" refers to two or more. In view of this, in the embodiments of the present invention, "multiple" can also be understood as "at least two". "And / or" describes the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / ", unless otherwise specified, generally indicates that the previous and next associated objects are in an "or" relationship. In addition, it should be understood that in the description of the embodiments of the present invention, words such as "first" and "second" are only used to distinguish the purpose of description, and cannot be understood as indicating or implying relative importance, nor can they be understood as indicating or implying order.

[0022] Please refer to Figure 1 An embodiment of the present invention provides a method for monitoring ship interior tank coatings based on pixel scanning and laser scanning, which is applied to a ship tank coating monitoring device. The method includes:

[0023] Step 1: determining a plurality of composite information collection positions based on structural information of a ship's interior cabin, wherein the sum of the visual fields of all composite information collection positions covers all to-be-detected ranges of the ship's interior cabin.

[0024] When monitoring a ship's interior, it's necessary to first determine the acquisition locations so that holes can be drilled in the corresponding locations to allow the scanning device to access and acquire laser and pixel scan data. Due to the complexity of the ship's interior environment, collecting scan data from only one location cannot yield sufficient data. Therefore, it's necessary to simultaneously acquire scan data from multiple locations and conduct a comprehensive analysis. Existing technologies typically randomly determine acquisition locations. However, in actual applications, due to the complex structure of a ship's interior, which may include randomly distributed pipes, corners, and equipment, randomly selected acquisition locations can create coverage blind spots or structural safety hazards. Furthermore, drilling holes in locations such as the top of a ship's interior can damage its load-bearing structure and reduce its physical performance. Therefore, holes cannot be drilled arbitrarily in a ship's interior. The location and number of holes should be determined based on the actual physical strength requirements. This is especially true in complex cabin layouts and dynamic occlusion environments, where existing methods lack comprehensive optimization of structural strength and visual range.

[0025] In an embodiment of the present invention, the determination of multiple composite information collection positions based on the structural information of the ship's interior cabin includes: determining the spatial parameters and occlusion data of the ship's interior cabin based on the structural information; determining the information collectible area based on the spatial parameters and the occlusion data; determining the aperture of the punching, and determining the intensity impact factor of punching in the information collectible area on the ship's interior cabin based on the aperture; determining the composite information collection position according to the intensity impact factor, a preset intensity threshold, a preset quantity threshold and a preset position constraint.

[0026] In one possible embodiment, structural information of a ship's interior is obtained by analyzing drawings of the interior of the ship, from which spatial parameters and occlusion data are extracted. Spatial data may include, but is not limited to, information such as the length, width, height, and three-dimensional position of the interior of the ship. Occlusion data may include, but is not limited to, data on obstructing pipes, corner data, and equipment data (such as equipment dimensions and spatial position). Based on these spatial parameters and occlusion data, areas where information can be collected can be determined, and multiple initial composite information collection locations can be generated within these areas. For example, in an embodiment of the present invention, a ship's interior coating monitoring device includes an integrated industrial linear array camera and a two-dimensional laser scanning radar. A hole is opened in the top of the interior of the ship to allow the industrial linear array camera and the two-dimensional laser scanning radar to penetrate the interior of the ship and perform a scanning operation. The areas where information can be collected are, for example, located in the upper left and upper right corners of the top of the interior of the ship.

[0027] When determining the specific composite information collection locations, a ray casting algorithm can be used to calculate the corresponding field of view for different initial collection locations. Subsequently, the aperture diameter is determined based on the dimensions of the tank coating monitoring device, and finite element analysis is used to evaluate the factors affecting the strength of the ship's interior. Based on this, a multi-objective optimization model can be constructed to minimize the number of collection locations, maximize the field of view, and minimize the factors affecting the strength of the ship's interior. This multi-objective optimization model is solved using a genetic algorithm, taking into account preset intensity thresholds, quantity thresholds, and position constraints, to determine the number and precise coordinates of the composite information collection locations. The preset intensity thresholds, quantity thresholds, and position constraints are determined by technical personnel based on experience and practical needs and are not specifically limited in the embodiments of the present invention. For example, considering that the top of a ship's interior is close to the deck for easier maintenance, the image collection window can be located at the top of the interior. Since image collection windows are typically not located in the center of a ship's interior, the image collection window can be located at the top edge of the interior. For example, a large ship's interior can have four image collection windows, a medium-sized ship's can have two, and a small ship's can have one.

[0028] By integrating structural strength constraints with field of view optimization, this embodiment of the present invention effectively scans all scene information within the complex interior of a ship. It also minimizes the number of openings required, minimizing the impact of the monitoring process on the structure and ensuring its service life. Compared to random point placement methods, a multi-objective optimization model based on a ray casting algorithm and finite element analysis accurately calculates the effective field of view of each acquisition point and the mechanical impact of the openings on the bulkhead, eliminating coverage blind spots and avoiding high-stress risk areas.

[0029] After determining the composite information collection location, scanning of the vessel's interior begins. Conventional cameras used to capture images of the vessel's interior are subject to numerous factors, including light intensity, oil contamination, and obstructions. Consequently, their information collection precision and accuracy are low, failing to meet practical requirements. Furthermore, conventional scanning devices for vessel interior coating monitoring often rely on a single sensor, such as a camera or lidar, resulting in a single data dimension.

[0030] Step 2: Collect column pixel scanning information and two-dimensional laser scanning information simultaneously at each composite information collection position.

[0031] After determining the composite information acquisition position, the cabin coating monitoring device is controlled to scan the interior of the ship. Specifically, the industrial linear array camera and the two-dimensional laser scanning radar are controlled to scan simultaneously to obtain corresponding scanning information. In an embodiment of the present invention, the acquisition of column pixel scanning information and two-dimensional laser scanning information includes: determining an information acquisition trajectory; determining a preset shooting speed of the industrial linear array camera at the current composite information acquisition position, and an acquisition pitch angle of the two-dimensional laser scanning radar at the current composite information acquisition position; based on the information acquisition trajectory and the preset shooting speed, the industrial linear array camera is controlled to perform a corresponding column pixel scanning operation to obtain column pixel scanning information, and the column pixel scanning information includes all pixel information of the field of view corresponding to the current composite information acquisition position; based on the information acquisition trajectory and the acquisition pitch angle, the two-dimensional laser scanning radar is controlled to perform a corresponding laser scanning operation at the current composite information acquisition position to obtain two-dimensional laser scanning information, and the two-dimensional laser scanning information includes all point cloud information of the field of view corresponding to the current composite information acquisition position.

[0032] In one possible embodiment, a vessel interior coating monitoring device (including an integrated industrial linear array camera and a two-dimensional laser scanning radar) is connected to one end of a telescopic rod via a pan / tilt platform. The other end of the telescopic rod is then connected to a suspension bracket located outside the opening. This allows the telescopic rod to drive the vessel interior coating monitoring device vertically through the opening and into the vessel interior for scanning. Based on the multiple composite information collection positions determined, a collection trajectory for the vessel interior coating monitoring device can be pre-determined at each composite information collection position. This collection trajectory includes the collection trajectory of the industrial linear array camera and the collection trajectory of the two-dimensional laser scanning radar.

[0033] In an embodiment of the present invention, determining the information acquisition trajectory includes: determining the optical axis direction of the line array camera at a current composite information acquisition position; obtaining a bulkhead normal field, determining a centering position based on the bulkhead normal field, and determining a configuration position of the line array camera based on the centering position; determining a shooting trajectory of the line array camera based on a field of view of the current composite information acquisition position, the optical axis direction, and the configuration position; determining a scanning trajectory of the two-dimensional laser scanning radar based on the shooting trajectory; and generating an information acquisition trajectory based on the shooting trajectory and the scanning trajectory.

[0034] In one possible implementation, the optical axis direction of the line scan camera at the current composite information acquisition position is first determined. This optical axis direction is, for example, the direction of a plane extending outward from an axis coaxial with the tank coating monitoring device, with this plane being perpendicular to the sidewalls of the ship's interior. While industrial line scan cameras offer high precision and strong anti-interference capabilities, image acquisition is still affected by the angle between the captured object and the industrial line scan camera. Ideally, maintaining an angle close to 90° between the captured object and the industrial line scan camera optimizes image quality. Therefore, in this embodiment of the present invention, a bulkhead normal field is further acquired, and a centering position is determined based on this field. The configuration position of the line scan camera is then determined based on the centering position. At this configuration position, the angle between the industrial line scan camera and all bulkheads of the ship's interior is minimized, ensuring optimal overall image quality. Finally, a capture trajectory for the line scan camera is determined based on the field of view, optical axis direction, and configuration position of the current composite information acquisition position. This capture trajectory ensures that the industrial line scan camera captures all pixel information within the field of view corresponding to the current composite information acquisition position. On this basis, the scanning trajectory of the 2D laser scanning radar can be further determined. Specifically, the scanning trajectory of the 2D laser scanning radar is also determined based on the configuration position of the industrial linear array camera. Specifically, it is determined based on the configuration position of the industrial linear array camera, the field of view of the current composite information collection position, and its own scanning angle range. Based on the above shooting trajectory and scanning trajectory, the information collection trajectory can be generated.

[0035] In an embodiment of the present invention, the information acquisition trajectory is designed accordingly by combining the actual physical characteristics of the industrial line array camera during the scanning process to ensure that the industrial line array camera has minimal distortion during image acquisition, effectively improve the accuracy of image acquisition of the entire ship's interior cabin, and improve the accuracy of subsequent corrosion analysis. On this basis, the scanning trajectory of the two-dimensional laser scanning radar is determined, which can ensure that both the industrial line array camera and the two-dimensional laser scanning radar can independently complete independent information scanning work within the current field of view, thereby providing high-precision and reliable data support for subsequent accurate analysis of the corrosion situation.

[0036] At this point, the preset shooting speed for the industrial line scan camera is further determined, for example, based on actual clarity requirements; the pitch angle for the 2D laser scanning radar is also determined. After these parameters are determined, the industrial line scan camera and 2D laser scanning radar each independently collect their own information (pixel information and point cloud information) for subsequent independent analysis to improve monitoring accuracy.

[0037] During the scanning process, the cabin coating monitoring device is controlled to rotate along a predetermined information collection trajectory, and the industrial linear array camera is controlled to scan at a set shooting speed to obtain column pixel scanning information. Simultaneously, the 2D laser scanning radar is controlled to scan at a set pitch angle to obtain 2D laser scanning information.

[0038] In another embodiment, when the vertical field of view of the composite information collection location exceeds that of the industrial line scan camera, the corresponding field of view can be horizontally divided into two or more sub-fields of view, thereby generating two or more information collection tracks. This allows adaptive segmentation of data tracks across all areas of the ship's interior, covering the complex bulkhead structure. This multi-sub-field coverage strategy completely eliminates vertical scanning blind spots. Simultaneously, the capture speed and the pitch angle of the LiDAR are adjusted to ensure seamless matching of the data ranges of the two sensors, significantly improving the detection range and consistency of subtle coating defects.

[0039] The embodiment of the present invention uses an integrated industrial line array camera and a two-dimensional laser scanning radar. On the one hand, the excellent performance of the industrial line array camera is utilized to effectively solve the problems of light interference and oil pollution interference in the complex scenes of the ship's interior cabin, and realizes the accurate acquisition of the ship's interior cabin image, which can facilitate the subsequent reliable differentiation between oil pollution and corrosion, and achieve higher monitoring accuracy. On the other hand, by combining the coordinated control and acquisition parameters (information acquisition trajectory, acquisition pitch angle, etc.) of the industrial line array camera and the two-dimensional laser scanning radar, efficient and blind-spot-free automated scanning of the ship's interior cabin is achieved, ensuring the spatiotemporal synchronization of image data and point cloud data, and avoiding the complexity of repeated calibration required by traditional split equipment.

[0040] In actual applications, industrial line scan cameras use a fixed shooting speed. Although they can complete data acquisition, when faced with the complex geometric structures of ship cabins, such as curved bulkheads, the fixed shooting speed results in inconsistent image pixels collected per unit time when scanning surfaces at different angles, and cannot dynamically adjust according to the curvature of the deck. When the angle between the optical axis of the industrial line scan camera and the deck normal increases, such as when scanning a recessed area, the sampling interval between adjacent pixels at a fixed speed increases, resulting in image stretching distortion, which affects the geometric measurement amplitude of coating defects. At the same time, flat areas generate redundant data due to uniform scanning speed, while high curvature or critical areas, such as welds and corrosion spots, lose details due to insufficient sampling density, requiring multiple rescans, which is inefficient.

[0041] In order to solve the above technical problems, in an embodiment of the present invention, the method also includes: determining a first angle between each location in the interior of the ship and the direction of the optical axis based on the two-dimensional laser scanning information; adjusting the preset shooting speed based on the first angle to generate a first adjusted speed, and the first adjusted speed is inversely proportional to the first angle; and controlling the industrial line array camera to perform corresponding column pixel scanning operations based on the information acquisition trajectory and the first adjusted speed.

[0042] In one possible implementation, a normal vector estimation algorithm (such as PCA) is used to calculate the local surface normal of each point using 2D laser scanning information, thereby determining the actual angle between that point and the optical axis of the industrial line scan camera. Simultaneously, the surface normal of each region is calculated to determine its real-time angle with the camera's optical axis. The line scan camera's speed is dynamically adjusted based on the angle. When the angle is small (e.g., at a straight bulkhead), high scanning speed is maintained to improve efficiency. When the angle increases (e.g., in a curved recessed area), the speed is automatically reduced to increase pixel sampling density, thereby suppressing image perspective distortion. The spatial coordinates of the laser point cloud are synchronously fused with the camera image texture, and residual deformation is eliminated through a geometric correction model, enabling high-amplitude, seamless detection of coating defects throughout the entire tank.

[0043] The embodiments of the present invention adaptively adjust the acquisition speed of the industrial line array camera according to the actual spatial distribution in the ship's interior cabin, thereby increasing pixel density. This significantly improves the accuracy and efficiency of pixel information acquisition while ensuring data integrity, and effectively suppresses image perspective distortion.

[0044] In actual applications, due to the limitation of equipment procurement costs, the number of collection points on the two-dimensional laser scanning radar often only has the accuracy required for normal use. For example, for ordinary radars, their angular resolution is generally at the 1° level. Because the scanning beam is sparse, such as only multiple arrays scanning in a single line, the sparse data volume is difficult to meet the coating monitoring needs. If its angular resolution is increased, the equipment procurement cost will increase significantly; if the angular resolution is not increased, it will not be able to meet the monitoring accuracy requirements in large space scenarios such as ship cabins. Especially in complex bulkhead structures, there is a plane angle between the scanning plane of the two-dimensional laser scanning radar and the inner wall of the cabin, which further reduces the accuracy of the laser scanning point cloud data.

[0045] In an embodiment of the present invention, the method also includes: determining the scanning direction of the two-dimensional laser scanning radar; determining the plane angle of the current scanning surface of the ship's interior cabin based on the two-dimensional laser scanning information; determining a second angle between the scanning direction and the plane angle; judging whether the second angle is greater than a preset angle value; if so, determining a first jitter frequency and a first jitter amplitude based on the second angle; controlling the two-dimensional laser scanning radar to perform a compensation scanning operation on the current scanning surface based on the first jitter frequency and the first jitter amplitude to generate compensated laser scanning information; optimizing the two-dimensional laser scanning information based on the compensated laser scanning information to generate optimized two-dimensional laser scanning information.

[0046] In one possible embodiment, a vertical dithering device is provided on the cabin coating monitoring device. For example, the vertical dithering device can be configured with a motor + reducer to precisely control its dithering amplitude. The device is then applied to a two-dimensional laser scanning radar to drive the two-dimensional laser scanning radar to dither in the vertical direction through the vertical dithering device to achieve scanning compensation. For example, if the angular resolution of the two-dimensional laser scanning radar is 1°, then during dither compensation, the two-dimensional laser scanning radar can be controlled to first scan downward 1°, then upward 0.5°, and then based on the same principle, scan downward until the laser scan of the entire screen is completed, thereby achieving compensation for scanning accuracy. Therefore, it is necessary to determine the corresponding compensation parameters based on the actual scanning accuracy required.

[0047] Specifically, based on the 2D laser scanning information, the least squares method is used to fit the plane normal of the current scanning surface. The angle between the plane normal and the direction of gravity is calculated and used as the plane angle. Furthermore, the deviation angle between the scanning direction (i.e., the radar beam direction) and the plane angle is calculated, which is the second angle. If this deviation angle exceeds a preset threshold, vertical coverage is determined to be insufficient and jitter compensation is required. At this point, the vertical jitter frequency and amplitude of the laser radar are dynamically adjusted based on the magnitude of the second angle. For example, a larger angle increases the jitter frequency and a smaller step size of the stepper motor. By controlling the 2D laser scanning radar to perform high-frequency, micro-swings in the vertical direction, the effective scanning beam can be expanded, increasing the point cloud density of the 2D laser scanning radar scan on the cabin interior wall and improving data accuracy.

[0048] This embodiment uses dynamic jitter compensation technology to expand the scanning line beam of the two-dimensional laser scanning radar to multiple times its original size to match the field of view of the linear array camera, eliminate vertical blind spots, and increase point cloud coverage. This solves the inherent hardware differences in the vertical field of view between the two-dimensional laser scanning radar and the linear array camera, and provides a reliable solution for low-cost, high-efficiency, full-dimensional inspection of the cabin.

[0049] Step 3: Generate an interior cabin image of the ship based on the column pixel scanning information.

[0050] Step 4: Generate point cloud information of the interior of the ship based on the two-dimensional laser scanning information.

[0051] After collecting the corresponding column pixel scan information and 2D laser scan information at each composite information acquisition location, all column pixel scan information can be integrated and processed to generate an interior image of the ship's interior; and all 2D laser scan information can be integrated and processed to generate point cloud information of the ship's interior. At this point, the coating corrosion status analysis is performed based on these interior image and point cloud information.

[0052] Step 5: Analyze the coating corrosion status of the ship's interior cabin based on the interior cabin image and the point cloud information to generate a coating monitoring result.

[0053] In an embodiment of the present invention, the coating corrosion status of the inner cabin of the ship is analyzed based on the inner cabin image and the point cloud information to generate a coating monitoring result, including: fusing the inner cabin image and the point cloud information to obtain fused information; performing coating corrosion status analysis on the inner cabin of the ship based on the fused information to generate corrosion height information and corrosion area information; and generating a coating monitoring result based on the corrosion height information and the corrosion area information.

[0054] In one possible implementation, to overcome the technical problem of low accuracy and inability to meet practical needs in existing corrosion analysis using a single data source, the collected interior cabin images and point cloud data are fused to perform corrosion analysis from multiple dimensions, improving analysis accuracy. Specifically, the interior cabin images and point cloud data are first spatially and temporally aligned, texture information is extracted from the interior cabin images, and geometric information is extracted from the point cloud data. This information is then mapped into a unified 3D space using a feature matching algorithm to generate a composite data model that integrates color, depth, and surface topology information. Next, based on this composite data model, the 3D deformation and 2D diffusion characteristics of the corrosion are simultaneously analyzed. The local curvature and normal offset of the point cloud are used to quantify the depth of the coating depression. Image segmentation techniques are then used to extract the boundaries of the corroded areas and calculate the actual diffusion area. Finally, the corrosion height and area data are integrated to construct a multidimensional evaluation index, generating a graded monitoring result that includes both corrosion height and area information, providing a comprehensive diagnostic basis for coating maintenance, from local to global perspectives.

[0055] In traditional ship coating inspections, image and point cloud data fusion typically relies on simple overlay or static plane splitting analysis, resulting in inefficient data utilization. For example, the difference in coordinate systems between 2D images and 3D point clouds makes it difficult to accurately align texture and geometric information, separating apparent corrosion features from 3D deformation and making it impossible to fully quantify the corrosion impact. Furthermore, fixed threshold segmentation of the scanning plane fails to account for the dynamic geometric characteristics of curved bulkheads, leading to missed detection of localized corrosion diffusion paths and making it difficult to support accurate maintenance decisions.

[0056] In an embodiment of the present invention, the fusing of the interior cabin image and the point cloud information to obtain fused information includes: extracting depth information of the interior cabin of the ship based on the point cloud information; performing three-dimensional conversion on the interior cabin image based on the depth information to generate fused information; or: determining multiple scanning planes of the interior cabin of the ship based on the point cloud information; performing corrosion analysis on each scanning plane to generate preliminary corrosion information; and highlighting the interior cabin image based on the preliminary corrosion information to generate fused information.

[0057] In one possible implementation, a triangular mesh model of the ship's interior is constructed using point cloud data, and the three-dimensional coordinates and normal vector corresponding to each pixel are extracted. The RGB texture of the interior cabin image is mapped to the mesh vertices to generate a three-dimensional texture model. The fused information simultaneously covers color, depth, and geometric attributes.

[0058] This embodiment eliminates the coordinate system deviation between the two-dimensional image and the three-dimensional point cloud through the mapping of depth information, realizes the seamless integration of texture and geometric features, and significantly improves the accuracy of corrosion quantitative analysis.

[0059] In another possible implementation, the bulkhead is segmented into multiple scanning planes, including straight and curved surfaces, based on the curvature and density of the point cloud. Corrosion analysis algorithms, including but not limited to point cloud height difference thresholds and image color clustering, are independently executed on each scanning plane to identify preliminary corrosion areas, such as those with a height loss ≥ 0.2 mm or a color deviation exceeding 15% from the standard value. The coordinates of the preliminary corrosion areas are projected onto the interior cabin image, and fused information is generated through edge enhancement and pseudo-color highlighting (e.g., red marking) to intuitively display the location and severity of the corrosion.

[0060] This embodiment can dynamically segment the scanning plane based on geometric characteristics, accurately capture the corrosion diffusion patterns in complex areas such as curved surfaces and welds, and thus reduce missed detections and misjudgments.

[0061] Traditional methods directly determine the final corrosion area based on the corrosion area indicated by the coating inspection results. However, interference from water mist, oil stains, and other factors in the cabin can lead to unclear images and laser failure, affecting the accuracy of coating inspection. Technicians hope to further improve the accuracy of monitoring data based on existing monitoring equipment and monitoring accuracy, so as to further improve the accuracy of monitoring results.

[0062] In an embodiment of the present invention, the method also includes: after generating a coating monitoring result, determining a suspected corrosion area based on the coating monitoring result; adjusting the preset shooting speed based on the suspected corrosion area to generate a second adjustment speed, and determining a second jitter frequency and a second jitter amplitude of the two-dimensional laser scanning radar based on the suspected corrosion area, the second jitter frequency being greater than the first jitter frequency, and the second jitter amplitude being greater than the first jitter amplitude; controlling the industrial linear array camera to perform a corresponding column pixel scanning operation based on the information acquisition trajectory and the second adjustment speed; and controlling the two-dimensional laser scanning radar to perform a compensation scanning operation on the current scanning surface based on the first jitter frequency and the first jitter amplitude.

[0063] In one possible implementation, suspected corrosion areas are screened based on coating monitoring results, and their spatial distribution and risk level are marked. For the identified suspected corrosion areas, the scanning speed is significantly reduced from the established shooting speed to form a second adjusted speed. The industrial line scan camera can then be controlled to perform a second, focused scan of the suspected corrosion area at this second adjusted speed, thereby increasing the image density of the suspected corrosion area. Simultaneously, based on the first dithering frequency and amplitude, the vertical dithering frequency and amplitude are simultaneously increased to generate a second dithering frequency and amplitude, thereby further expanding the scanning beam density. At this point, the 2D laser scanning radar can be controlled to perform a second, focused scan of the suspected corrosion area to obtain denser point cloud data, thereby further improving the accuracy of corrosion identification and meeting practical needs.

[0064] This embodiment controls the linear array camera to perform low-speed, high-precision scanning of suspected corrosion areas along a trajectory, and controls the lidar to generate a dense point cloud with wide-band, high-frequency jitter, thereby obtaining more detailed features of the suspected corrosion areas. By aligning the local detailed features with the initial inspection results in time and space, it is possible to eliminate reflection and shadow artifacts and output high-confidence coating corrosion detection results.

[0065] In addition, existing ship interior tank coating corrosion risk assessment methods mainly rely on real-time monitoring data of the current coating status, such as point cloud data and / or image data, but ignore the long-term impact of historical maintenance measures on coating performance, resulting in prediction results deviating from the actual corrosion process.

[0066] In an embodiment of the present invention, the method also includes: obtaining historical maintenance measures and their corresponding historical maintenance time and historical maintenance location; determining the maintenance mode effectiveness coefficient based on the historical maintenance measures; determining the maintenance time attenuation coefficient based on the historical maintenance measures and their corresponding historical maintenance time; determining the spatial influence coefficient based on the historical maintenance location; determining the corrosion risk prediction value based on the maintenance mode effectiveness coefficient, the maintenance time attenuation coefficient, the spatial influence coefficient and the coating monitoring results; and generating a corrosion risk prediction map based on the corrosion risk prediction value.

[0067] In one possible implementation, historical maintenance data, including historical maintenance times and locations, is obtained. The time interval between the historical maintenance time and the current time is calculated. If the time interval is less than a set value, the location is identified as a low-risk area, and a predicted corrosion risk map is generated based on the low-risk areas. This predicted corrosion risk map, generated in this manner, determines risk based solely on time intervals, ignoring the differences in the corrosion inhibition effects of different maintenance measures. For example, temporary painting (with a short shelf life) and full coating replacement (long-term protection) are treated the same at the same time interval, leading to misidentification of high-risk areas. For example, a temporary maintenance area (e.g., six months after a touch-up) is marked as low-risk due to the short time interval, even though the coating has actually failed, resulting in a missed detection rate of up to 30%. The map also ignores the nonlinear degradation of coating performance. It also ignores the protective coverage of surrounding areas with maintenance measures. Localized repair welding only suppresses corrosion near the repair point, but traditional methods consider this to be globally low-risk. It also ignores the spatial impact of paint bridging. For example, a maintenance location may be located in one area, but during repainting or spraying, the paint may naturally level or splash onto adjacent areas, reducing the corrosion risk in adjacent areas.

[0068] In order to solve the above problems, in an embodiment of the present invention, the historical operation and maintenance data includes historical maintenance measures and their corresponding historical maintenance time and historical maintenance location, and a predicted corrosion risk map is generated based on the historical operation and maintenance data, including: determining the maintenance method effectiveness coefficient based on the historical maintenance measures; determining the maintenance time attenuation coefficient based on the historical maintenance measures and their corresponding historical maintenance time; determining the spatial influence coefficient based on the historical maintenance location; determining the predicted risk corrosion value based on the maintenance method effectiveness coefficient, the maintenance time attenuation coefficient and the spatial influence coefficient; and generating a predicted corrosion risk map based on the predicted risk corrosion value.

[0069] Specifically, in the ship interior coating maintenance scenario, a mapping relationship table of maintenance measures and maintenance protection effectiveness is established (for example, the protection effectiveness coefficient corresponding to full coating replacement is 1, the effectiveness coefficient of local mechanical grinding and recoating is 0.75, the efficiency coefficient of temporary spraying is 0.5, the effectiveness coefficient is obtained according to experimental fitting, and the effectiveness coefficient of coating cleaning and maintenance is 0.1), and the maintenance method effectiveness coefficient is determined according to the mapping relationship table of maintenance measures and maintenance protection effectiveness and the historical maintenance measures; a time decay function of the maintenance measure effectiveness is established, and the maintenance time decay coefficient is determined according to the time decay function, the historical maintenance measures and their corresponding historical maintenance time, and the time decay function is obtained according to experimental fitting; a mapping relationship table of maintenance measure intervals and spatial influence coefficients is established (for example, for full ship recoating, the spatial influence coefficient is 1, large-scale local mechanical grinding and recoating is 1.1, and small-scale local mechanical grinding and recoating is 1.3), and the spatial influence coefficient is determined according to the mapping relationship table of maintenance measures intervals and spatial influence coefficients and the historical maintenance position.

[0070] The embodiments of the present invention comprehensively consider the relationship between maintenance measures and maintenance effectiveness, time and space, and thoroughly solve the problem that the existing technology ignores the long-term impact of historical maintenance measures on coating performance, resulting in the prediction results deviating from the actual corrosion process.

[0071] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0072] The above describes in detail the optional implementation methods of the embodiments of the present invention in conjunction with the accompanying drawings. However, the embodiments of the present invention are not limited to the specific details in the above implementation methods. Within the technical concept of the embodiments of the present invention, various simple modifications can be made to the technical solutions of the embodiments of the present invention, and these simple modifications all fall within the scope of protection of the embodiments of the present invention.

[0073] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any appropriate manner without contradiction. To avoid unnecessary repetition, the embodiments of the present invention will not further describe various possible combinations.

[0074] In addition, various implementations of the embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the embodiments of the present invention, they should also be regarded as the contents disclosed in the embodiments of the present invention.

Claims

1. A method for monitoring ship interior coatings based on pixel scanning and laser scanning, characterized in that: Applied to a ship cabin coating monitoring device, the method comprises: Determining multiple composite information collection positions based on structural information of the ship's interior cabin, wherein the sum of the field of view of all composite information collection positions covers all to-be-detected ranges of the ship's interior cabin; At each composite information collection position, column pixel scanning information and two-dimensional laser scanning information are simultaneously collected; generating an interior cabin image of the ship's interior cabin based on the column pixel scanning information; generating point cloud information of the interior of the ship based on the two-dimensional laser scanning information; Analyzing the coating corrosion status of the ship's interior cabin based on the interior cabin image and the point cloud information to generate a coating monitoring result; The cabin coating monitoring device includes a two-dimensional laser scanning radar, the two-dimensional laser scanning radar includes a first number of scanning beams, and the method further includes: Determining a scanning direction of the two-dimensional laser scanning radar, where the scanning direction is the direction of the radar beam; Determining the plane angle of the current scanning surface of the ship's interior cabin based on the two-dimensional laser scanning information; determining a second angle between the scanning direction and the plane angle; Determining whether the second angle is greater than a preset angle value; If so, determining a first swing frequency and a first swing amplitude based on the second angle; controlling the two-dimensional laser scanning radar to perform a compensation scanning operation on a current scanning plane based on the first swing frequency and the first swing amplitude to expand a scanning line beam of the two-dimensional laser scanning radar, and generating compensated laser scanning information, wherein the compensated laser scanning information includes point cloud information of a second number of scanning line beams, where the second number is N times the first number, where N is a positive integer; The two-dimensional laser scanning information is optimized based on the compensated laser scanning information to generate optimized two-dimensional laser scanning information.

2. A method for monitoring ship interior tank coatings based on pixel scanning and laser scanning according to claim 1, characterized in that: The determining of multiple composite information collection positions based on the structural information of the ship's interior cabin includes: Determining spatial parameters and occlusion data of the ship's interior cabin based on the structural information; Determining an information-collectible area based on the spatial parameters and the occlusion data; Determining a diameter of a hole to be punched, and determining, based on the diameter of the hole, a strength impact factor of the hole in the information-collectible area on the interior of the ship; The composite information collection position is determined according to the intensity influencing factor, the preset intensity threshold, the preset quantity threshold and the preset position constraint.

3. The method for monitoring ship interior coating based on pixel scanning and laser scanning according to claim 1, characterized in that: The cabin coating monitoring device further includes an integrated industrial linear array camera, which collects column pixel scanning information and two-dimensional laser scanning information, including: Determine the information collection trajectory; Determining a preset shooting speed of the industrial linear array camera at the current composite information collection position, and a collection pitch angle of the two-dimensional laser scanning radar at the current composite information collection position; Based on the information acquisition trajectory and the preset shooting speed, the industrial line array camera is controlled to perform a corresponding column pixel scanning operation to obtain column pixel scanning information, where the column pixel scanning information includes all pixel information of a field of view corresponding to a current composite information acquisition position; Based on the information collection trajectory and the collection pitch angle, the two-dimensional laser scanning radar is controlled to perform a corresponding laser scanning operation at the current composite information collection position to obtain two-dimensional laser scanning information, wherein the two-dimensional laser scanning information includes all point cloud information of the field of view corresponding to the current composite information collection position.

4. A method for monitoring ship interior tank coatings based on pixel scanning and laser scanning according to claim 3, characterized in that: Determining the information collection trajectory includes: Determining the optical axis direction of the line array camera at the current composite information acquisition position; Acquiring a bulkhead normal field, determining a centering position based on the bulkhead normal field, and determining a configuration position of the line array camera based on the centering position; Determining a shooting trajectory of the line array camera based on the field of view of the current composite information acquisition position, the optical axis direction, and the configuration position; Determining a scanning trajectory of the two-dimensional laser scanning radar based on the shooting trajectory; An information collection trajectory is generated based on the shooting trajectory and the scanning trajectory.

5. A method for monitoring ship interior tank coatings based on pixel scanning and laser scanning according to claim 4, characterized in that: The method further comprises: Acquiring spatial depth information of the ship's interior cabin based on the two-dimensional laser scanning information; Determine a first angle between each location in the ship's interior and the optical axis based on the spatial depth information; adjusting the preset shooting speed based on the first angle to generate a first adjusted speed, where the first adjusted speed is inversely proportional to the first angle; The industrial line array camera is controlled to perform a corresponding column pixel scanning operation based on the information acquisition trajectory and the first adjusted speed.

6. The method for monitoring ship interior coating based on pixel scanning and laser scanning according to claim 1, characterized in that: The analyzing the coating corrosion state of the ship's interior cabin based on the interior cabin image and the point cloud information to generate a coating monitoring result includes: fusing the interior cabin image and the point cloud information to obtain fused information; Performing a coating corrosion status analysis on the inner cabin of the ship based on the fused information to generate corrosion height information and corrosion area information; A coating monitoring result is generated based on the corrosion height information and the corrosion area information.

7. A method for monitoring ship interior tank coatings based on pixel scanning and laser scanning according to claim 6, characterized in that: The fusing the interior cabin image and the point cloud information to obtain fused information includes: Extracting depth information of the ship's interior cabin based on the point cloud information; Performing a three-dimensional conversion on the interior cabin image based on the depth information to generate fused information; or: determining a plurality of scanning planes of the interior cabin of the ship based on the point cloud information; Perform corrosion analysis on each scanned plane to generate preliminary corrosion information; The interior cabin image is highlighted based on the preliminary corrosion information to generate fused information.

8. The method for monitoring ship interior tank coatings based on pixel scanning and laser scanning according to claim 5, characterized in that: The method further comprises: After generating the coating monitoring results, determining suspected corrosion areas based on the coating monitoring results; Adjusting the preset shooting speed based on the suspected corrosion area to generate a second adjusted speed, and determining a second swing frequency and a second swing amplitude of the two-dimensional laser scanning radar based on the suspected corrosion area, wherein the second swing frequency is greater than the first swing frequency, and the second swing amplitude is greater than the first swing amplitude; Controlling the industrial line array camera to perform a corresponding column pixel scanning operation based on the information acquisition trajectory and the second adjustment speed; The two-dimensional laser scanning radar is controlled to perform a compensation scanning operation on a current scanning surface based on the first swing frequency and the first swing amplitude.

9. A method for monitoring ship interior tank coatings based on pixel scanning and laser scanning according to any one of claims 1 to 8, characterized in that: The method further comprises: Obtain historical maintenance measures and their corresponding historical maintenance time and historical maintenance location; determining a maintenance method effectiveness coefficient based on the historical maintenance measures; Determining a maintenance time attenuation coefficient based on the historical maintenance measures and their corresponding historical maintenance times; determining a spatial impact coefficient based on the historical maintenance location; Determining a corrosion risk prediction value based on the maintenance mode effectiveness coefficient, the maintenance time attenuation coefficient, the spatial influence coefficient, and the coating monitoring result; A corrosion risk prediction map is generated according to the corrosion risk prediction value.

Images