Monitoring method and equipment for logistics fluidization of bulk cargo and storage medium

Abstract

The invention discloses a bulk cargo fluidization monitoring method and device and a storage medium, and belongs to the technical field of easy-fluidization bulk cargo supervision and safe transportation in the marine transportation industry. The method comprises the steps that before a cargo ship departs, first point cloud data of cargoes are collected through visual detection equipment, and a first image is generated; in the marching process of the cargo ship, reading second point cloud data, collected by the visual inspection equipment, of the cargo by taking preset time as an interval, and generating a second image; performing identification processing on the first point cloud data; marking a possible ponding area in the second image according to the easy ponding area; performing image comparison on the easy water accumulation area and the possible water accumulation area, and determining an actual water accumulation area in the possible water accumulation area according to a comparison result; and calculating the ponding amount corresponding to the actual ponding area so as to give an alarm when the ponding amount exceeds a preset ponding threshold value. According to the scheme, early and middle stage cargo fluidization can be monitored.

Description

Technical Field

[0001] The present invention relates to the technical field of supervision and safe transportation of bulk cargoes that are prone to fluidization in the shipping industry, and in particular to a monitoring method, equipment and storage medium for fluidization of bulk cargoes. Background Art

[0002] Among the bulk cargoes transported at sea, some cargoes (bulk cargoes that are easy to liquefy, Class A bulk cargoes) will experience water-cargo separation during transportation due to factors such as ship vibration and turbulence, that is, water seeps out of the bulk cargoes. If too much water seeps out, a large amount of free-flowing water, i.e., a huge free liquid surface, will be formed; or if the cargo and water are fully mixed, the friction resistance between the cargo molecules will be lost due to the loss of water molecules, and the upper part or the whole cargo will liquefy. Both states will greatly reduce the stability of the ship, causing the ship to tilt at a large angle or even capsize, seriously endangering the safety of personnel, ships and cargoes.

[0003] There are four main methods for monitoring cargo liquefaction. The first is for the crew to observe the amount of water in the sewage well at the bottom of the cargo hold; the second is for the crew to enter the cargo hold to observe the water accumulation on the top of the cargo; the third is to make a judgment based on the alarm of water inflow in the cargo hold; the fourth is to make a judgment based on the heel and roll cycle of the ship. However, none of the above methods can accurately monitor the liquefaction state of the cargo for the following reasons:

[0004] (1) There are two states of cargo fluidization: cargo and water separation, with a free liquid surface formed on the cargo surface, or cargo and water fully mixed, forming a fluidized paste. In the case of cargo and water separation, water seeps out and gathers in the pits above the cargo, and cannot gather in the bilge well at the bottom of the cargo hold; in the case of cargo and water fully mixed, with a fluidized paste, very little water seeps out and only appears on the cargo surface, and no water will accumulate in the bilge well at the bottom of the cargo hold. Therefore, it is impossible to judge the progress or state of cargo fluidization by observing the condition of the bilge well.

[0005] (2) Due to the lack of oxygen and darkness in the cargo hold, the crew can only observe the situation on the top of the cargo with the naked eye from a distance at the cargo hold inspection ladder. It is difficult to observe the progress or degree of liquefaction inside and at the bottom of the cargo. They can only observe obvious changes or water accumulation on the upper part of the cargo. Such obvious conditions that can be observed with the naked eye often indicate that the cargo has already liquefied and seriously endangered the safety of the ship.

[0006] (3) During the cargo liquefaction process, it is difficult for water to enter the bottom of the cargo hold and the cargo hold water ingress alarm cannot be triggered. Moreover, even if the cargo hold water ingress alarm is triggered, it is easy to be considered as a false alarm caused by the moisture in the cargo itself and ignored. Therefore, the progress or status of the cargo liquefaction cannot be detected based on the cargo hold water ingress alarm.

[0007] (4) When the heel and roll cycle of the ship becomes significantly longer, it indicates that serious cargo fluidization has occurred and the ship is in a dangerous state. Therefore, the heel and roll cycle of the ship cannot monitor the cargo fluidization state in advance, but only the phenomenon after the cargo fluidization. Summary of the invention

[0008] The present invention provides a bulk cargo fluidization monitoring method, equipment and storage medium, which are used to solve the problem of state monitoring and early warning of bulk cargo prone to fluidization.

[0009] The present invention adopts the following technical solutions:

[0010] In a first aspect, the present invention provides a method for monitoring the fluidization of bulk cargo, the method comprising: before the cargo ship departs, collecting first point cloud data of the cargo by a visual inspection device and generating a first image; wherein the visual inspection device is installed above or diagonally above the cargo; during the movement of the cargo ship, reading second point cloud data of the cargo collected by the visual inspection device at preset time intervals and generating a second image; identifying and processing the first point cloud data to identify areas prone to water accumulation in the first image; marking possible water accumulation areas in the second image based on the areas prone to water accumulation; performing image comparison between the areas prone to water accumulation and the possible water accumulation areas, and determining the actual water accumulation areas in the possible water accumulation areas based on the comparison results; calculating the amount of water accumulated corresponding to the actual water accumulation area, so as to issue a warning when the amount of water accumulated exceeds a preset water accumulation threshold.

[0011] In a feasible implementation, the visual inspection equipment adopts a camera group, which includes at least two laser radar cameras, and the at least two laser radar cameras are arranged opposite to each other, so as to be able to perform a panoramic scan of the cargo hold of the cargo ship.

[0012] In a feasible implementation, the first point cloud data is identified and processed, including: using a preset filtering method to denoise the first point cloud data to obtain denoised data; performing coordinate transformation on the denoised data according to the angle between the visual inspection device and the cargo ship deck plane, so that the XY plane of the denoised data after the coordinate transformation is parallel to the cargo ship deck plane, and the lowest point is the height 0 point, to obtain transformed data; setting the volume calculation height to a preset initial height, and determining the local point cloud data whose height is lower than the volume calculation height in the transformed data; calculating the volume of the concave area in the local point cloud data; if the volume of the concave area is less than a preset volume threshold, increasing the volume calculation height and recalculating the volume of the concave area; if the volume of the concave area is greater than or equal to the preset volume threshold, identifying the water-prone area in the first image according to the concave area.

[0013] In a feasible implementation, the volume of the sunken area in the local point cloud data is calculated, specifically including: converting the local point cloud data into triangular mesh data; projecting each triangular face in the triangular mesh data to the XY plane where the volume calculation height is located, and calculating the volume of the pentahedron formed by the projection; and calculating the volume of the sunken area based on the volume of the pentahedron.

[0014] In a feasible implementation, marking possible water accumulation areas in the second image according to water accumulation-prone areas includes: adjusting the second image according to image information of the first image so that the image information of the second image is equal to that of the first image; wherein the image information includes at least an image acquisition angle, image acquisition conditions and image size, and the image acquisition conditions include at least a balance condition of the cargo ship during image acquisition; extracting a pixel point set corresponding to the water accumulation-prone area in the first image, and assigning a value to the pixel point set to generate a mask feature corresponding to the water accumulation-prone area in the first image; overlapping the second image and the first image, and controlling the second image to cover the first image; and identifying the area corresponding to the mask feature in the second image according to the image result of the overlapping setting to obtain the possible water accumulation area.

[0015] In a feasible implementation, first point cloud data of the cargo is collected by visual inspection equipment and a first image is generated, including: coordinate transformation of the first point cloud data; obtaining a preset image range and image resolution, and generating a blank image; assigning each data point to a corresponding pixel point in the blank image according to the coordinates of each data point in the first point cloud data after the coordinate transformation; determining the grayscale of the pixel point corresponding to each data point according to the laser reflection intensity data contained in each data point, and generating a first image.

[0016] In a feasible implementation, image comparison is performed between the area prone to water accumulation and the area likely to water accumulation, including: obtaining pixel characteristic values ​​of each pixel in the images of the area prone to water accumulation and the area likely to water accumulation, the pixel characteristic values ​​at least including the pixel grayscale value; calculating the difference between the pixel characteristic value of each pixel in the image of the area prone to water accumulation and the pixel characteristic value of the corresponding pixel in the area likely to water accumulation.

[0017] In a feasible implementation, the amount of water accumulated in an actual water-logged area is calculated, including: determining the actual shape of water accumulated in the actual water-logged area; performing coordinate transformation on the first point cloud data; determining the shape of the sunken area corresponding to the data below the shape recognition height in the first point cloud data at a plurality of shape recognition heights; screening out the shape of the sunken area with the highest similarity to the shape of the actual water-logged area; and calculating the amount of water accumulated according to the shape recognition height corresponding to the sunken area shape with the highest similarity.

[0018] In a second aspect, the present invention also provides a bulk cargo fluidization monitoring device, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor so that the at least one processor can execute a bulk cargo fluidization monitoring method as described in any of the above-mentioned embodiments.

[0019] In a third aspect, the present invention further provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to be able to execute a bulk cargo fluidization monitoring method as described in any of the above embodiments.

[0020] The present invention provides a bulk cargo fluidization monitoring method, device and storage medium, which have the following beneficial effects:

[0021] (1) The present invention collects point cloud data of cargo and generates images through visual inspection equipment. It can determine the pixel features in the image based on the laser reflection intensity data contained in the point cloud data, and then detect the amount of water accumulation on the top of the cargo based on the difference in pixel features of the images generated before the departure of the cargo ship and during the travel, thereby detecting the fluidization of the cargo. The image generated according to the laser reflection intensity data can accurately detect the accumulation of water on the top of the cargo, so the present invention can monitor the early and middle stages of cargo fluidization. At the same time, the present invention first determines the area prone to water accumulation, and then determines the possible water accumulation area based on the area prone to water accumulation, and determines the actual water accumulation area in the possible water accumulation area. By limiting the detection range in the second image for image comparison, the burden on the hardware during image comparison can be reduced, and the comparison accuracy for the area prone to water accumulation can also be improved.

[0022] (2) In the process of identifying the first point cloud data to determine the area prone to water accumulation in the first image, the present invention first performs denoising on the point cloud data, so as to avoid the influence of noise data points on subsequent processing; then the first point cloud data is transformed in coordinates, and the lowest point is determined as the height 0 point. By transforming the coordinates of the first point cloud data, the actual lowest point on the top of the cargo is determined, and the actual lowest point is used as the height 0 point to facilitate the subsequent calculation of the volume of the sunken area; then the volume calculation height is gradually increased and the corresponding sunken area volume is calculated, which can ensure that the range of the identified area prone to water accumulation meets the requirements.

[0023] (3) When the present invention collects point cloud data at different times to generate images, it is necessary to ensure that the image information is equal, so as to ensure that the image Figure 1 The cargo position corresponding to the image at the same position is also the same. By setting the mask feature and overlapping the images to determine the possible water accumulation area in the second image, the possible water accumulation area in the second image can be accurately determined by the water-prone area in the first image. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the prior art descriptions. Obviously, the drawings described below are only some embodiments recorded in the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0025] Figure 1 A method flow chart of a bulk cargo fluidization monitoring method provided by the present invention;

[0026] Figure 2 A schematic diagram of the structure of a bulk cargo fluidization monitoring device provided by the present invention; DETAILED DESCRIPTION

[0027] In order to enable those skilled in the art to better understand the technical solutions in the present invention, the technical solutions in the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of this specification, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0028] The present invention provides a method for monitoring the fluidization of bulk cargoes. A visual detection device is set to generate a first image and a second image, and the actual amount of water accumulation is determined by comparing the first image with the second image, thereby solving the technical problem that the fluidization of early and mid-term futures cannot be monitored.

[0029] The method of the present invention is described in detail below with reference to the accompanying drawings.

[0030] Figure 1 A method flow chart of a bulk cargo fluidization monitoring method provided by the present invention, such as Figure 1 As shown, the method in the present invention at least includes the following execution steps:

[0031] Step 101: Before the cargo ship departs, first point cloud data of the cargo is collected by visual inspection equipment and a first image is generated.

[0032] The point cloud data in the present invention is a data set composed of a large number of points in three-dimensional space generated by the laser radar in the visual detection equipment, and each point contains its coordinate information (X, Y, Z) in three-dimensional space and the reflection intensity data of the laser point.

[0033] Specifically, the first point cloud data is first subjected to coordinate transformation. The coordinate transformation here is the same as the steps performed in the subsequent identification of the first point cloud data and the calculation of the actual amount of water accumulation. The XY coordinate plane in the point cloud data is first rotated to be parallel to the deck plane, so that the true relative height of each point in the point cloud data can be determined, and then the lowest point in the point cloud data is extracted as the height 0 point, that is, as the 0 point of the Z axis. Then a blank image is generated according to the preset image range and pixel resolution. The image range here needs to be determined according to the maximum detection range of the visual inspection device. After the blank image is generated, the pixel points corresponding to each data point are determined, and the characteristic value of the pixel point is determined according to the laser reflection intensity in the data point. The characteristic value here can be set as a gray value, that is, the higher the reflection intensity, the higher the gray value. It can also be set to other values ​​such as color value, so that the first image is generated. The seepage in the cargo hold will absorb most of the laser, resulting in a relatively low laser reflection intensity. Therefore, by determining the gray value of the image through the laser reflection intensity value, the seepage area above the cargo can be clearly reflected in the image.

[0034] Step 102: While the cargo ship is traveling, the second point cloud data of the cargo collected by the visual inspection device is read at preset time intervals and a second image is generated.

[0035] Specifically, the visual inspection equipment collects point cloud data of the goods in the warehouse once at regular intervals, and generates a second image based on the above point cloud data. The specific steps for generating the second image here are: first, the coordinates of the second point cloud data are transformed, and then the image feature values ​​of the pixel points are determined based on the laser reflection intensity of different data points in the second point cloud data. The feature values ​​here need to be the same as the feature values ​​selected for the first image to facilitate image comparison.

[0036] Step 103: performing recognition processing on the first point cloud data.

[0037] Specifically, firstly, the first point cloud data is denoised using a preset filtering method to obtain denoised data, where the filtering method can be any one of Gaussian filtering, mean filtering, and median filtering, and then the denoised data is subjected to coordinate transformation, where the specific steps of coordinate transformation are the same as those for generating the first image. Then, the volume calculation height is set as the preset initial height, and the local point cloud data whose height is lower than the volume calculation height is determined in the transformed data. Under the action of gravity, the water seeping from the cargo always flows to the lowest point in the top area of ​​the cargo first, and as the amount of seepage water increases, the water level gradually rises. The present invention sets the volume calculation height and determines the local point cloud data whose height is lower than the volume calculation height, which is equivalent to determining the area that can carry water accumulation at different water level heights. After determining the local point cloud data, the volume of the concave area in the local point cloud data is calculated. If the volume of the concave area is less than the preset volume threshold, the volume calculation height is increased, and the volume of the concave area is recalculated. If the volume of the concave area is greater than or equal to the preset volume threshold, the water-prone area in the first image is identified according to the concave area. The specific steps for calculating the volume of the sunken area are as follows: first, convert the local point cloud data into triangular mesh data, which can be completed by algorithms such as Poisson reconstruction algorithm, Delaunay triangulation or greedy projection triangulation algorithm. Then project each triangular face in the triangular mesh data to the XY plane where the volume calculation height is located, and calculate the volume of the pentahedron formed by the projection. Finally, the volume of the sunken area is calculated according to the volume of the pentahedron, that is, the volume of the pentahedron formed by all triangular faces is added to obtain the volume of the sunken area. By determining the volume of the sunken area at different volume calculation heights, it is equivalent to determining the amount of cargo water seepage at different horizontal plane heights, and then determining the water accumulation area corresponding to the early and middle stage cargo water seepage, and setting it as the subsequent key detection area, that is, the area prone to water accumulation.

[0038] Step 104: Mark the possible water accumulation area in the second image according to the water accumulation-prone area.

[0039] Specifically, first, the second image is adjusted according to the image information of the first image so that the image information of the second image is equal to the image information of the first image. Among them, the image information includes at least the image acquisition angle, the image acquisition condition and the image size, and the image acquisition condition includes at least the balance condition of the cargo ship when the image is acquired. Because the water on the top of the cargo hold can flow freely, if the cargo ship is in a tilted state when the second image is generated, the water on the top of the cargo hold will flow to other positions, and the amount of water remaining in the possible water accumulation area may be much smaller than the actual amount of water accumulation. If the water accumulation situation is judged according to the second image generated in this case, there will be serious errors, so it is necessary to ensure that the cargo ship is in a balanced condition. Then, the pixel point set corresponding to the easy water accumulation area is extracted from the first image, and the pixel point set is assigned to generate the mask feature corresponding to the easy water accumulation area in the first image. Then, the second image and the first image are overlapped, and the second image is controlled to cover the first image. Finally, according to the image result of the overlapping setting, the corresponding area of ​​the mask feature is identified in the second image to obtain the possible water accumulation area. By setting mask features and overlapping coverage, the position of the possible water accumulation area in the second image corresponding to the water accumulation-prone area in the first image can be accurately determined.

[0040] Step 105: perform image comparison between the area prone to water accumulation and the area likely to water accumulation, and determine the actual water accumulation area in the area likely to water accumulation based on the comparison result.

[0041] Specifically, first, the pixel characteristic value of each pixel in the image of the area prone to water accumulation and the area likely to water accumulation, such as the grayscale value of the pixel, is obtained. Then, the difference between the pixel characteristic value of each pixel in the image of the area prone to water accumulation and the pixel characteristic value of the corresponding pixel in the area likely to water accumulation is calculated. Before the departure of the cargo ship, there is almost no water seepage on the top of the cargo, so the pixel characteristic value of the area prone to water accumulation in the first image will show a characteristic, such as a high grayscale value. As the cargo ship travels, water seepage gradually accumulates on the top of the cargo, and in the area likely to water accumulate in the second image, the pixel characteristic value of the part with water seepage will show another characteristic, such as a low grayscale value or even 0. By calculating the difference between the characteristic values ​​of the pixels corresponding to the first image and the second image, the area on the top of the cargo where water seepage exists, that is, the actual water accumulation area, can be quickly and accurately determined.

[0042] Step 106: Calculate the amount of water accumulated in the actual waterlogged area so as to issue a warning when the amount of water accumulated exceeds a preset waterlogging threshold.

[0043] Specifically, first, determine the actual water shape of the actual water accumulation area, that is, separate the actual water accumulation area from the second image to determine the actual water accumulation shape. Then, perform coordinate transformation on the first point cloud data to determine the shape of the sunken area corresponding to the data below the shape recognition height in the first point cloud data at multiple shape recognition heights. Because the cargo ship is in a balanced state when the second image is generated by the present invention, the horizontal plane in the cargo hold is parallel to the deck plane of the cargo ship, and after the coordinate transformation, the XY plane of the first point cloud data is also parallel to the deck plane, so that the XY plane of the first point cloud data can be guaranteed to be parallel to the horizontal plane, that is, at different shape recognition heights, the shape of the sunken area corresponding to the data below the shape recognition height in the first point cloud data is the same as the shape of the water accumulation area at the same water accumulation height, so that the actual water accumulation height can be determined by comparing the shape of the sunken area at different shape recognition heights with the shape of the actual water accumulation area. After determining the shapes of the sunken areas corresponding to the various shape recognition heights, the sunken area shape with the highest similarity to the actual water accumulation shape is selected, and then the volume of the sunken area at the corresponding shape recognition height is calculated according to the corresponding shape recognition height. The volume of the sunken area here is the actual amount of water accumulation. After calculating the actual amount of water accumulation, it is determined whether the amount of water accumulation reaches the preset water accumulation threshold. If so, a warning is issued.

[0044] Based on the same inventive concept, the present invention also provides a bulk cargo fluidization monitoring device, the structure of which is shown in the figure.

[0045] Figure 2 The present invention provides a schematic diagram of the structure of a device for monitoring the fluidization of bulk cargo. Figure 2 As shown, the bulk cargo fluidization monitoring device 200 in the present invention specifically includes: at least one processor 201; and a memory 203 that is communicatively connected to the at least one processor (connected via a bus 202); wherein the memory 203 stores instructions that can be executed by the at least one processor 201, so that the at least one processor 201 can execute a bulk cargo fluidization monitoring method as described in the above embodiment.

[0046] In one or more possible implementations of the present invention, the aforementioned processor is used to execute, before the cargo ship departs, collecting first point cloud data of the cargo through a visual inspection device and generating a first image; during the movement of the cargo ship, reading second point cloud data of the cargo collected by the visual inspection device at preset time intervals and generating a second image; identifying and processing the first point cloud data; marking possible water accumulation areas in the second image based on water-prone areas; performing image comparison between water-prone areas and possible water accumulation areas, and determining actual water accumulation areas in possible water accumulation areas based on the comparison results; and calculating the amount of water accumulated corresponding to the actual water accumulation area, so as to issue a warning when the amount of water accumulated exceeds a preset water accumulation threshold.

[0047] In addition, the present invention also provides a non-volatile computer storage medium storing computer executable instructions, wherein the computer executable instructions are configured to be able to execute a bulk cargo fluidization monitoring method as described in any one of the above embodiments.

[0048] In one or more possible implementations of the present invention, the aforementioned computer executable instructions are configured to execute: before the cargo ship departs, first point cloud data of the cargo is collected by a visual inspection device and a first image is generated; during the movement of the cargo ship, second point cloud data of the cargo collected by the visual inspection device is read at intervals of a preset time and a second image is generated; the first point cloud data is identified and processed; possible water accumulation areas are marked in the second image based on areas prone to water accumulation; images of areas prone to water accumulation and possible water accumulation areas are compared, and the actual water accumulation areas are determined in the possible water accumulation areas based on the comparison results; and the amount of water accumulated corresponding to the actual water accumulation area is calculated, so as to issue a warning when the amount of water accumulated exceeds a preset water accumulation threshold.

[0049] Each embodiment of the present invention is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the IoT device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0050] The system and medium provided by the present invention correspond one-to-one to the method, and therefore, the system and medium also have similar beneficial technical effects to the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the system and medium will not be repeated here.

[0051] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0052] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0053] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0054] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0055] The above are only embodiments of the present invention and are not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for monitoring the fluidization of bulk cargo, characterized in that: The method comprises: Before the cargo ship departs, the first point cloud data of the cargo is collected by a visual inspection device and a first image is generated; wherein the visual inspection device is installed above or obliquely above the cargo; During the movement of the cargo ship, the second point cloud data of the cargo collected by the visual inspection device is read at preset time intervals and a second image is generated; Performing recognition processing on the first point cloud data to identify areas prone to water accumulation in the first image; Marking a possible water accumulation area in the second image according to the water accumulation-prone area; Performing image comparison between the prone water accumulation area and the possible water accumulation area, and determining the actual water accumulation area in the possible water accumulation area according to the comparison result; The amount of water accumulated in the actual waterlogged area is calculated, so as to issue a warning when the amount of water accumulated exceeds a preset waterlogging threshold.

2. A bulk cargo fluidization monitoring method according to claim 1, characterized in that: The visual inspection equipment adopts a camera group, which includes at least two laser radar cameras, and the at least two laser radar cameras are arranged relative to each other and can perform a panoramic scan of the cargo hold of the cargo ship.

3. A bulk cargo fluidization monitoring method according to claim 1, characterized in that: Performing recognition processing on the first point cloud data includes: Using a preset filtering method to perform denoising on the first point cloud data to obtain denoised data; According to the angle between the visual inspection device and the deck plane of the cargo ship, coordinate transformation is performed on the denoised data, so that the XY plane of the denoised data after the coordinate transformation is parallel to the deck plane of the cargo ship, and the lowest point is the height 0 point, to obtain transformed data; Setting the volume calculation height as a preset initial height, and determining the local point cloud data whose height is lower than the volume calculation height in the transformed data; Calculating the volume of the concave area in the local point cloud data; If the volume of the sunken area is less than a preset volume threshold, increasing the volume calculation height and recalculating the volume of the sunken area; If the volume of the sunken area is greater than or equal to the preset volume threshold, a water-prone area in the first image is identified based on the sunken area.

4. A bulk cargo fluidization monitoring method according to claim 3, characterized in that: Calculating the volume of the concave area in the local point cloud data specifically includes: Converting the local point cloud data into triangular mesh data; Projecting each triangular face in the triangular mesh data onto the XY plane where the volume calculation height is located, and calculating the volume of the pentahedron formed by the projection; The volume of the recessed area is calculated according to the volume of the pentahedron.

5. A bulk cargo fluidization monitoring method according to claim 1, characterized in that: Marking a possible water accumulation area in the second image according to the water accumulation-prone area includes: The second image is adjusted according to the image information of the first image so that the image information of the second image is equal to the image information of the first image; wherein the image information at least includes an image acquisition angle, an image acquisition condition and an image size, and the image acquisition condition at least includes a balance condition of the cargo ship during image acquisition; Extracting a pixel point set corresponding to the area prone to water accumulation in the first image, and performing value assignment processing on the pixel point set to generate a mask feature corresponding to the area prone to water accumulation in the first image; The second image is overlapped with the first image, and the second image is controlled to cover the first image; According to the image result of the overlapping setting, the corresponding area of ​​the mask feature is identified in the second image to obtain the possible water accumulation area.

6. A bulk cargo fluidization monitoring method according to claim 1, characterized in that: Collecting first point cloud data of the goods through a visual inspection device and generating a first image includes: Performing coordinate transformation on the first point cloud data; Get the preset image range and image resolution, and generate a blank image; According to the coordinates of each data point in the first point cloud data after coordinate conversion, each data point is assigned to a corresponding pixel point in the blank image; According to the laser reflection intensity data contained in each data point, the grayscale of the pixel point corresponding to each data point is determined, and the first image is generated.

7. A bulk cargo fluidization monitoring method according to claim 1, characterized in that: Performing image comparison between the area prone to water accumulation and the area likely to water accumulation includes: Obtaining pixel characteristic values ​​of each pixel in the image of the area prone to water accumulation and the image of the area likely to water accumulation, wherein the pixel characteristic values ​​at least include pixel grayscale values; The difference between the pixel characteristic value of each pixel in the water accumulation prone area image and the pixel characteristic value of the corresponding pixel in the possible water accumulation area is calculated.

8. A bulk cargo fluidization monitoring method according to claim 1, characterized in that: Calculating the amount of water accumulation corresponding to the actual waterlogged area includes: Determining the actual water accumulation shape of the actual water accumulation area; Performing coordinate transformation on the first point cloud data; Determine, at multiple shape recognition heights, the shape of the concave area corresponding to the data in the first point cloud data that is lower than the shape recognition height; Screening out the shape of the concave area that is most similar to the actual water accumulation shape; The amount of accumulated water is calculated according to the shape recognition height corresponding to the sunken area shape with the highest similarity.

9. A bulk cargo fluidization monitoring device, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions that can be executed by the at least one processor, so that the at least one processor can execute the method for monitoring fluidization of bulk cargo according to any one of claims 1-8.

10. A non-volatile computer storage medium having computer executable instructions stored thereon, characterized in that: The computer executable instructions are configured to execute a bulk cargo fluidization monitoring method according to any one of claims 1-8.

Images