Cabin offset detection method, equipment and program product

Abstract

The invention discloses a cabin offset detection method and device and a program product, and the method comprises the steps: obtaining a cabin image of a cabin, and carrying out the processing of the cabin image, and obtaining an edge contour image of the cabin; determining a feature point set of the edge contour image, and decomposing the edge contour image into a plurality of feature segments based on the feature point set; determining the offset of each feature segment based on the geometric feature parameter of each feature segment and the cabin reference image; based on the morphological features of each feature segment, matching an elastic deformation mode corresponding to each feature segment in a preset deformation rule library, and determining an elastic deformation quantity corresponding to each feature segment; and determining the real offset of each characteristic section based on the offset and the corresponding elastic deformation quantity, and determining the overall rigid offset of the cabin based on the real offset. Through the technical scheme provided by the invention, the accuracy of cabin offset detection can be improved.

Description

Technical Field

[0001] The present application belongs to the technical field of cabin deviation detection, and in particular, relates to a cabin deviation detection method, device and program product. Background Art

[0002] With the development of the economy, ships have become an important way to transport goods. During the process of ship sailing or unloading, the cabin may shift due to wind and waves or changes in the loading status of the ship. The cabin shift phenomenon may cause damage to the hull structure and may also affect the loading or unloading of cargo. It is necessary to monitor the status of the cabin in real time to prevent the cabin shift phenomenon. In the prior art, the stability and accuracy of cabin shift detection are insufficient. Therefore, how to improve the accuracy of cabin shift detection is a technical problem that needs to be solved urgently. Summary of the invention

[0003] The embodiments of the present application provide a method, device and program product for detecting cabin deviation, thereby improving the accuracy of cabin deviation detection at least to a certain extent.

[0004] Other features and advantages of the present application will become apparent from the following detailed description, or may be learned in part by the practice of the present application.

[0005] According to a first aspect of an embodiment of the present application, a method for detecting cabin displacement is provided, characterized in that the method comprises: acquiring a cabin image of the cabin, processing the cabin image, and obtaining an edge contour image of the cabin; determining a feature point set of the edge contour image, and based on the feature point set, decomposing the edge contour image into a plurality of feature segments; determining an offset of each feature segment based on geometric feature parameters of each feature segment and a cabin reference image, wherein the cabin reference image is an image of the cabin when no displacement occurs; matching an elastic deformation mode corresponding to each feature segment in a preset deformation law library based on morphological features of each feature segment, and determining an elastic deformation amount corresponding to each feature segment, wherein the morphological features at least include shape features, structural force features, and position features of the feature segment in the edge contour image; determining a true offset of each feature segment based on the offset and the corresponding elastic deformation amount of each feature segment, and determining the overall rigid displacement of the cabin based on the true offset.

[0006] In some embodiments of the present application, based on the foregoing solution, the processing of the cabin image to obtain the edge contour image of the cabin includes: performing grayscale processing on the cabin image to obtain a grayscale cabin image; performing noise reduction processing and enhancement processing on the grayscale cabin image to obtain an edge-enhanced image of the cabin; and processing the edge-enhanced image through an edge detection algorithm and a contour detection algorithm to obtain the edge contour image of the cabin.

[0007] In some embodiments of the present application, based on the foregoing solution, the determination of the set of feature points of the edge contour image includes: calculating the curvature values of the cabin edge contours in different regions of the edge contour image, and taking the extreme points in each curvature value as the first candidate set of feature points; determining the significant corner points in the edge contour image through a corner detection algorithm, and taking each significant corner point as the second candidate set of feature points, where the significant corner points are corner points with a corner response value greater than a preset response value; integrating the first candidate set of feature points and the second candidate set of feature points to obtain a total candidate set of feature points; determining the Euclidean distance between any two candidate feature points in the total candidate set of feature points, and if the Euclidean distance between any two candidate feature points is less than a preset distance, then calculating the ratio between the respective curvature values and corner response values of the two candidate feature points as a trade-off coefficient, and retaining the point with a larger trade-off coefficient between the two candidate feature points until the Euclidean distance between any two candidate feature points is greater than the preset distance; and taking all the remaining candidate feature points as the set of feature points of the edge contour image.

[0008] In some embodiments of the present application, based on the foregoing solution, determining the offset of each feature segment based on the geometric feature parameters of each feature segment and the cabin reference image includes: determining the offset feature between each feature segment and the corresponding position in the cabin reference image based on the geometric feature parameters of each feature segment and the cabin reference image, where the offset feature may at least include the offset direction and offset amplitude of the corresponding feature segment; dividing each feature segment into multiple offset sub-regions based on the offset feature of each feature segment and the spatial position of each feature segment, where the offset sub-region includes multiple feature segments with adjacent spatial positions and similar offset features; determining the main offset direction of each offset sub-region, and calculating the included angle between the main offset directions of any two adjacent offset sub-regions. If the included angle is less than a preset included angle threshold, then fusing the any two adjacent offset sub-regions into a new offset sub-region until the included angle between the main offset directions of any two adjacent offset sub-regions is greater than the preset included angle threshold, to obtain multiple fused offset regions; determining the regional offset parameters of each fused offset region, and establishing an offset field distribution model based on the regional offset parameters, where the regional offset parameters at least include the regional range boundary coordinates, the main offset direction of the region, the average offset vector within the region, and the offset feature of the feature segments within the region, and the offset field distribution model is used to reflect the offset distribution law and deformation characteristics of each region of the cabin; calculating the offset of each feature segment according to the offset field distribution model.

[0009] In some embodiments of the present application, based on the foregoing solution, matching the corresponding elastic deformation mode of each feature segment in a preset deformation law library based on the morphological features of each feature segment and determining the corresponding elastic deformation amount of each feature segment includes: matching the corresponding elastic deformation mode of each feature segment in a preset deformation law library based on the morphological features of each feature segment, and determining the corresponding reference elastic deformation amount formula and reference geometric parameters of each feature segment;

[0010] Determine the elastic deformation amount of the straight segment in the feature segment through the following formula:

[0011]

[0012] where, δ elastic is the elastic deformation amount, M is the dynamic load moment, L is the length of the feature segment, E is the elastic modulus, I is the moment of inertia of the cross-section, and f(θ) is a shape coefficient function related to the deformation angle of the feature segment;

[0013] Determine the elastic deformation amount of other feature segments except the straight segment through the following formula:

[0014]

[0015] Wherein, M is the dynamic load moment, L is the length of the characteristic section, E is the elastic modulus, I is the moment of inertia of the cross-section, V is the shear force, G is the shear modulus, and A is the cross-sectional area.

[0016] In some embodiments of the present application, based on the foregoing solution, the true offset is determined by the following formula:

[0017] δ real = δ measured - ω1·δ elastic - ω2[(k1Lsinθ + k2L 2 cosθ) + h(L, θ, M, k)]

[0018] Wherein, δ real is the true offset, δ measured is the offset, δ elastic is the elastic deformation amount, ω1 is the elastic correction weight factor, ω2 is the geometric correction weight factor, k, k1 and k2 are geometric correction coefficients, L is the length of the characteristic section, θ is the deformation angle of the characteristic section, and M is the dynamic load moment of the characteristic section.

[0019] In some embodiments of the present application, based on the foregoing solution, determining the overall rigid offset of the cabin based on the true offset includes: judging whether each true offset is within a preset offset range, and removing the true offsets outside the preset offset range, and taking the remaining true offsets as effective offsets; determining the correlation data between the effective real offsets, and based on the correlation data, determining the weight coefficients corresponding to the effective offsets, wherein the correlation data is used to describe the dependence relationship and linkage mechanism between the effective offsets, and the weight coefficients are used to describe the magnitude of the influence of the effective offsets on the overall rigid offset of the cabin; determining the horizontal effective offset of each effective offset in the horizontal direction and the vertical effective offset in the vertical direction;

[0020] The overall rigid offset of the cabin is determined by the following formula:

[0021]

[0022] Wherein, ΔX total is the horizontal component of the overall rigid offset of the cabin, ΔY total is the vertical component of the overall rigid offset of the cabin, ΔX i is the horizontal effective offset, ΔY i is the vertical effective offset, ω i is the weight coefficient of the characteristic section, δ total is the overall rigid offset of the cabin, D total is the overall offset direction of the cabin.

[0023] In some embodiments of the present application, based on the foregoing solution, the method further includes: when the overall rigid offset of the cabin is greater than a preset rigid offset, sending out a warning signal and a compensation control instruction to adjust the overall rigid offset of the cabin.

[0024] According to a second aspect of the embodiments of the present application, a cabin offset detection device is provided, characterized in that the device includes: an image acquisition unit, configured to acquire a cabin image of the cabin, process the cabin image to obtain an edge contour image of the cabin; a decomposition unit, configured to determine a set of feature points of the edge contour image, and based on the set of feature points, decompose the edge contour image into a plurality of feature segments; a first determination unit, configured to determine the offset of each feature segment based on the geometric feature parameters of each feature segment and a cabin reference image, where the cabin reference image is an image of the cabin when no offset occurs; a second determination unit, configured to match the elastic deformation mode corresponding to each feature segment in a preset deformation rule library based on the morphological features of each feature segment, and determine the elastic deformation amount corresponding to each feature segment, where the morphological features at least include shape features, structural stress features, and position features of the feature segment in the edge contour image; a third determination unit, configured to determine the true offset of each feature segment based on the offset and the corresponding elastic deformation amount of each feature segment, and determine the overall rigid offset of the cabin based on the true offset.

[0025] According to a third aspect of the embodiments of the present application, a computer-readable storage medium is provided, in which at least one computer program instruction is stored, and the at least one computer program instruction is loaded and executed by a processor to implement the operations performed by the method according to any one of the foregoing first aspects.

[0026] According to a fourth aspect of the embodiments of the present application, a computer program product is provided, the computer program product includes computer instructions, the computer instructions are stored in a computer-readable storage medium, and are adapted to be read and executed by a processor, so that a computer device having the processor executes to implement the operations performed by the method according to any one of the foregoing first aspect embodiments.

[0027] Based on the technical solution proposed in the present application, by extracting the edge contour image of the cabin, determining the set of feature points in the edge contour image, and decomposing the edge contour image into multiple feature segments through the feature point set, the cabin structure can be refined and the local features therein can be highlighted, so that the slight deformation in the cabin can be captured, thereby improving the accuracy of cabin offset detection, and determining the elastic deformation mode of each feature segment in combination with a preset deformation law library, and determining the real offset of each feature segment according to the elastic deformation mode and the offset corresponding to each feature segment, thereby determining the overall rigid offset of the cabin. In this way, the elastic deformation and rigid offset can be effectively separated, and the reasonable elastic deformation of the cabin under different loading conditions can be avoided from affecting the cabin offset detection, thereby further improving the accuracy of cabin offset detection; the offset corresponding to each feature segment can be determined by comprehensively determining the geometric feature parameters, thereby enhancing the reliability of the result, and taking the image when the cabin offset occurs as a reference, it can be more intuitive and specific to determine whether the cabin is offset, thereby improving the accuracy of cabin offset detection.

[0028] It should be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The drawings herein are incorporated into the specification and constitute a part of the specification, showing embodiments consistent with the present application, and together with the specification, are used to explain the principles of the present application. Obviously, the drawings described below are only some embodiments of the present application, and for ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work. In the drawings:

[0030] Figure 1 A flow chart showing a method for detecting cabin deviation in one embodiment of the present application is shown;

[0031] Figure 2 A block diagram of a cabin deviation detection device in one embodiment of the present application is shown;

[0032] Figure 3 A schematic structural diagram of a cabin deviation detection device in one embodiment of the present application is shown. DETAILED DESCRIPTION

[0033] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0034] In addition, the described features, structures, or characteristics may be combined in one or more embodiments in any suitable manner. In the following description, numerous specific details are provided to give a thorough understanding of the embodiments of the present application. However, those skilled in the art will realize that the technical solutions of the present application may be practiced without one or more of the specific details, or other methods, components, devices, steps, etc. may be employed. In other cases, well-known methods, devices, implementations, or operations are not shown or described in detail to avoid obscuring aspects of the present application.

[0035] The block diagrams shown in the drawings are only functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities may be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor devices and / or microcontroller devices.

[0036] The flowcharts shown in the drawings are only illustrative and do not necessarily include all the contents and operations / steps, nor do they have to be executed in the order described. For example, some operations / steps may be decomposed, while some operations / steps may be combined or partially combined, so the actual execution order may change according to the actual situation.

[0037] It should be noted that the term "a plurality of" mentioned herein refers to two or more. "And / or" describes the association relationship of associated objects and indicates that three relationships may exist. For example, A and / or B may represent: A exists alone, A and B exist simultaneously, and B exists alone. The character " / " generally represents an "or" relationship between the associated objects before and after.

[0038] It should also be noted that the terms "first", "second", etc. in the description, claims, and above-mentioned drawings of the present application are used to distinguish similar objects and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the objects so used may be interchanged under appropriate circumstances so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described.

[0039] To enable those skilled in the art to better understand the present application, the cabin offset proposed by the present application will be briefly described first.

[0040] With the development of economy, ships have become an important way to transport goods. During the process of ship sailing or unloading, the cabin may shift due to wind and waves or changes in the loading status of the ship. The cabin shift phenomenon may cause damage to the hull structure and may also affect the loading or unloading of goods. It is necessary to monitor the state of the cabin in real time to prevent the cabin shift phenomenon. In the prior art, the stability and accuracy of cabin shift detection are insufficient. Therefore, how to improve the accuracy of cabin shift detection is a technical problem to be solved urgently. In this regard, the inventor of this application proposes a cabin shift detection method to improve the accuracy of cabin shift detection.

[0041] Next, the present application will elaborate on the proposed cabin deviation detection method in detail.

[0042] See also Figure 1 , which shows a flow chart of a method for detecting cabin deviation in one embodiment of the present application, and the method for detecting cabin deviation can be executed by a device having a computing and processing function, referring to Figure 1 As shown, the cabin deviation detection method at least includes steps 110 to 150, which are described in detail as follows:

[0043] Step 110: Acquire a cabin image of the cabin, and process the cabin image to obtain an edge contour image of the cabin.

[0044] Step 120: determine a feature point set of the edge contour image, and decompose the edge contour image into a plurality of feature segments based on the feature point set.

[0045] Step 130, determining the offset of each feature segment based on the geometric feature parameters of each feature segment and a cabin reference image, wherein the cabin reference image is an image of the cabin when no offset occurs.

[0046] Step 140, based on the morphological features of each feature segment, match the elastic deformation mode corresponding to each feature segment in a preset deformation law library, and determine the elastic deformation amount corresponding to each feature segment, wherein the morphological features at least include shape features, structural force features, and position features of the feature segments in the edge contour image.

[0047] Step 150, based on the offset of each characteristic segment and the corresponding elastic deformation, determine the actual offset of each characteristic segment, and based on the actual offset, determine the overall rigid offset of the cabin.

[0048] In this application, the acquisition of the cabin image of the cabin can specifically be obtained through an image acquisition device, or the cabin images in different loading states can be continuously acquired according to the change of the loading state of the cabin, and subsequent processing procedures can be carried out. In this way, real-time monitoring of the cabin state can be achieved to avoid serious cabin offset phenomena.

[0049] In this application, by extracting the edge contour image of the cabin, determining the set of feature points in the edge contour image, and decomposing the edge contour image into multiple feature segments through the set of feature points, the cabin structure can be refined, and the local features therein can be highlighted, so as to be able to capture the minute deformations in the cabin, and further improve the accuracy of cabin offset detection. Combining with a preset deformation rule library to determine the elastic deformation modes of each feature segment, and according to the elastic deformation modes and the offset amounts corresponding to each feature segment, determining the true offsets of each feature segment, and further being able to determine the overall rigid offset of the cabin. In this way, elastic deformation and rigid offset can be effectively separated, and the reasonable elastic deformation of the cabin under different loading states can be avoided from affecting the cabin offset detection, further improving the accuracy of cabin offset detection.

[0050] In this application, by comprehensively determining the offset amounts corresponding to each feature segment according to geometric feature parameters, the reliability of the results can be enhanced. Using the image when the cabin offset occurs as a reference, it can be more intuitive and specific to determine whether the cabin has offset. Thus, the accuracy of cabin offset detection can be improved.

[0051] In the above step 110, the processing of the cabin image to obtain the edge contour image of the cabin can specifically be performed according to the following steps 111 to 113:

[0052] Step 111, perform grayscale processing on the cabin image to obtain a grayscale cabin image.

[0053] Step 112, perform noise reduction processing and enhancement processing on the grayscale cabin image to obtain the edge enhanced image of the cabin.

[0054] Step 113, process the edge enhanced image through an edge detection algorithm and a contour detection algorithm to obtain the edge contour image of the cabin.

[0055] In this application, for the noise reduction processing, specifically, Gaussian filtering can be used to perform noise reduction on the grayscale cabin image; for the enhancement processing, specifically, the contrast of the image can be enhanced through histogram equalization, and then the edge features of the image can be enhanced through a sharpening filter. According to actual needs, other image noise reduction tools and image enhancement tools can also be selected. For this, this application does not make specific limitations.

[0056] In this application, by performing relevant processing on the cabin image, an edge contour image can be obtained, which can refine the cabin structure and highlight local features therein, so that the deformation and offset occurring in the cabin can be captured more accurately, and further the accuracy of cabin offset detection can be improved.

[0057] In step 120 above, to determine the set of feature points of the edge contour image, specifically, it can be executed according to the following steps 121 to 125:

[0058] Step 121, calculate the curvature values of the cabin edge contours in different regions of the edge contour image, and use the extreme value points among the respective curvature values as the first candidate feature point set.

[0059] Step 122, determine the significant corner points in the edge contour image through a corner point detection algorithm, and use each significant corner point as the second candidate feature point set, where the significant corner points are the corner points whose corner point response values are greater than a preset response value.

[0060] Step 123, integrate the first candidate feature point set and the second candidate feature point set to obtain a total candidate feature point set.

[0061] Step 124, determine the Euclidean distance between any two candidate feature points in the total candidate feature point set. If the Euclidean distance between any two candidate feature points is less than a preset distance, then calculate the ratio between the respective curvature values and corner point response values of the two candidate feature points as a trade-off coefficient, and retain the point with a larger trade-off coefficient between the two candidate feature points until the Euclidean distance between any two candidate feature points is greater than the preset distance.

[0062] Step 125, use all the remaining candidate feature points as the set of feature points of the edge contour image.

[0063] In this application, the preset distance can specifically be 10, or 12, or 14. According to actual needs, the preset distance can also be other values. In this regard, this application does not make specific limitations.

[0064] In this application, the first candidate feature points are determined through curvature extreme value points (used to reflect the bending change of the contour), and the second candidate feature points are determined through corner point response values (used to capture sharp structural features), which can expand the coverage range of candidate feature points, including both smooth curve mutation points and rigid corner points at the same time, and avoid missing some feature points due to only using a single feature to determine the feature point set, which can effectively improve the accuracy of feature point selection, and thus improve the accuracy of cabin offset detection.

[0065] In this application, by setting a preset distance and a trade-off coefficient, duplicate candidate feature points in the dense area of candidate feature points can be eliminated. Among them, setting the preset distance can improve the rationality of the spatial distribution of feature points, avoid the situation that the distribution of feature points is locally over-dense and interfere with subsequent segmentation of feature segments, while setting the weight coefficient can further refine the screening criteria and improve the matching degree between the feature points and the key points of the real structure, so as to improve the accuracy of feature point selection and further improve the accuracy of cabin offset detection.

[0066] In step 130 above, based on the geometric feature parameters of each feature segment and the cabin reference image, the offset of each feature segment is determined. Specifically, it can be executed according to the following steps 131 to 135:

[0067] Step 131, based on the geometric feature parameters of each feature segment and the cabin reference image, determine the offset features between each feature segment and the corresponding position in the cabin reference image. The offset features can at least include the offset direction and offset amplitude of the corresponding feature segment.

[0068] Step 132, based on the offset features of each feature segment and the spatial positions of each feature segment, divide each feature segment into multiple offset sub-regions, where the offset sub-regions include multiple feature segments with adjacent spatial positions and similar offset features.

[0069] Step 133, determine the main offset direction of each offset sub-region, and calculate the angle between the main offset directions of any two adjacent offset sub-regions. If the angle is less than the preset angle threshold, fuse the any two adjacent offset sub-regions into a new offset sub-region until the angle between the main offset directions of any two adjacent offset sub-regions is greater than the preset angle threshold, and obtain multiple fused offset regions.

[0070] Step 134, determine the regional offset parameters of each fused offset region, and establish an offset field distribution model based on the regional offset parameters. The regional offset parameters at least include the boundary coordinates of the regional range, the main offset direction of the region, the average offset vector within the region, and the offset features of the feature segments within the region. The offset field distribution model is used to reflect the offset distribution law and deformation characteristics of each region of the cabin.

[0071] Step 135, calculate the offset of each feature segment according to the offset field distribution model.

[0072] In this application, the preset angle threshold can specifically be 25°, or 30°, or 35°. According to actual needs, the preset angle threshold can also be other angles. In this regard, this application does not make specific limitations.

[0073] In this application, first, based on the offset features between each feature segment and the corresponding positions in the cabin reference image, and the spatial positions of each feature segment, the feature segments are divided into multiple offset sub-regions. Then, the multiple offset sub-regions are fused to achieve a progressive process from local to regional and then to the whole, which can more accurately determine the overall deformation law of the cabin, thereby improving the accuracy of the offset detection of the cabin.

[0074] In this application, by setting a preset angle threshold, adjacent offset sub-regions with an angle between the main offset directions less than the preset angle threshold are fused. That is, based on the similarity of the main offset directions of adjacent offset sub-regions, the offset sub-regions are dynamically merged, which can eliminate the fragmented results caused by segmentation, ensure that the internal offset directions of each fused offset region are consistent, to ensure the accuracy of the subsequent processing process, and improve the accuracy of the cabin offset detection. In addition, by fusing adjacent offset sub-regions with similar offset directions and combining spatial proximity and offset similarity, the error caused by simply dividing the deviation region by geometric features can be avoided, further improving the accuracy of the cabin offset detection.

[0075] In this application, each feature segment is divided into multiple offset sub-regions according to its corresponding offset features, and gradually fused to obtain an offset field distribution model, which can make the offset field distribution model form a mapping relationship with the structural partition in the cabin, so as to facilitate determining the offset amounts of the feature segments in each region, thereby providing a basis for subsequent processing to improve the accuracy of the cabin offset detection.

[0076] In step 140 above, based on the morphological features of each feature segment, the corresponding elastic deformation modes of each feature segment are matched in a preset deformation law library, and the corresponding elastic deformation amounts of each feature segment are determined. Specifically, it can be carried out according to the following steps:

[0077] Step 141, based on the morphological features of each feature segment, the corresponding elastic deformation modes of each feature segment are matched in a preset deformation law library, and the corresponding reference elastic deformation amount formula and reference geometric parameters of each feature segment are determined.

[0078] Step 142, the elastic deformation amount of the straight line segment in the feature segment is determined by the following formula (1):

[0079]

[0080] where, δ elastic is the elastic deformation amount, M is the dynamic load moment, L is the length of the feature segment, E is the elastic modulus, I is the moment of inertia of the cross-section, and f(θ) is a shape coefficient function related to the deformation angle of the feature segment.

[0081] Step 143, determine the elastic deformation amount of other feature segments except the straight line segment through the following formula (2):

[0082]

[0083] where M is the dynamic load moment, L is the length of the feature segment, E is the elastic modulus, I is the moment of inertia of the cross-section, V is the shear force, G is the shear modulus, and A is the cross-sectional area.

[0084] In the present application, by presetting a deformation law library, determining the elastic deformation modes of each feature segment under different loading states, and determining the reference elastic deformation amount formula and reference geometric parameters corresponding to each feature segment based on the preset deformation law library, the accuracy of data acquisition can be improved, providing accurate data support for the subsequent calculation of the elastic deformation amount, thereby improving the accuracy of detecting the offset of the cabin.

[0085] In the present application, for different types of feature segments, appropriate mechanical formulas are respectively used to calculate the elastic deformation amounts corresponding to different types of feature segments. For example, for a straight line segment, the influence of the bending moment is mainly considered, while for other feature segments except the straight line segment (i.e., the curve segment), the shear force direction is introduced, and the composite deformation of bending and shear is comprehensively considered. In this way, the systematic error caused by using a single formula can be avoided, the applicable range of the formula can be expanded, and the accuracy of the calculation result can be improved, thereby further improving the accuracy of detecting the offset of the cabin.

[0086] In the above step 150, specifically, the true offset can be determined through the following formula (3):

[0087] δ real =δ measured -ω1·δ elastic -ω2[(k1Lsinθ + k2L 2 cosθ)+h(L,θ,M,k)] (3)

[0089] where δ real is the true offset, δ measured is the offset, δ elastic is the elastic deformation amount, ω1 is the elastic correction weight factor, ω2 is the geometric correction weight factor, k, k1 and k2 are geometric correction coefficients, L is the length of the feature segment, θ is the deformation angle of the feature segment, and M is the dynamic load moment of the feature segment.

[0090] In this application, by comprehensively considering the elastic deformation amount and the offset amount, the true offset amount corresponding to each feature segment is determined, which can eliminate the influence of the reasonable elastic deformation of the cabin under different loading states on the cabin offset detection, and only retain the true offset amount caused by the cabin offset. Therefore, by removing the interference factors and determining the true offset amount, the accuracy of the cabin offset detection can be effectively improved.

[0091] In the above step 150, based on the true offset amount, determining the overall rigid offset of the cabin can be specifically performed according to the following steps 151 to 154:

[0092] Step 151, determine whether each true offset amount is within the preset offset range, and remove the true offset amounts outside the preset offset range, and use the remaining true offset amounts as the effective offset amounts.

[0093] Step 152, determine the correlation data between each effective true offset amount, and based on the correlation data, determine the weight coefficients corresponding to each effective offset amount, where the correlation data is used to describe the dependence relationship and linkage mechanism between each effective offset amount, and the weight coefficient is used to describe the magnitude of the influence of each effective offset amount on the overall rigid offset of the cabin.

[0094] Step 153, determine the horizontal effective offset amount in the horizontal direction and the vertical effective offset amount in the vertical direction for each effective offset amount.

[0095] Step 154, determine the overall rigid offset of the cabin through the following formulas (4) to (7):

[0096]

[0097] where, ΔX total is the horizontal component of the overall rigid offset of the cabin, ΔY total is the vertical component of the overall rigid offset of the cabin, ΔX i is the horizontal effective offset amount, ΔY i is the vertical effective offset amount, ω i is the weight coefficient of the feature segment, δ total is the overall rigid offset of the cabin, D total is the overall offset direction of the cabin.

[0098] In this application, by setting a preset offset range, the true offset amounts within the preset offset range are screened out as the effective offset amounts. In this way, outliers and noise data can be eliminated, the accuracy of the data is improved, and further the accuracy of the cabin offset detection can be improved.

[0099] In the present application, by determining the weight coefficient of the effective offset, that is, considering the influence of different characteristic segments on the overall offset of the cabin, the importance or influence of each characteristic segment in the overall offset of the cabin is reflected, thereby further improving the accuracy of data processing and improving the accuracy of cabin offset detection.

[0100] In the present application, each effective offset is decomposed into a horizontal effective offset in the horizontal direction and a vertical effective offset in the vertical direction. In this way, the complex offset situation can be simplified into offsets in two basic directions, reducing the difficulty of data processing and improving the accuracy of data processing.

[0101] In the cabin deviation detection method proposed in the present application, the method may further perform the following step 160:

[0102] Step 160: When the overall rigidity deviation of the cabin is greater than a preset rigidity deviation, a warning signal and a compensation control instruction are issued to adjust the overall rigidity deviation of the cabin.

[0103] In the present application, when the overall rigid offset of the cabin is greater than the preset rigid offset, that is, the offset of the cabin is more serious, it may have a greater impact on the operation of the ship or the loading and unloading of cargo in the cabin. Therefore, an early warning signal can be issued to remind the control personnel to deal with it in time and control the degree of offset of the cabin. At the same time, a compensation control instruction can also be issued for self-regulation. A compensation strategy is formulated based on the overall rigid offset detected to restore the balance of the cabin, thereby improving the safety of the ship's operation and the loading and unloading of cargo.

[0104] Based on the technical solution proposed in the present application, by extracting the edge contour image of the cabin, determining the set of feature points in the edge contour image, and decomposing the edge contour image into multiple feature segments through the feature point set, the cabin structure can be refined and the local features therein can be highlighted, so that the slight deformation in the cabin can be captured, thereby improving the accuracy of cabin offset detection, and determining the elastic deformation mode of each feature segment in combination with a preset deformation law library, and determining the real offset of each feature segment according to the elastic deformation mode and the offset corresponding to each feature segment, thereby determining the overall rigid offset of the cabin. In this way, the elastic deformation and rigid offset can be effectively separated, and the reasonable elastic deformation of the cabin under different loading conditions can be avoided from affecting the cabin offset detection, thereby further improving the accuracy of cabin offset detection; the offset corresponding to each feature segment can be determined by comprehensively determining the geometric feature parameters, thereby enhancing the reliability of the result, and taking the image when the cabin offset occurs as a reference, it can be more intuitive and specific to determine whether the cabin is offset, thereby improving the accuracy of cabin offset detection.

[0105] The following introduces an apparatus embodiment of the present application, which can be used to execute the cabin offset detection method in the above embodiments of the present application. For details not disclosed in the apparatus embodiment of the present application, please refer to the embodiments of the cabin offset detection method in the above of the present application.

[0106] Refer to Figure 2 , which shows a block diagram of a cabin offset detection device in an embodiment of the present application.

[0107] As Figure 2 shown, the cabin offset detection device 300 according to an embodiment of the present application includes: an image acquisition unit 201, a decomposition unit 202, a first determination unit 203, a second determination unit 204, and a third determination unit 205.

[0108] Among them, the image acquisition unit 201 is configured to acquire a cabin image of the cabin, process the cabin image to obtain an edge contour image of the cabin; the decomposition unit 202 is configured to determine a set of feature points of the edge contour image, and based on the set of feature points, decompose the edge contour image into a plurality of feature segments; the first determination unit 203 is configured to determine the offset of each feature segment based on the geometric feature parameters of each feature segment and a cabin reference image, where the cabin reference image is an image of the cabin when no offset occurs; the second determination unit 204 is configured to match the elastic deformation mode corresponding to each feature segment in a preset deformation rule library based on the morphological features of each feature segment, and determine the elastic deformation amount corresponding to each feature segment, where the morphological features at least include shape features, structural force-bearing features, and position features of the feature segment in the edge contour image; the third determination unit 205 is configured to determine the true offset of each feature segment based on the offset and the corresponding elastic deformation amount of each feature segment, and determine the overall rigid offset of the cabin based on the true offset.

[0109] In some embodiments of the present application, based on the foregoing solution, the image acquisition unit 201 is configured to: perform grayscale processing on the cabin image to obtain a grayscale cabin image; perform noise reduction processing and enhancement processing on the grayscale cabin image to obtain an edge-enhanced image of the cabin; process the edge-enhanced image through an edge detection algorithm and a contour detection algorithm to obtain the edge contour image of the cabin.

[0110] In some embodiments of the present application, based on the foregoing solution, the decomposition unit 202 is configured to: calculate the curvature values of the cabin edge contours in different regions of the edge contour image, and use the extreme points among the respective curvature values as the first candidate feature point set; determine the significant corner points in the edge contour image through a corner detection algorithm, and use the respective significant corner points as the second candidate feature point set, where the significant corner points are corner points with a corner response value greater than a preset response value; integrate the first candidate feature point set and the second candidate feature point set to obtain a total candidate feature point set; determine the Euclidean distance between any two candidate feature points in the total candidate feature point set, and if the Euclidean distance between any two candidate feature points is less than a preset distance, then calculate the ratio between the respective curvature values and corner response values of the any two candidate feature points as a trade-off coefficient, and retain the point with a larger trade-off coefficient between the any two candidate feature points until the Euclidean distance between any two candidate feature points is greater than the preset distance; use the remaining all candidate feature points as the feature point set of the edge contour image.

[0111] In some embodiments of the present application, based on the foregoing solution, the first determination unit 203 is configured to: based on the geometric feature parameters of the respective feature segments and the cabin reference image, determine the offset features between the respective feature segments and the corresponding positions in the cabin reference image, where the offset features may at least include the offset direction and offset amplitude of the corresponding feature segment; based on the offset features of the respective feature segments and the spatial positions of the respective feature segments, divide the respective feature segments into multiple offset sub-regions, where the offset sub-regions include multiple feature segments with adjacent spatial positions and similar offset features; determine the main offset direction of each offset sub-region, and calculate the included angle between the main offset directions of any two adjacent offset sub-regions, and if the included angle is less than a preset included angle threshold, then fuse the any two adjacent offset sub-regions into a new offset sub-region until the included angle between the main offset directions of any two adjacent offset sub-regions is greater than the preset included angle threshold, to obtain multiple fused offset regions; determine the regional offset parameters of each fused offset region, and establish an offset field distribution model based on the regional offset parameters, where the regional offset parameters at least include the boundary coordinates of the regional range, the main offset direction of the region, the average offset vector within the region, and the offset features of the feature segments within the region, and the offset field distribution model is used to reflect the offset distribution law and deformation characteristics of each region of the cabin; calculate the offset amount of each feature segment according to the offset field distribution model.

[0112] In some embodiments of the present application, based on the foregoing solution, the second determination unit 204 is configured to: based on the morphological features of the respective feature segments, match the elastic deformation modes corresponding to the respective feature segments in a preset deformation rule library, and determine the reference elastic deformation amount formula and reference geometric parameters corresponding to the respective feature segments;

[0113] Determine the elastic deformation amount of the straight segment in the feature segment through the following formula:

[0114]

[0115] where, δ elastic is the elastic deformation amount, M is the dynamic load moment, L is the length of the feature segment, E is the elastic modulus, I is the moment of inertia of the cross section, and f(θ) is a shape coefficient function related to the deformation angle of the feature segment;

[0116] Determine the elastic deformation amount of other feature segments except the straight segment through the following formula:

[0117]

[0118] where, M is the dynamic load moment, L is the length of the feature segment, E is the elastic modulus, I is the moment of inertia of the cross section, V is the shear force, G is the shear modulus, and A is the cross-sectional area.

[0119] In some embodiments of the present application, based on the foregoing solution, the third determination unit 205 is configured to: determine the true offset through the following formula:

[0120] δ real = δ measured - ω1·δ elastic - ω2[(k1Lsinθ + k2L 2 cosθ)+ h(L, θ, M, k)]

[0121] where, δ real is the true offset, δ measured is the offset, δ elastic is the elastic deformation amount, ω1 is the elastic correction weight factor, ω2 is the geometric correction weight factor, k, k1 and k2 are geometric correction coefficients, L is the length of the feature segment, θ is the deformation angle of the feature segment, and M is the dynamic load moment of the feature segment.

[0122] In some embodiments of the present application, based on the foregoing solution, the third determination unit 205 is further configured to: determine whether each true offset is within a preset offset range, remove the true offsets outside the preset offset range, and use the remaining true offsets as valid offsets; determine the correlation data between the valid true offsets, and based on the correlation data, determine the weight coefficients corresponding to the valid offsets, where the correlation data is used to describe the dependency relationship and linkage mechanism between the valid offsets, and the weight coefficients are used to describe the magnitude of the influence of the valid offsets on the overall rigid offset of the cabin; determine the horizontal valid offsets of the valid offsets in the horizontal direction and the vertical valid offsets in the vertical direction;

[0123] Determine the overall rigid offset of the cabin through the following formula:

[0124]

[0125] where, ΔX total is the horizontal component of the overall rigid offset of the cabin, ΔY total is the vertical component of the overall rigid offset of the cabin, ΔX i is the horizontal valid offset, ΔY i is the vertical valid offset, ω i is the weight coefficient of the feature segment, δ total is the overall rigid offset of the cabin, D total is the overall offset direction of the cabin.

[0126] In some embodiments of the present application, based on the foregoing solution, the method further includes: when the overall rigid offset of the cabin is greater than the preset rigid offset, sending a warning signal and a compensation control instruction to adjust the overall rigid offset of the cabin.

[0127] Based on the same inventive concept, an embodiment of the present application provides a computer-readable storage medium, in which at least one computer program instruction is stored, and the at least one computer program instruction is loaded and executed by a processor to implement the operations performed by the method as described above.

[0128] Based on the same inventive concept, an embodiment of the present application provides a computer program product, the computer program product includes computer instructions, the computer instructions are stored in a computer-readable storage medium, and are adapted to be read and executed by a processor, so that a computer device having the processor executes to implement the operations performed by the method as described above.

[0129] Based on the same inventive concept, an embodiment of the present application further provides a cabin offset detection device, refer to Figure 3, which shows a schematic structural diagram of a cabin offset detection device in an embodiment of the present application. The cabin offset detection device includes one or more memories 304, one or more processors 302, and at least one computer program (computer program instructions) stored on the memory 304 and executable on the processor 302. When the processor 302 executes the computer program, the method described above is implemented.

[0130] Among them, in Figure 3 , the bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges. Bus 300 links together various circuits including one or more processors represented by processor 302 and memories represented by memory 304. Bus 300 may also link together various other circuits such as peripheral devices, voltage regulators, and power management circuits, etc., which are well known in the art, so they will not be further described herein. Bus interface 305 provides an interface between bus 300 and receiver 301 and transmitter 303. Receiver 301 and transmitter 303 may be the same element, i.e., a transceiver, providing a unit for communicating with various other devices over a transmission medium. Processor 302 is responsible for managing bus 300 and general processing, while memory 304 may be used to store data used by processor 302 when performing operations.

[0131] The functions described herein may be implemented in hardware, software executed by a processor, firmware, or any combination thereof. If implemented in software executed by a processor, the functions may be stored on a computer-readable medium or transmitted via a computer-readable medium as one or more instructions or codes. Other examples and implementations are within the scope and spirit of the present application and the appended claims. For example, due to the nature of software, the functions described above may be implemented using software executed by a processor, hardware, firmware, hardwired, or any combination of these. In addition, each functional unit may be integrated in one processing unit, or each unit may exist physically alone, or two or more units may be integrated in one unit.

[0132] In several embodiments provided by the present application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are merely illustrative. For example, the division of the units may be a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other may be through some interfaces. The indirect coupling or communication connection of units or modules may be in an electrical or other form.

[0133] The unit described as a separation component may or may not be physically separated. The component as a control device may or may not be a physical unit, that is, it may be located in one place or distributed over multiple units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0134] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in various embodiments of this application. The foregoing storage medium includes: various media such as USB flash drives, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), mobile hard disks, magnetic disks, or optical discs that can store computer program instructions.

[0135] The above are only the embodiments of this application and are not used to limit this application. For those skilled in the art, this application can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of this application shall be included within the scope of the claims of this application.

Claims

1. A method for detecting cabin deviation, characterized in that: The method comprises: Acquiring a cabin image of the cabin, and processing the cabin image to obtain an edge contour image of the cabin; Determine a feature point set of the edge contour image, and decompose the edge contour image into a plurality of feature segments based on the feature point set; Determine the offset of each characteristic segment based on the geometric characteristic parameters of each characteristic segment and a cabin reference image, wherein the cabin reference image is an image of the cabin when no offset occurs; Based on the morphological features of each feature segment, the elastic deformation mode corresponding to each feature segment is matched in a preset deformation law library to determine the elastic deformation amount corresponding to each feature segment, wherein the morphological features at least include shape features, structural force features, and position features of the feature segment in the edge contour image; Based on the offset of each characteristic segment and the corresponding elastic deformation, the actual offset of each characteristic segment is determined, and based on the actual offset, the overall rigid offset of the cabin is determined.

2. The method according to claim 1, characterized in that: The processing of the cabin image to obtain the edge contour image of the cabin includes: Performing grayscale processing on the cabin image to obtain a grayscale cabin image; Performing noise reduction and enhancement processing on the grayscale cabin image to obtain an edge enhanced image of the cabin; The edge enhanced image is processed by an edge detection algorithm and a contour detection algorithm to obtain an edge contour image of the cabin.

3. The method according to claim 1, characterized in that The step of determining a set of feature points of the edge contour image comprises: Calculating the curvature values ​​of the cabin edge contours in different areas of the edge contour image, and taking the extreme value points in each curvature value as the first candidate feature point set; Determine significant corner points in the edge contour image by using a corner point detection algorithm, and use each significant corner point as a second candidate feature point set, wherein the significant corner point is a corner point whose corner point response value is greater than a preset response value; Integrate the first candidate feature point set and the second candidate feature point set to obtain a total candidate feature point set; Determine the Euclidean distance between any two candidate feature points in the total candidate feature point set, and if the Euclidean distance between the any two candidate feature points is less than a preset distance, calculate the ratio between the curvature value and the corner point response value of each of the any two candidate feature points as a weighting coefficient, and retain the point with a larger weighting coefficient between the any two candidate feature points until the Euclidean distance between the any two candidate feature points is greater than the preset distance; All remaining candidate feature points are used as a feature point set of the edge contour image.

4. The method according to claim 1, characterized in that The step of determining the offset of each characteristic segment based on the geometric characteristic parameters of each characteristic segment and the cabin reference image comprises: Based on the geometric characteristic parameters of each characteristic segment and the cabin reference image, determining the offset characteristics between each characteristic segment and the corresponding position in the cabin reference image, wherein the offset characteristics may at least include the offset direction and offset amplitude of the corresponding characteristic segment; Based on the offset features of each feature segment and the spatial position of each feature segment, each feature segment is divided into a plurality of offset sub-regions, wherein the offset sub-region includes a plurality of feature segments that are adjacent in spatial position and have similar offset features; Determine the main offset direction of each offset sub-region, and calculate the angle between the main offset directions of any two adjacent offset sub-regions. If the angle is less than a preset angle threshold, merge the two adjacent offset sub-regions into a new offset sub-region until the angle between the main offset directions of any two adjacent offset sub-regions is greater than the preset angle threshold, thereby obtaining multiple merged offset regions. Determine the regional offset parameters of each fused offset region, and establish an offset field distribution model based on the regional offset parameters, wherein the regional offset parameters at least include the coordinates of the regional range boundary, the main offset direction of the region, the average offset vector within the region, and the offset characteristics of the characteristic segments within the region, and the offset field distribution model is used to reflect the offset distribution law and deformation characteristics of each region of the cabin; The offset of each characteristic segment is calculated according to the offset field distribution model.

5. The method according to claim 1, characterized in that The method of matching the elastic deformation modes corresponding to the respective characteristic segments in a preset deformation rule library based on the morphological features of the respective characteristic segments and determining the elastic deformation amounts corresponding to the respective characteristic segments includes: Based on the morphological features of each characteristic segment, the elastic deformation mode corresponding to each characteristic segment is matched in a preset deformation law library, and the reference elastic deformation variable formula and reference geometric parameters corresponding to each characteristic segment are determined; The elastic deformation of the straight line segment in the characteristic segment is determined by the following formula: Among them, δ elastic is the elastic deformation, M is the dynamic load moment, L is the characteristic segment length, E is the elastic modulus, I is the section inertia moment, and f(θ) is the shape coefficient function related to the characteristic segment deformation angle; The elastic deformation of other feature segments except straight line segments is determined by the following formula: Where M is the dynamic load moment, L is the characteristic segment length, E is the elastic modulus, I is the section inertia moment, V is the shear force, G is the shear modulus, and A is the cross-sectional area.

6. The method according to claim 1, characterized in that The actual offset is determined by the following formula: d real =d measured -ω1·d elastic -ω2[(k1Lsinθ+k2L 2 cosθ)+h(L,θ,M,k)] Among them, δ real is the actual offset, δ measured is the offset, δ elastic is the elastic deformation, ω1 is the elastic correction weight factor, ω2 is the geometric correction weight factor, k, k1 and k2 are geometric correction coefficients, L is the length of the feature segment, θ is the deformation angle of the feature segment, and M is the dynamic load moment of the feature segment.

7. The method according to claim 1, characterized in that The determining the overall rigidity offset of the cabin based on the actual offset comprises: Determine whether each real offset is within a preset offset range, remove the real offset outside the preset offset range, and use the remaining real offset as a valid offset; Determine correlation data between each effective real offset, and determine weight coefficients corresponding to each effective offset based on the correlation data, wherein the correlation data is used to describe the dependency relationship and linkage mechanism between each effective offset, and the weight coefficient is used to describe the magnitude of the influence of each effective offset on the overall rigid offset of the cabin; Determine the horizontal effective offset of each effective offset in the horizontal direction and the vertical effective offset in the vertical direction; The overall rigidity offset of the cabin is determined by the following formula: Where ΔX total is the horizontal component of the overall rigid deflection of the cabin, ΔY total is the vertical component of the overall rigid deflection of the cabin, ΔX i is the effective horizontal offset, ΔY i is the vertical effective offset, ω i is the weight coefficient of the feature segment, δ total is the overall rigidity offset of the cabin, D total is the overall offset direction of the cabin.

8. The method according to claim 1, characterized in that The method further comprises: When the overall rigidity deviation of the cabin is greater than the preset rigidity deviation, an early warning signal and a compensation control instruction are issued to adjust the overall rigidity deviation of the cabin.

9. A cabin deviation detection device, characterized in that: The device comprises: an image acquisition unit, configured to acquire a cabin image of the cabin, and process the cabin image to obtain an edge contour image of the cabin; a decomposition unit, used to determine a feature point set of the edge contour image, and decompose the edge contour image into a plurality of feature segments based on the feature point set; A first determining unit, configured to determine an offset of each feature segment based on a geometric feature parameter of each feature segment and a cabin reference image, wherein the cabin reference image is an image of the cabin when no offset occurs; a second determining unit, configured to match the elastic deformation mode corresponding to each feature segment in a preset deformation law library based on the morphological features of each feature segment, and determine the elastic deformation amount corresponding to each feature segment, wherein the morphological features at least include shape features, structural force features, and position features of the feature segment in the edge contour image; The third determination unit is used to determine the real offset of each characteristic segment based on the offset of each characteristic segment and the corresponding elastic deformation, and determine the overall rigid offset of the cabin based on the real offset.

10. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium and are suitable for being read and executed by a processor, so that a computer device having the processor executes the method according to any one of claims 1 to 8.

Images