Computer vision-based automatic identification method for punching parameters of roll-on-roll-off ship drawing

Abstract

The invention discloses a computer vision-based roll-on-roll-off ship drawing tapping parameter automatic identification method. The method comprises the following steps of: firstly, acquiring a drawing image of a roll-on-roll-off ship profile map and carrying out image preprocessing; performing edge detection to obtain a candidate contour of the roll-on-roll-off ship cross beam; extracting a cross beam number by using an optical character recognition technology, screening and determining a target beam contour, and outputting the size of the target beam contour; then generating a mask of the target beam according to the contour of the target beam, determining an opening detection area in the mask of the target beam, and identifying all openings and opening parameters in the opening detection area; and finally, according to the scale ratio of the drawing, all holes and hole parameters are converted into true values, and the true values are exported and stored in an excel file. Aiming at the problems of low efficiency, limited precision and the like of a current manual method, automatic identification and true value restoration of the tapping parameters in the roll-on-roll-off ship drawing are realized by utilizing a computer vision technology and a machine learning method, and the accuracy of subsequent tapping strength prediction is ensured.

Description

Technical Field

[0001] The present invention belongs to the technical field of computer vision and drawing recognition, and particularly relates to an automatic recognition method for the opening parameters of a ro-ro ship drawing based on computer vision. Background Art

[0002] Ship design and manufacturing is a highly specialized and technology-intensive industry, in which ro-ro ships are widely used because they can efficiently load and unload cargo vehicles. During the design process of a ro-ro ship, ensuring structural strength and safety is crucial, especially for the design of openings in the hull, which are used for purposes such as ventilation, cable routing, and pipe installation. However, openings will weaken the overall rigidity of the hull structure, so it is necessary to accurately predict the stress distribution in the opening area to avoid potential safety hazards.

[0003] Ro-ro ship drawings are key documents for engineering design, which specify the specific parameters of each part of the hull structure in detail. The information on the drawings includes not only dimension markings but also complex graphic elements such as beams, ribs, and other structural components. To perform accurate stress analysis, engineers must extract detailed structural parameters from the drawings, especially information such as the location, size, and shape of the openings.

[0004] With the development of computer technology, automated tools have gradually been applied to the ship design field to improve work efficiency and reduce human errors. The requirements of modern shipbuilding for rapid production and high quality have prompted enterprises to seek more advanced solutions to process large amounts of complex drawing data. Nevertheless, the current technologies still have some limitations: on the one hand, the method of manually reading drawings and manually marking is time-consuming and laborious and prone to human errors; on the other hand, the existing semi-automated and automated tools are limited to files in specific formats and show poor accuracy when processing different types of drawings and still require human intervention.

[0005] Therefore, how to efficiently and accurately extract various parameters from ro-ro ship drawings for opening strength prediction is an urgent problem that needs to be solved by those skilled in the art in the current field. Summary of the Invention

[0006] The main purpose of the present invention is to overcome the disadvantages and deficiencies of the prior art, and provide an automatic recognition method for the opening parameters of a ro-ro ship drawing based on computer vision, so as to solve the problems of low efficiency and limited accuracy in the current manual methods, and use computer vision technology to achieve efficient, accurate, and automated reading of the opening parameters.

[0007] To achieve the above purpose, the present invention adopts the following technical solutions: The first purpose is to provide an automatic recognition method for the opening parameters of a ro-ro ship drawing based on computer vision, including the following steps: Collect the drawing image of the ro-ro ship cross-section and perform image preprocessing to obtain the preprocessed image; Perform edge detection on the preprocessed image to obtain the candidate contours of the ro-ro ship crossbeams; Use optical character recognition technology to extract the crossbeam numbers from the vicinity of the candidate contours of the crossbeams, screen and determine the target beam contours, and output the dimensions of the target beam contours; Generate a mask for the target beam based on the target beam contours, determine the opening detection area in the target beam mask, and identify all openings and opening parameters within the opening detection area; According to the scale ratio of the drawing, convert all openings and opening parameters into real values and export and save them to an excel file. As a preferred technical solution, the image preprocessing includes: First, perform grayscale processing on the drawing image; Then, use the Otsu threshold method to binarize the image; Finally, remove the noise points in the binarized image through Gaussian filtering and smooth the image edges.

[0008] As a preferred technical solution, the edge detection is performed using the Canny algorithm, all contours in the preprocessed image are extracted, and the contours are screened according to the area and aspect ratio, and the candidate contours of the ro-ro ship crossbeams are extracted.

[0009] As a preferred technical solution, the optical character recognition technology reads the crossbeam numbers from the vicinity of the candidate contours of the crossbeams, then screens and determines the target beam contours according to the set target numbers, and takes the length and width parameters of the minimum bounding rectangle of the target beam contours as the dimensions of the target beam contours.

[0010] As a preferred technical solution, the identification of all openings and opening parameters within the opening detection area is specifically: Identify the contours of all openings within the opening detection area; Use the polygon fitting algorithm to classify the opening contours to obtain the opening types; the opening types include round holes and waist-shaped holes; Extract the corresponding opening parameters according to the opening types.

[0011] As a preferred technical solution, the classification of the opening contours using the polygon fitting algorithm is specifically: Use the polygon fitting algorithm to simplify the identified opening contours to obtain approximate polygons; Judge the opening type according to the number of vertices of the approximate polygon; If the approximate polygon has no vertices, the opening type is a round hole; If the approximate polygon has multiple vertices, the opening type is a waist-shaped hole.

[0012] As a preferred technical solution, extracting the corresponding hole-opening parameters according to the hole-opening type specifically includes: When the hole-opening type is a regular round hole, directly extract the center coordinates and radius of the hole-opening contour by fitting the minimum circumscribed circle of the hole-opening contour as the hole-opening parameters of the regular round hole; When the hole-opening type is an oval hole, extract the length, width, and center coordinates of the hole-opening contour by fitting the minimum circumscribed rectangle of the hole-opening contour, take the width of the minimum circumscribed rectangle as the radius of the oval hole, and take the difference between the length and width of the minimum circumscribed rectangle as the long side length of the oval hole to obtain the hole-opening parameters of the oval hole.

[0013] As a preferred technical solution, converting all the holes and hole-opening parameters into real values specifically includes: Calculate the real sizes of the target beam and its holes according to the scale ratio in the drawing; Save the target beam number, target beam size, all the holes and hole-opening parameters in the target beam as structured data; Use the pandas library to export and save the structured data as an excel file.

[0014] The second object of the present invention is to provide a computer vision-based automatic identification system for the hole-opening parameters of a ro-ro ship drawing, which is applied to the above-mentioned computer vision-based automatic identification method for the hole-opening parameters of a ro-ro ship drawing, and includes a drawing processing module, an edge detection module, a target screening module, a hole-opening identification module, and a result saving module; The drawing processing module is used to collect the drawing image of the cross-section of the ro-ro ship and perform image preprocessing to obtain a preprocessed image; The edge detection module is used to perform edge detection on the preprocessed image to obtain the candidate contours of the ro-ro ship crossbeam; The target screening module is used to extract the crossbeam number from the vicinity of the candidate contours of the crossbeam by using optical character recognition technology, screen and determine the target beam contour and output the size of the target beam contour; The hole-opening identification module is used to generate a mask of the target beam according to the target beam contour, determine the hole-opening detection area in the target beam mask, and identify all the holes and hole-opening parameters in the hole-opening detection area; The result saving module is used to convert all the holes and hole-opening parameters into real values according to the scale ratio of the drawing and export and save them to an excel file.

[0015] The third object of the present invention is to provide a computer-readable storage medium storing a program, which when executed by a processor, implements the above-mentioned computer vision-based automatic identification method for the hole-opening parameters of a ro-ro ship drawing.

[0016] Compared with the prior art, the present invention has the following advantages and beneficial effects: Through an automated process, the present invention requires no manual intervention from image preprocessing to parameter output, significantly reducing human errors and improving work efficiency. By using technologies such as the Canny algorithm and polygon fitting to distinguish the types of openings and converting the results into real sizes according to the drawing scale ratio, the automated identification of opening parameters in the ro-ro ship drawings and the restoration of real values are realized, ensuring the accuracy of subsequent opening strength prediction. This method supports multiple drawing formats, adapts to complex backgrounds, simplifies the user operation process, and saves the results in the form of structured data for subsequent analysis. The present invention utilizes computer vision technology to achieve efficient, accurate, and automated reading of the opening parameters of ro-ro ship drawings, so as to solve the problems of low efficiency, poor accuracy, and low automation level in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0018] Figure 1 It is the overall flowchart of the automatic identification method for the opening parameters of ro-ro ship drawings based on computer vision in the embodiments of the present invention.

[0019] Figure 2 It is the overall block diagram of the automatic identification system for the opening parameters of ro-ro ship drawings based on computer vision in the embodiments of the present invention.

[0020] Figure 3 It is the structural schematic diagram of the computer-readable storage medium in the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] In order to enable those skilled in the art of the present technology to better understand the solutions of the present application, the following will clearly and completely describe the technical solutions in the embodiments of the present application in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, rather than all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0022] The mention of "embodiment" in the present application means that the specific features, structures, or characteristics described in combination with the embodiment may be included in at least one embodiment of the present application. The phrase appears in various positions in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment mutually exclusive with other embodiments. Those skilled in the art explicitly and implicitly understand that the embodiments described in the present application can be combined with other embodiments.

[0023] For ease of description, in this embodiment, Figure 1 is taken as an example to elaborate in detail the implementation steps of the automatic recognition method for the opening parameters of the roll-on / roll-off ship drawings based on computer vision, specifically including: S1. Collect the drawing image of the roll-on / roll-off ship's cross-section and perform image preprocessing to obtain a preprocessed image.

[0024] Specifically, the image preprocessing includes: First, perform grayscale processing on the drawing image to reduce data complexity; then use the Otsu threshold method (Otsu algorithm) to binarize the image and separate the foreground and background; finally, remove the noise points in the binarized image through Gaussian filtering and smooth the image edges, so that the structural contours in the image are clearer and convenient for subsequent contour extraction.

[0025] S2. Perform edge detection on the preprocessed image to obtain the candidate contours of the roll-on / roll-off ship's crossbeams.

[0026] Specifically, in step S2, the Canny algorithm is used to perform edge detection on the preprocessed image, extract all the contours in the preprocessed image, and screen the contours through area and aspect ratio to extract the candidate contours of the roll-on / roll-off ship's crossbeams. It should be noted that this application is not limited to using the Canny algorithm for edge detection, and other algorithms that can achieve the same purpose can also be used.

[0027] S3. Use optical character recognition technology to extract the crossbeam numbers from the vicinity of the candidate contours of the crossbeams, screen and determine the target beam contours, and output the dimensions of the target beam contours.

[0028] Specifically, the crossbeam numbers are read from the vicinity of the candidate contours of the crossbeams through optical character recognition (OCR) technology, and then the target beam contours are screened according to the target numbers set by the user, and the length and width parameters of the minimum bounding rectangle of the target beam contours are output as the dimensions of the target beam contours.

[0029] The cross-section of the roll-on / roll-off ship contains multiple crossbeam structures and the openings on them, and each crossbeam has a corresponding number. Each crossbeam will be marked with a number on the left side along the crossbeam direction. Since the numbers are sorted from the bottom of the hull upwards in sequence, identifying the numbers is just one method. It is also possible to select the corresponding beams from the bottom up in sequence as the targets after identifying multiple beam structures.

[0030] S4. Generate a mask for the target beam according to the target beam contours, determine the opening detection area in the target beam mask, and identify all the openings and opening parameters in the opening detection area.

[0031] After the target beam is screened and determined according to the target number in step S3, the target beam profile is the opening detection area. Except for the opening detection area, other parts are masked to prevent the openings of other cross beams from being recognized subsequently. Specifically, the specific steps for recognizing the opening and its parameters are as follows: First, use the existing method (such as the contour detection function in the OpenCV library) to recognize the contours of all openings in the opening detection area; then, use the polygon fitting algorithm to classify the opening contours to obtain the opening types. Among them, the opening types include round holes and waist-shaped holes.

[0032] Furthermore, the classification method of the opening type is as follows: Use the polygon fitting algorithm to simplify the recognized opening contour to obtain an approximate polygon; judge the opening type according to the number of vertices of the approximate polygon; if the approximate polygon has no vertices, the opening type is a round hole; if the approximate polygon has multiple vertices, the opening type is a waist-shaped hole.

[0033] Finally, extract the corresponding opening parameters according to the opening type.

[0034] Furthermore, when the opening type is a round hole, directly extract the center coordinates and radius of the opening contour by fitting the minimum circumscribed circle of the opening contour as the opening parameters of the round hole. When the opening type is a waist-shaped hole, extract the length, width and center coordinates of the opening contour by fitting the minimum circumscribed rectangle of the opening contour, take the width of the minimum circumscribed rectangle as the radius of the waist-shaped hole, and take the difference between the length and width of the minimum circumscribed rectangle as the long side length of the waist-shaped hole to obtain the opening parameters of the waist-shaped hole.

[0035] S5. According to the scale ratio of the drawing, convert all the openings and opening parameters into real values and save them in an excel file.

[0036] Specifically, calculate the real sizes of the target beam and its openings according to the scale ratio in the drawing, that is, convert the size information extracted from the image in pixels into real sizes according to the scale ratio of the drawing; save the target beam number, target beam size, all openings and opening parameters in the target beam (such as opening number, opening type, opening radius, center coordinates and / or long side length) as structured data; use the pandas library to export and save the structured data as an excel file.

[0037] The above embodiments are implemented based on the python language and the pycharm development environment. Of course, other computer languages or programming environments can also be used to implement them. At the same time, it is not necessary to export the output result as an excel file. The excel file is used in this embodiment because the output parameters are used as the input of the opening strength prediction software for the roll-on / roll-off ship, and it is more convenient for the program to read this file.

[0038] It should be noted that for the foregoing method embodiments, for the sake of simplicity of description, they are all expressed as a series of action combinations. However, those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be carried out in other sequences or simultaneously.

[0039] Based on the same idea as the computer vision-based automatic identification method for the opening parameters of the roll-on / roll-off ship drawings in the above embodiments, the present invention also provides a computer vision-based automatic identification system for the opening parameters of the roll-on / roll-off ship drawings. This system can be used to execute the above computer vision-based automatic identification method for the opening parameters of the roll-on / roll-off ship drawings. For the sake of convenience of description, in the structural schematic diagram of the embodiment of the computer vision-based automatic identification system for the opening parameters of the roll-on / roll-off ship drawings, only the parts related to the embodiments of the present invention are shown. Those skilled in the art can understand that the illustrated structure does not constitute a limitation on the device, and it may include more or fewer components than those illustrated, or combine certain components, or have different component arrangements.

[0040] As Figure 2 shown, another embodiment of the present invention provides a computer vision-based automatic identification system for the opening parameters of the roll-on / roll-off ship drawings, including a drawing processing module, an edge detection module, a target screening module, an opening identification module, and a result saving module; Among them, the drawing processing module is used to collect the drawing image of the roll-on / roll-off ship sectional view and perform image preprocessing to obtain a preprocessed image; The edge detection module is used to perform edge detection on the preprocessed image to obtain the candidate contours of the roll-on / roll-off ship crossbeams; The target screening module is used to extract the crossbeam numbers from the vicinity of the candidate contours of the crossbeams by using optical character recognition technology, screen and determine the target beam contours, and output the dimensions of the target beam contours; The opening identification module is used to generate a target beam mask according to the target beam contours, determine the opening detection area in the target beam mask, and identify all the openings and opening parameters in the opening detection area; The result saving module is used to convert all the openings and opening parameters into real values according to the scale ratio of the drawing and export and save them to an excel file.

[0041] It should be noted that the computer vision-based automatic identification system for the opening parameters of the roll-on / roll-off ship drawings of the present invention corresponds one-to-one with the computer vision-based automatic identification method for the opening parameters of the roll-on / roll-off ship drawings of the present invention. The technical features and their beneficial effects described in the embodiments of the above computer vision-based automatic identification method for the opening parameters of the roll-on / roll-off ship drawings are applicable to the embodiments of the computer vision-based automatic identification system for the opening parameters of the roll-on / roll-off ship drawings. For the specific content, reference can be made to the description in the method embodiments of the present invention, and details will not be repeated here. This is hereby declared.

[0042] In addition, in the implementation of the computer vision-based automatic recognition system for the opening parameters of the roll-on / roll-off ship drawings in the above embodiments, the logical division of each program module is only for illustrative purposes. In practical applications, according to needs, for example, considering the configuration requirements of the corresponding hardware or the convenience of software implementation, the above functions can be assigned to different program modules to complete, that is, the internal structure of the computer vision-based automatic recognition system for the opening parameters of the roll-on / roll-off ship drawings is divided into different program modules to complete all or part of the functions described above.

[0043] As Figure 3 shown, in one embodiment, a computer-readable storage medium is provided, storing a program in a memory. When the program is executed by a processor, the computer vision-based automatic recognition method for the opening parameters of the roll-on / roll-off ship drawings is implemented, specifically as follows: Collect the drawing image of the cross-section of the roll-on / roll-off ship and perform image preprocessing to obtain a preprocessed image; Perform edge detection on the preprocessed image to obtain the candidate contours of the roll-on / roll-off ship beams; Use optical character recognition technology to extract the beam numbers from the vicinity of the candidate contours of the beams, screen and determine the target beam contours, and output the dimensions of the target beam contours; Generate a mask for the target beam according to the target beam contours, determine the opening detection area in the target beam mask, and identify all the openings and opening parameters in the opening detection area; According to the scale ratio of the drawing, convert all the openings and opening parameters into real values and export and save them to an excel file.

[0044] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium used in the embodiments provided in the present application can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0045] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0046] The above embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited to the above embodiments. Any other changes, modifications, substitutions, combinations, and simplifications made without departing from the spirit and principle of the present invention should be equivalent replacement methods and are all included in the protection scope of the present invention.

Claims

1. An automatic recognition method for the opening parameters of the roll-on / roll-off ship drawings based on computer vision, characterized in that It includes the following steps: Collect the drawing image of the ro-ro ship sectional view and perform image preprocessing to obtain a preprocessed image; Perform edge detection on the preprocessed image to obtain the candidate contours of the ro-ro ship crossbeams; Use optical character recognition technology to extract the crossbeam numbers near the candidate contours of the crossbeams, screen and determine the target beam contours, and output the dimensions of the target beam contours; Generate a mask for the target beam according to the target beam contour, determine the opening detection area in the target beam mask, and identify all openings and opening parameters in the opening detection area; According to the scale ratio of the drawing, convert all openings and opening parameters into real values and export and save them to an excel file.

2. The automatic recognition method for the opening parameters of the roll-on / roll-off ship drawings based on computer vision according to claim 1, wherein The image preprocessing includes: First, perform grayscale processing on the drawing image; Then use the Otsu threshold method to binarize the image; Finally, remove the noise points in the binarized image through Gaussian filtering and smooth the image edges.

3. The automatic recognition method for the opening parameters of the roll-on / roll-off ship drawing based on computer vision according to claim 1, characterized in that, The edge detection is performed using the Canny algorithm, all contours in the preprocessed image are extracted, and the contours are screened according to the area and aspect ratio, and the candidate contours of the ro-ro ship crossbeams are extracted.

4. The automatic recognition method for the opening parameters of the ro-ro ship drawing based on computer vision according to claim 1, characterized in that The optical character recognition technology reads the crossbeam numbers near the candidate contours of the crossbeams, then screens and determines the target beam contours according to the set target numbers, and takes the length and width parameters of the minimum bounding rectangle of the target beam contour as the dimensions of the target beam contour.

5. The automatic recognition method for the opening parameters of the ro-ro ship drawings based on computer vision according to claim 1, wherein Identifying all openings and opening parameters in the opening detection area specifically includes: Identifying the contours of all openings in the opening detection area; Using the polygon fitting algorithm to classify the opening contours to obtain the opening types; the opening types include round holes and waist-shaped holes; Extract the corresponding opening parameters according to the opening types.

6. The automatic recognition method for the opening parameters of the ro-ro ship drawing based on computer vision according to claim 5, characterized in that The classification of the opening contours using the polygon fitting algorithm specifically includes: Using the polygon fitting algorithm to simplify the identified opening contours to obtain an approximate polygon; Judging the opening type according to the number of vertices of the approximate polygon; If the approximate polygon has no vertices, the opening type is a round hole; If the approximate polygon has multiple vertices, the opening type is a waist-shaped hole.

7. The automatic recognition method for the opening parameters of the ro-ro ship drawings based on computer vision according to claim 5, characterized in that The extraction of the corresponding opening parameters according to the opening types specifically includes: When the opening type is a round hole, directly extract the center coordinates and radius of the opening contour by fitting the minimum circumscribed circle of the opening contour as the opening parameters of the round hole; When the opening type is a waist-shaped hole, extract the length, width and center coordinates of the opening contour by fitting the minimum circumscribed rectangle of the opening contour, take the width of the minimum circumscribed rectangle as the radius of the waist-shaped hole, and take the difference between the length and width of the minimum circumscribed rectangle as the long side length of the waist-shaped hole to obtain the opening parameters of the waist-shaped hole.

8. The automatic recognition method for the opening parameters of the roll-on / roll-off ship drawing based on computer vision according to claim 1, characterized in that The conversion of all openings and opening parameters into real values specifically includes: Calculating the real sizes of the target beam and its openings according to the scale ratio in the drawing; Saving the target beam number, target beam size, all openings and opening parameters in the target beam as structured data; Using the pandas library to export and save the structured data as an excel file.

9. An automatic recognition system for the opening parameters of a ro-ro ship drawing based on computer vision, characterized in that, Applied to the computer vision-based automatic identification method for opening parameters of ro-ro ship drawings described in any one of claims 1-8, including a drawing processing module, an edge detection module, a target screening module, an opening identification module and a result saving module; The drawing processing module is used to collect the drawing image of the cross-section of the ro-ro ship and perform image preprocessing to obtain a preprocessed image; The edge detection module is used to perform edge detection on the preprocessed image to obtain the candidate contour of the ro-ro ship beam; The target screening module is used to extract the beam number from the vicinity of the candidate contour of the beam by using optical character recognition technology, screen and determine the target beam contour and output the size of the target beam contour; The opening recognition module is used to generate a mask of the target beam according to the target beam contour, determine the opening detection area in the target beam mask and identify all openings and opening parameters in the opening detection area; The result saving module is used to convert all the openings and opening parameters into real values according to the scale ratio of the drawing and export and save them to an excel file.

10. A computer-readable storage medium storing a program, characterized in that, When the program is executed by a processor, it implements the computer vision-based automatic recognition method for opening parameters of ro-ro ship drawings according to any one of claims 1-8.

Images