Tire ink mark identification method, equipment and medium

Abstract

The invention discloses a tire printing ink mark identification method and device and a medium, and the method comprises the steps: scanning an original image of a printing ink mark, and carrying out the preprocessing of the scanning image of the printing ink mark, so as to obtain a preprocessed mark image; the preprocessing comprises color model parameter adjustment, median filtering processing and binarization processing; fitting impression contours corresponding to all impression areas in the impression image, and generating an adjusted impression contour in response to a dragging operation of a user for the impression contours; taking all the adjusted impression contours as a whole, fitting a minimum circumscribed polygon corresponding to the impression contour whole, and automatically extracting impression geometric features; and in response to a selection operation of a user for the measurement points, determining a corresponding target measurement point, and based on the minimum circumscribed polygon, calculating the print length of the position where the target measurement point is located.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a method, device and medium for identifying tire ink prints. Background Art

[0002] At present, in the development history of the automobile industry, tires are the key medium for the interaction between cars and roads, and their performance is directly related to the overall handling stability, braking efficiency and ride comfort of the vehicle. With the continuous advancement of automobile technology and the increasing demand of consumers for driving experience, in-depth research and optimization of tire ground contact performance is particularly important. The geometric characteristics and pressure distribution characteristics of tires when they are grounded not only reflect the design and manufacturing level of the tire itself, but also directly affect the driving performance of the vehicle under various road conditions.

[0003] As a direct basis for evaluating tire performance, the precise measurement and analysis technology of tire contact footprint has always been a hot topic in the field of tire R&D and vehicle dynamics research. The geometric characteristics of the footprint, such as footprint area, actual contact area, footprint length, footprint width and rectangular ratio, i.e., footprint aspect ratio, provide valuable feedback information for tire designers, which helps to optimize tire structure, material formulation and tread pattern design, thereby improving the overall performance of the tire.

[0004] With the development of computer vision, existing technologies can process tire ink print images through image recognition technology, extract the geometric features of tires, and analyze the ground contact performance of tires. However, most existing ink print analysis and processing software cannot distinguish between the print area and impurity areas such as marks, cannot manually adjust the print contour, and cannot independently select the measurement position, which affects the accuracy of the analysis. Summary of the invention

[0005] The embodiments of the present application provide a tire ink print recognition method, device and medium to solve the above-mentioned technical problems.

[0006] On the one hand, an embodiment of the present application provides a method for identifying a tire ink mark, comprising:

[0007] Scanning the original image of the ink imprint, and preprocessing the ink imprint scanned image to obtain a preprocessed imprint image; the preprocessing includes color model parameter adjustment, median filtering and binarization;

[0008] Fitting the imprint contours corresponding to all the imprint regions in the imprint image, and generating an adjusted imprint contour in response to a user's dragging operation on the imprint contour;

[0009] Taking all the adjusted imprint contours as a whole, fitting the minimum circumscribed polygon corresponding to the entire imprint contour, and automatically extracting the imprint geometric features;

[0010] In response to the user's selection operation on the measuring point, the corresponding target measuring point is determined, and based on the minimum circumscribed polygon, the length of the imprint at the position where the target measuring point is located is calculated.

[0011] In one implementation of the present application, the original image of the ink imprint is scanned, and the ink imprint scanned image is preprocessed to obtain a preprocessed imprint image, specifically including:

[0012] Acquire an original image of the ink impression, and scan the original image to obtain a corresponding ink impression scanned image;

[0013] Performing color filtering on the ink print scanned image, and performing median filtering on the color filtered print image;

[0014] The color-filtered and filtered impression image is binarized to obtain a preprocessed impression image.

[0015] In one implementation of the present application, color filtering is performed on the ink print scanned image, and median filtering is performed on the color filtered print image, specifically including:

[0016] Adjusting the model parameters in the color model corresponding to the ink imprint scanned image to perform color filtering on the ink imprint scanned image, and extracting the imprint image corresponding to the imprint area in the ink imprint scanned image after color filtering;

[0017] Based on the filter kernel, a filter process is performed on the imprint area in the color filtered imprint image to remove image edge noise in the imprint image.

[0018] In an implementation of the present application, in response to a user's dragging operation on the print contour, after generating an adjusted print contour, the method further includes:

[0019] Calculate the sum of the areas of the pixels of the grounded part corresponding to all the adjusted imprint contours to obtain the pixel grounded area of ​​the enclosed area corresponding to all the adjusted imprint contours;

[0020] Acquire the actual paper area of ​​the paper corresponding to the ink print scan image, as well as the pixel paper length and pixel paper width corresponding to the paper, and calculate the pixel paper area corresponding to the paper according to the pixel paper length and the pixel paper width;

[0021] A grounded paper area ratio between the pixel grounded area and the pixel paper area is determined, so as to calculate an actual grounded paper area corresponding to the ink imprint according to a product between the grounded paper area ratio and the actual paper area.

[0022] In one implementation of the present application, after taking all the adjusted imprint contours as a whole and fitting the minimum circumscribed polygon corresponding to the entire imprint contour, the method further includes:

[0023] Calculating the sum of the areas of the pixels of the print portion corresponding to the minimum circumscribed polygon to obtain the pixel print area corresponding to the entire print outline;

[0024] An imprint-to-paper area ratio between the pixel imprint area and the pixel paper area is determined, so as to calculate an actual imprint area corresponding to the entire imprint contour according to a product between the imprint-to-paper area ratio and the actual paper area.

[0025] In one implementation of the present application, after taking all the adjusted imprint contours as a whole and fitting the minimum circumscribed polygon corresponding to the entire imprint contour, the method further includes:

[0026] Fitting the minimum circumscribed rectangle corresponding to the entire imprint contour, and determining the imprint length and imprint width of the entire imprint contour according to the length and width of the minimum circumscribed rectangle;

[0027] Acquire the actual paper length and actual paper width of the paper corresponding to the ink imprint scan image, and determine the longitudinal position to be measured in the minimum circumscribed rectangle;

[0028] Determine the pixel imprint length based on the line segment length between the intersection point of the straight line corresponding to the longitudinal position to be measured and the minimum circumscribed polygon;

[0029] Determine an impression-to-paper length ratio between a pixel impression length and a pixel paper length, and determine an actual impression length corresponding to the entire impression contour according to a product of the impression-to-paper length ratio and an actual paper length;

[0030] The horizontal side length of the minimum circumscribed rectangle is determined, and based on the horizontal side length, the actual impression width corresponding to the entire impression outline is determined.

[0031] In one implementation of the present application, after fitting the minimum circumscribed rectangle corresponding to the entire print contour, the method further includes:

[0032] Identify the print contour in the minimum circumscribed rectangle, determine the coordinates corresponding to the leftmost endpoint and the rightmost endpoint of the print contour, and calculate the horizontal coordinate corresponding to the center position of all the print contours according to the horizontal coordinate of the leftmost endpoint and the horizontal coordinate of the rightmost endpoint to determine the length of the print at the center position;

[0033] Based on the horizontal coordinate corresponding to the center position, the imprint length of the left end designated position and the imprint length of the right end designated position of all imprint contours are determined to calculate the sum of the corresponding imprint lengths of the left and right end designated positions, and based on the sum of the imprint length of the center position and the imprint lengths of the left and right end designated positions, the rectangular ratio corresponding to the entire imprint area is calculated.

[0034] In one implementation of the present application, fitting the imprint contours corresponding to all the imprint areas in the imprint image, and generating an adjusted imprint contour in response to a user's dragging operation on the imprint contour, specifically includes:

[0035] Generating a transparent layer having the same size as the original image of the ink print, and superimposing the transparent layer on the original image;

[0036] Fitting the imprint contour on the original image, and displaying the fitted imprint contour on the transparent layer;

[0037] According to a preset division rule, the minimum circumscribed polygon is longitudinally divided into a plurality of longitudinal contours to obtain a corresponding plurality of equally divided points, and the plurality of equally divided points are inserted into a vertex coordinate set corresponding to the minimum circumscribed polygon;

[0038] receiving a user's drag operation request for the imprint outline, and using all points in the vertex coordinate set as identification points of the drag operation request;

[0039] In response to the drag operation request, an identification point corresponding to the drag operation request is determined, and a corresponding imprint contour is adjusted according to the identification point to generate an adjusted imprint contour.

[0040] On the other hand, the embodiment of the present application further provides a tire ink mark recognition device, the device comprising:

[0041] at least one processor;

[0042] and, a memory communicatively coupled to the at least one processor;

[0043] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the tire ink print recognition method as described above.

[0044] On the other hand, an embodiment of the present application further provides a non-volatile computer storage medium storing computer executable instructions, which, when executed, implements a tire ink print recognition method as described above.

[0045] The present application provides a method, device and medium for identifying tire ink marks, which at least have the following beneficial effects:

[0046] By adjusting the color model parameters, the contrast between the print and the background can be enhanced to make the print more prominent; the median filter process can effectively remove the noise in the image and improve the image clarity; and the binarization process can simplify the image into black and white, which is convenient for subsequent contour recognition and processing, thereby improving the accuracy and efficiency of print recognition; by automatically fitting the print contour, the user's time for manual outlining can be saved and work efficiency can be improved; at the same time, allowing the user to drag and adjust the contour enhances the flexibility and accuracy of the operation, making the print contour more in line with actual needs; by fitting the minimum circumscribed polygon, it is convenient for subsequent calculation and analysis; and allowing the user to select the measurement point makes the measurement more targeted and practical, meeting the measurement needs in different scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0048] Figure 1 A schematic diagram of a process for identifying a tire ink mark provided in an embodiment of the present application;

[0049] Figure 2 A schematic diagram of a binary impression image provided in an embodiment of the present application;

[0050] Figure 3 A schematic diagram of an unadjusted minimum circumscribed polygon provided in an embodiment of the present application;

[0051] Figure 4 A schematic diagram of the minimum circumscribed polygon after adjustment provided in an embodiment of the present application;

[0052] Figure 5 A schematic diagram of the internal structure of a tire ink mark recognition device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. 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 making creative work are within the scope of protection of the present application.

[0054] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0055] Figure 1 A schematic flow chart of a method for identifying tire ink marks provided in an embodiment of the present application.

[0056] The analysis method involved in the embodiments of the present application can be implemented by a terminal device or a server, and the present application does not impose any special restrictions on this. For the convenience of understanding and description, the following embodiments are described in detail by taking a server as an example.

[0057] It should be noted that the server may be a single device or a system consisting of multiple devices, that is, a distributed server, and this application does not make any specific limitation on this.

[0058] like Figure 1 As shown, a tire ink mark recognition method provided in an embodiment of the present application includes:

[0059] 101. Scan the original image of the ink print, and pre-process the ink print scanned image to obtain a pre-processed print image. It should be noted that the pre-processing in the embodiment of the present application includes color model parameter adjustment, median filtering and binarization.

[0060] This application uses a visual program interface designed with the PyQt package, which has the functions of importing pictures, selecting paper size, print analysis, displaying and saving results. The tire's forward direction in the imported ink print scan image may be along the up-down direction of the screen, or along the left-right direction. In order to make the recognition and calculation results more accurate, this application adds an image rotation button to keep the ink print scan image always in the direction of the tire's forward direction along the up-down direction of the screen. In addition, in order to make the imported ink print scan image adapt to the size of the program window, this application scales the image, so the vertical or horizontal scaling ratio of the image should also be considered when analyzing and calculating the geometric parameters of the print.

[0061] Specifically, in one embodiment of the present application, scanning the original image of the ink imprint and preprocessing the ink imprint scanned image to obtain a preprocessed imprint image specifically includes:

[0062] Acquire an original image of the ink impression, and scan the original image to obtain a corresponding ink impression scan image;

[0063] Performing color filtering on the ink print scanned image, and performing median filtering on the color filtered print image;

[0064] The color-filtered and filtered impression image is binarized to obtain a preprocessed impression image.

[0065] In one embodiment, a high-resolution digital camera or scanner is used to photograph or scan the ink imprint left by the tire during the test, ensuring that the light in the shooting environment is uniform to avoid the influence of shadows and reflections on the image quality, and the photographed or scanned image is saved in a digital format, such as JPEG, PNG or TIFF, for subsequent processing.

[0066] If you are using a scanner, directly import the original image file into the scanning software and make the scanning settings, such as resolution, color mode, etc. If you are using a photo taken with a digital camera, you do not need to scan it again and can directly proceed to the next step of color filtering. After the scan is completed, save the scanned image of the ink impression to ensure that the image is clear and distortion-free.

[0067] The ink impression image obtained by scanning often contains impurities such as handwriting and stains. If it is not processed, it will interfere with the image recognition of the impression area. Therefore, the ink impression scanned image is imported into the program, and the parameters of the color model are adjusted according to the color characteristics of the ink impression to highlight the impression area and remove background interference. After color filtering, the obtained impression image is saved to ensure that the impression area is clear and recognizable. The color filtered impression image is processed by median filtering to remove noise and spots in the image while retaining the outline and details of the impression. After filtering, the filtered impression image is saved to ensure that the image is smooth and the impression outline is clear.

[0068] Binarization is to set the grayscale value of the pixel on the image to 0 or 255, so that the entire image presents a clear black and white effect. It can effectively distinguish the target area and the background area, enhance the image contrast and features, facilitate subsequent image analysis and processing, and can also greatly reduce the amount of data, saving storage and computing costs. This application adopts the OTSU binarization method, and the obtained division threshold can maximize the variance between the foreground and the background, and the calculation is simple. The color filtered and filtered imprint image is binarized to convert the image into a binary image containing only black and white. In the binary image, the imprint area is black and the background is white. After the binarization process, the obtained pre-processed imprint image is saved, which will be used for subsequent contour fitting, area calculation and other analysis and processing.

[0069] In one embodiment of the present application, color filtering is performed on the ink print scanned image, and median filtering is performed on the color filtered print image, specifically including:

[0070] Adjusting the model parameters in the color model corresponding to the ink imprint scanned image to perform color filtering on the ink imprint scanned image, and extracting the imprint image corresponding to the imprint area in the ink imprint scanned image after color filtering;

[0071] Based on the filter kernel, the imprint area in the color filtered imprint image is filtered to remove image edge noise in the imprint image.

[0072] In one embodiment, HSV is a color space created based on the intuitive characteristics of color, also known as a hexagonal pyramid model. In the HSV model, color is composed of hue, saturation, and value. By adjusting the H, S, and V parameters, the image of the imprint area can be enhanced and the impurity image with a color different from the imprint color can be weakened to achieve the effect of color filtering of the image.

[0073] Median filtering is a nonlinear filtering method that takes the pixel values ​​of the current pixel and the surrounding pixels (an odd number of pixels in total), sorts them, and uses the value in the middle as the pixel value of the current pixel. The median filter has a good noise elimination effect, but as the filter kernel increases, the image will become blurred. This work uses a 5*5 filter kernel to filter the mask area after HSV color filtering to achieve the effect of eliminating image edge noise.

[0074] Figure 2 This is a schematic diagram of a binary impression image provided in an embodiment of the present application. Figure 2 As shown, the original image of the ink print is subjected to color filtering and filtering processing, and further to binarization processing to obtain a binary black and white print image, so as to subsequently calculate the actual ground contact area of ​​the ink print in the black and white print image.

[0075] 102. Fitting the print contours corresponding to all the print regions in the print image, and generating an adjusted print contour in response to a user's dragging operation on the print contour.

[0076] Specifically, in one embodiment of the present application, fitting the print contours corresponding to all the print areas in the print image, and generating an adjusted print contour in response to a user's dragging operation on the print contour, specifically includes:

[0077] Generate a transparent layer with the same size as the original image of the ink impression, and overlay the transparent layer on the original image;

[0078] Fitting the imprint contour on the original image, and displaying the fitted imprint contour on a transparent layer;

[0079] Divide the imprint contour into equal parts, determine the corresponding dividing points, and insert the dividing points into the vertex coordinate set corresponding to the minimum circumscribed polygon;

[0080] receiving a user's drag operation request for the imprint outline, and using all points in the vertex coordinate set as identification points of the drag operation request;

[0081] In response to the drag operation request, an identification point corresponding to the drag operation request is determined, and the corresponding print contour is adjusted according to the identification point to generate an adjusted print contour.

[0082] In one embodiment, the present application uses the minimum convex polygon to fit the impression contour. This method is accurate in fitting and fast in calculation. However, for butterfly-shaped impressions with depressions, the fitting result will have a large error. Therefore, this work adds the function of manually adjusting the contour. First, a transparent layer of the same size as the original image is superimposed on the imported image, and the fitting contour is displayed, adjusted, and updated on the transparent layer.

[0083] The fitted minimum convex polygon returns a set of vertex coordinates of the convex polygon. In order to enable the mouse to identify and adjust the contour more flexibly, this application also calculates 30 equally divided points of the upper and lower contours, and adds the equally divided points to the vertex coordinate set to interpolate the vertex coordinate set. When adjusting the contour, first identify the point closest to the mouse position in the vertex coordinate set, drag the mouse to the target position, update the vertex coordinate set, and then redraw the contour connected from beginning to end. After the imprint contour is updated, the geometric parameter features will also be recalculated and output.

[0084] In one embodiment of the present application, in response to a user's dragging operation on the print contour, after generating an adjusted print contour, the method includes:

[0085] Calculate the sum of the areas of the pixels of the grounded part corresponding to all the adjusted imprint contours to obtain the pixel grounded area of ​​the enclosed area corresponding to all the adjusted imprint contours;

[0086] Obtaining the actual paper area of ​​the paper corresponding to the ink imprint scanned image, as well as the pixel paper length and pixel paper width corresponding to the paper, and calculating the pixel paper area corresponding to the paper according to the pixel paper length and pixel paper width;

[0087] A grounded paper area ratio between the pixel grounded area and the pixel paper area is determined to calculate the actual grounded paper area corresponding to the ink impression according to the product between the grounded paper area ratio and the actual paper area.

[0088] In one embodiment, the red imprint part in the imprint scan image is extracted, the contour is fitted using the Opencv package, and the pixel area of ​​the area surrounded by the contour is calculated. The sum of all pixel areas is regarded as the pixel area of ​​the entire grounding part, and then the actual grounding area of ​​the ink imprint is calculated according to the ratio of the grounding pixel area to the pixel area of ​​the entire image. The specific calculation formula is:

[0089]

[0090] It should be noted that S in the embodiments of the present applicationgt Indicates the actual ground contact area of ​​the ink print in square centimeters (cm2), S pt Indicates the actual paper area in square centimeters (cm2). PP Represents the pixel paper area, which is the sum of the areas of all pixels on the entire paper and is determined by the product of the paper pixel length and the paper pixel width. gp Represents the ground area of ​​the pixel, which is the sum of the areas of all grounded pixels in the ink print.

[0091] 103. Take all the adjusted imprint contours as a whole, fit the minimum circumscribed polygon corresponding to the entire imprint contour, and automatically extract the imprint geometric features.

[0092] It should be noted that the geometric features of the footprint in the embodiments of the present application include, for example, contact area, footprint area, footprint length, footprint width and rectangular ratio.

[0093] In one embodiment of the present application, all the adjusted imprint contours are taken as a whole, and after fitting the minimum circumscribed polygon corresponding to the entire imprint contour, the following steps are included:

[0094] Calculate the sum of the areas of the pixels of the print part corresponding to the minimum circumscribed polygon to obtain the pixel print area corresponding to the entire print outline;

[0095] The impression-to-paper area ratio between the pixel impression area and the pixel paper area is determined, so as to calculate the actual impression area corresponding to the entire impression contour according to the product between the impression-to-paper area ratio and the actual paper area.

[0096] In one embodiment, the imprint area of ​​the entire imprint region is calculated by first treating all the imprint contours as a whole, fitting the minimum circumscribed convex polygon corresponding to the contour as a whole, and calculating the pixel imprint area corresponding to the minimum circumscribed convex polygon. Similarly, the imprint area corresponding to the entire imprint region is calculated based on the ratio of the polygon pixel imprint area to the entire paper pixel area. The specific calculation formula is:

[0097]

[0098] It should be noted that S in the embodiments of the present application ft Indicates the actual imprint area in square centimeters (cm2), S fp Represents the pixel imprint area, which is the sum of the areas of all pixels in the imprint part.

[0099] In one embodiment of the present application, all the adjusted imprint contours are taken as a whole, and after fitting the minimum circumscribed polygon corresponding to the entire imprint contour, the following steps are included:

[0100] Fitting the minimum circumscribed rectangle corresponding to the entire imprint contour, and determining the imprint length and imprint width of the entire imprint contour according to the length and width of the minimum circumscribed rectangle;

[0101] Obtaining the actual paper length and actual paper width of the paper corresponding to the ink imprint scanned image, and determining the longitudinal position to be measured in the minimum circumscribed rectangle;

[0102] Determine the pixel imprint length based on the line segment length between the intersection point of the straight line corresponding to the longitudinal position to be measured and the minimum circumscribed polygon;

[0103] Determine the impression-to-paper length ratio between the pixel impression length and the pixel paper length, and determine the actual impression length corresponding to the overall impression contour according to the product between the impression-to-paper length ratio and the actual paper length;

[0104] The horizontal side length of the minimum circumscribed rectangle is determined, and based on the horizontal side length, the actual impression width corresponding to the overall impression contour is determined.

[0105] In one embodiment, in a specific ink mark analysis system, in order to accurately measure the size of the ink mark on the paper, the system first obtains a scanned image containing the ink mark through a high-precision scanner. This image not only contains detailed information about the ink mark, but also reflects the actual physical size of the paper. According to the selected paper, the actual paper length and the actual paper width are determined. It should be noted that the paper selected in the embodiment of the present application, such as A4 paper or A3 paper, the actual paper length and the actual paper width can be directly determined according to the specifications of the selected paper.

[0106] Next, the ink print contour is extracted from the scanned image, and the minimum circumscribed rectangle corresponding to the entire print contour is calculated. This rectangle is the minimum rectangle surrounding the entire print contour, and its sides are parallel to the image coordinate axis.

[0107] In the minimum circumscribed rectangle, the system defines the vertical position to be measured as the vertical line where the midpoint of the long side of the rectangle is located, and the horizontal position to be measured is the line segment where the midpoint of the short side of the rectangle is located. It should be noted that this line segment may be a horizontal line or have a certain inclination angle. For the vertical position to be measured, the system calculates the length of the line segment between the two intersection points of the straight line and the minimum circumscribed polygon to obtain the pixel imprint length along the vertical direction.

[0108] In one embodiment, the length and width of the minimum circumscribed rectangle of the print outline are regarded as the length and width of the print, and the specific calculation formula is:

[0109]

[0110] It should be noted that L in the embodiments of the present application ftIndicates the actual length of the imprint in centimeters (cm), L pt Indicates the actual paper length in centimeters (cm), L fp Indicates the pixel imprint length, which is the sum of the vertical pixel lengths of the imprint, L PP Indicates the pixel paper length, which is the sum of the vertical pixel lengths of the entire paper.

[0111]

[0112] It should be noted that W in the embodiments of the present application ft Indicates the actual width of the imprint in centimeters (cm), W pt Indicates the actual paper width in centimeters (cm), W fp Indicates the pixel imprint width, which is the sum of the width of the horizontal pixels of the imprint, W PP Represents the pixel paper width, which is the sum of the horizontal pixel widths of the entire paper.

[0113] 104. In response to the user's selection operation on the measurement point, determine the corresponding target measurement point, and calculate the length of the imprint at the location of the target measurement point based on the minimum circumscribed polygon.

[0114] After the mouse event drags a point in the contour, the vertex coordinate set corresponding to the minimum circumscribed polygon is updated, and the closed contour connected end to end is redrawn according to the vertices in the updated vertex coordinate set to achieve manual adjustment of the contour.

[0115] First of all, the program can automatically extract the geometric features of the imprint, such as: ground contact area, imprint area, length, width, and rectangular ratio. In addition, in order to more flexibly meet the measurement needs of the staff, this application adds manual selection of measurement points, and automatically calculates the position and length of the imprint at the measurement point, so as to supplement the calculation of the imprint length of the measurement point. The selected measurement point is located by mouse events, the distance from the measurement point to the left contour is calculated, a line segment parallel to the center length line is drawn and its intersection with the upper and lower contours is obtained, and then the length of the line segment between the two intersections is calculated. The selection, drawing, cancellation and calculation of measurement points are also performed on a transparent layer to make the interface display more stable.

[0116] After calculating the print length, the application stores the print length in the length list, and in response to the user's reselection of the measurement point, deletes the corresponding print length in the length list in reverse order, and updates the displayed data and image to achieve the cancellation and reselection of the measurement point. All fitting, drawing, calculation and update in the tire ink print image will be displayed in the program's window interface, and the analysis image and result text file will be saved.

[0117] Specifically, in one embodiment of the present application, after fitting the minimum circumscribed rectangle corresponding to the entire print contour, the following steps are included:

[0118] Identify the imprint contour in the minimum circumscribed rectangle, determine the coordinates corresponding to the leftmost endpoint and the rightmost endpoint of the imprint contour, and calculate the abscissa corresponding to the center position of all imprint contours according to the abscissa of the leftmost endpoint and the abscissa of the rightmost endpoint to determine the imprint length at the center position;

[0119] Based on the horizontal coordinate corresponding to the center position, determine the imprint length of the left end specified position and the imprint length of the right end specified position of all imprint contours to calculate the sum of the corresponding imprint lengths of the left and right end specified positions, and based on the sum of the imprint length of the center position and the imprint lengths of the left and right end specified positions, calculate the rectangular ratio corresponding to the entire imprint area.

[0120] In one embodiment, the rectangular ratio is calculated as the percentage of the length of the center mark to the average length of the mark at 80% of the left and right positions. The specific calculation formula is:

[0121]

[0122] It should be noted that FSF in the embodiment of the present application represents the squareness ratio, and the unit is 1, L c Indicates the length of the center mark in centimeters (cm), L 8l Indicates the length of the mark at 80% on the left side, in centimeters (cm), L 8r It indicates the length of the mark at 80% on the right side, in centimeters (cm).

[0123] The closer the rectangular ratio is to 1, the closer the shape of the footprint is to a rectangle. When FSF is less than 1, it means that the ground contact length of the crown center is less than the average ground contact length of the two shoulders, the crown is concave, and the footprint is butterfly-shaped. At this time, the tire has good cornering performance, but poor straight-line performance. When FSF is greater than 1, the footprint is elliptical. At this time, the tire has good straight-line performance and strong load-bearing capacity, but poor steering performance when turning.

[0124] like Figure 3 and Figure 4 As shown, Figure 3 is the unadjusted minimum circumscribed polygon. The present application adjusts the imprint contour according to the user's drag operation request for the imprint contour, thereby obtaining Figure 4 The adjusted minimum enclosing polygon is shown.

[0125] The above is an embodiment of the method proposed in this application. Based on the same inventive concept, this embodiment of the application also provides a tire ink mark recognition device, the structure of which is as follows: Figure 5 shown.

[0126] Figure 5This is a schematic diagram of the internal structure of a tire ink mark recognition device provided in an embodiment of the present application. Figure 5 As shown, the device includes:

[0127] at least one processor;

[0128] and, a memory communicatively coupled to the at least one processor;

[0129] The memory stores instructions that can be executed by at least one processor, and the instructions are executed by at least one processor to enable the at least one processor to:

[0130] Scanning the original image of the ink imprint, and preprocessing the ink imprint scanned image to obtain a preprocessed imprint image; the preprocessing includes color model parameter adjustment, median filtering and binarization;

[0131] Fitting the imprint contours corresponding to all the imprint areas in the imprint image, and generating an adjusted imprint contour in response to a user's dragging operation on the imprint contour;

[0132] Taking all the adjusted imprint contours as a whole, fitting the minimum circumscribed polygon corresponding to the entire imprint contour, and automatically extracting the imprint geometric features;

[0133] In response to the user's selection operation on the measuring point, the corresponding target measuring point is determined, and based on the minimum circumscribed polygon, the length of the imprint at the position where the target measuring point is located is calculated.

[0134] The present application also provides a non-volatile computer storage medium storing computer executable instructions. When the computer executable instructions are executed, they can:

[0135] Scanning the original image of the ink imprint, and preprocessing the ink imprint scanned image to obtain a preprocessed imprint image; the preprocessing includes color model parameter adjustment, median filtering and binarization;

[0136] Fitting the imprint contours corresponding to all the imprint areas in the imprint image, and generating an adjusted imprint contour in response to a user's dragging operation on the imprint contour;

[0137] Taking all the adjusted imprint contours as a whole, fitting the minimum circumscribed polygon corresponding to the entire imprint contour, and automatically extracting the imprint geometric features;

[0138] In response to the user's selection operation on the measuring point, the corresponding target measuring point is determined, and based on the minimum circumscribed polygon, the length of the imprint at the position where the target measuring point is located is calculated.

[0139] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device and medium embodiments, since they are basically similar to the method embodiments, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiments.

[0140] The above describes specific embodiments of the present application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0141] The devices and media provided in the embodiments of the present application correspond one-to-one to the methods. Therefore, the devices and media also have similar beneficial technical effects as the corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the devices and media will not be repeated here.

[0142] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0143] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0144] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0145] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0146] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0147] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0148] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0149] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0150] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for identifying tire ink marks, characterized in that: The method comprises: Scanning the original image of the ink imprint, and preprocessing the ink imprint scanned image to obtain a preprocessed imprint image; the preprocessing includes color model parameter adjustment, median filtering and binarization; Fitting the print contours corresponding to all the print areas in the print image, and generating an adjusted print contour in response to a user's dragging operation on the print contour; Taking all the adjusted imprint contours as a whole, fitting the minimum circumscribed polygon corresponding to the entire imprint contour, and automatically extracting the imprint geometric features; In response to the user's selection operation on the measuring point, the corresponding target measuring point is determined, and based on the minimum circumscribed polygon, the length of the imprint at the position where the target measuring point is located is calculated.

2. The method for identifying tire ink marks according to claim 1, characterized in that: The original image of the ink impression is scanned, and the scanned image of the ink impression is preprocessed to obtain a preprocessed impression image, specifically including: Acquire an original image of the ink impression, and scan the original image to obtain a corresponding ink impression scanned image; Performing color filtering on the ink print scanned image, and performing median filtering on the color filtered print image; The color-filtered and filtered impression image is binarized to obtain a preprocessed impression image.

3. The method for identifying tire ink marks according to claim 2, characterized in that: The ink print scanned image is subjected to color filtering, and the color filtered print image is subjected to median filtering, specifically comprising: Adjusting the model parameters in the color model corresponding to the ink imprint scanned image to perform color filtering on the ink imprint scanned image, and extracting the imprint image corresponding to the imprint area in the ink imprint scanned image after color filtering; Based on the filter kernel, a filter process is performed on the imprint area in the color filtered imprint image to remove image edge noise in the imprint image.

4. The method for identifying tire ink marks according to claim 1, characterized in that: After generating an adjusted imprint contour in response to a user's dragging operation on the imprint contour, the method further includes: Calculate the sum of the areas of the pixels of the grounded part corresponding to all the adjusted imprint contours to obtain the pixel grounded area of ​​the enclosed area corresponding to all the adjusted imprint contours; Acquire the actual paper area of ​​the paper corresponding to the ink print scan image, as well as the pixel paper length and pixel paper width corresponding to the paper, and calculate the pixel paper area corresponding to the paper according to the pixel paper length and the pixel paper width; A grounded paper area ratio between the pixel grounded area and the pixel paper area is determined, so as to calculate an actual grounded paper area corresponding to the ink imprint according to a product between the grounded paper area ratio and the actual paper area.

5. The method for identifying tire ink marks according to claim 4, characterized in that: After taking all the adjusted imprint contours as a whole and fitting the minimum circumscribed polygon corresponding to the entire imprint contour, the method further includes: Calculating the sum of the areas of the pixels of the print portion corresponding to the minimum circumscribed polygon to obtain the pixel print area corresponding to the entire print outline; An imprint-to-paper area ratio between the pixel imprint area and the pixel paper area is determined, so as to calculate an actual imprint area corresponding to the entire imprint contour according to a product between the imprint-to-paper area ratio and the actual paper area.

6. The method for identifying tire ink marks according to claim 1, characterized in that: After taking all the adjusted imprint contours as a whole and fitting the minimum circumscribed polygon corresponding to the entire imprint contour, the method further includes: Fitting the minimum circumscribed rectangle corresponding to the entire imprint contour, and determining the imprint length and imprint width of the entire imprint contour according to the length and width of the minimum circumscribed rectangle; Acquire the actual paper length and actual paper width of the paper corresponding to the ink imprint scan image, and determine the longitudinal position to be measured in the minimum circumscribed rectangle; Determine the pixel imprint length based on the line segment length between the intersection point of the straight line corresponding to the longitudinal position to be measured and the minimum circumscribed polygon; Determine an impression-to-paper length ratio between a pixel impression length and a pixel paper length, and determine an actual impression length corresponding to the entire impression contour according to a product of the impression-to-paper length ratio and an actual paper length; The horizontal side length of the minimum circumscribed rectangle is determined, and based on the horizontal side length, the actual impression width corresponding to the entire impression outline is determined.

7. A tire ink mark recognition method according to claim 6, characterized in that: After fitting the minimum circumscribed rectangle corresponding to the entire print contour, the method further includes: Identify the print contour in the minimum circumscribed rectangle, determine the coordinates corresponding to the leftmost endpoint and the rightmost endpoint of the print contour, and calculate the horizontal coordinate corresponding to the center position of all the print contours according to the horizontal coordinate of the leftmost endpoint and the horizontal coordinate of the rightmost endpoint to determine the length of the print at the center position; Based on the horizontal coordinate corresponding to the center position, the imprint length of the left end designated position and the imprint length of the right end designated position of all imprint contours are determined to calculate the sum of the corresponding imprint lengths of the left and right end designated positions, and based on the sum of the imprint length of the center position and the imprint lengths of the left and right end designated positions, the rectangular ratio corresponding to the entire imprint area is calculated.

8. The method for identifying tire ink marks according to claim 1, characterized in that: Fitting the imprint contours corresponding to all the imprint areas in the imprint image, and generating an adjusted imprint contour in response to a user's dragging operation on the imprint contour, specifically includes: Generating a transparent layer having the same size as the original image of the ink print, and superimposing the transparent layer on the original image; Fitting the imprint contour on the original image, and displaying the fitted imprint contour on the transparent layer; According to a preset division rule, the minimum circumscribed polygon is longitudinally divided into a plurality of longitudinal contours to obtain a corresponding plurality of equally divided points, and the plurality of equally divided points are inserted into a vertex coordinate set corresponding to the minimum circumscribed polygon; receiving a user's drag operation request for the imprint outline, and using all points in the vertex coordinate set as identification points of the drag operation request; In response to the drag operation request, an identification point corresponding to the drag operation request is determined, and a corresponding imprint contour is adjusted according to the identification point to generate an adjusted imprint contour.

9. A tire ink mark recognition device, characterized in that: The device comprises: at least one processor; and, a memory communicatively coupled to the at least one processor; The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the tire ink print recognition method as described in any one of claims 1-8.

10. A non-volatile computer storage medium storing computer executable instructions, characterized in that: When the computer executable instructions are executed, a tire ink print recognition method as described in any one of claims 1 to 8 is implemented.

Images