Airbag unfolding attitude analysis method

Abstract

The invention aims to provide an airbag unfolding attitude analysis method, which comprises the following steps of: S1) extracting an image, and extracting a shape attitude contour of each frame of an airbag from an airbag explosion unfolding image; s2) image recognition: processing each frame of appearance posture contour color image of the airbag to be recognized so as to obtain an outer contour line of the airbag; s3) performing quantitative calculation, performing Hu moment shape matching on the outer contour line of the air bag, calculating a Hu moment value and a phase angle difference value of the outer contour line of the air bag, and performing evaluation analysis; s4) statistical evaluation: performing result statistical display on the Hu moment value and the phase angle difference value of the outer contour line of the air bag; and S5) providing and displaying an interactive interface, providing an interactive interface, and displaying the statistical result of the step S4) on the interactive interface.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to an airbag deployment posture analysis method. Background Art

[0002] At present, most professional engineers cannot obtain the key information needed to judge the accuracy of simulation experiment benchmarking by relying only on experimental images and simulation animations. In this context, it is almost impossible to perform professional analysis on the posture of airbag deployment in each frame, mark the contour lines, and give specific evaluation values ​​of similarity frame by frame. The main difficulties are as follows:

[0003] 1) High skill requirements for manual work. Manual work not only needs to have rich simulation and experimental experience, but also needs to master image processing tools to perform labeling work.

[0004] 2) Analyze and compare pictures frame by frame. Currently, the animation of a single airbag explosion needs to be calculated for at least 100ms. The time and labor costs required to manually analyze pictures frame by frame are immeasurable. Analyzing hundreds of frames of pictures will cause visual fatigue, which seriously affects the accuracy of judgment.

[0005] 3) It is difficult to unify the judgment standards. Manual identification is very subjective, and there will be different understandings under the same standards. Everyone will have deviations in judging the accuracy of benchmarking analysis.

[0006] 4) It is difficult to give a quantitative value for similarity. It is difficult to give a specific numerical value for image similarity during manual recognition. We can only give a good or bad evaluation based on subjective feelings, without a specific standard to measure. Summary of the invention

[0007] To solve the above problems, the present application provides an airbag deployment posture analysis method that does not require human intervention and can quickly identify the outer contour lines of each frame of the airbag after it is deployed in the experimental image and the simulation animation, and automatically make a quantitative evaluation of the similarity between the two contour lines of each frame.

[0008] The present application provides an airbag deployment posture analysis method comprising:

[0009] S1) extracting images, extracting the shape and posture contour of each frame of the airbag from the image of the airbag being detonated and deployed;

[0010] S2) Image recognition, processing the contour color image of each frame of the airbag to be identified to obtain the outer contour line of the airbag;

[0011] S3) quantitative calculation, performing Hu rectangular matching on the outer contour of the airbag, calculating the Hu moment value and phase angle difference of the outer contour of the airbag and performing evaluation and analysis;

[0012] S4) statistical evaluation, performing statistical analysis on the Hu moment value and phase angle difference of the outer contour of the airbag;

[0013] S5) providing and displaying an interactive interface, providing an interactive interface and displaying the statistical results of step S4) on the interactive interface.

[0014] The step S2) further comprises:

[0015] S21) performing pre-simplification processing on the shape and posture contour color image of each frame of the airbag to be identified, removing pixel modules in the image that are not related to the airbag body, and obtaining a color image of the airbag body;

[0016] S22) converting the airbag main body color image into an HSV color image, filtering pixel points by saturation and brightness, removing interference from the airbag surface and surrounding shadow parts, and obtaining an airbag binary image;

[0017] S23) performing an opening operation on the binary image of the airbag to process the external noise points of the airbag main body, and then processing the internal noise points of the airbag by first inflating and then corroding, to obtain an image of the airbag main body;

[0018] S24) performing contour edge smoothing processing on the main image of the airbag, taking the middle value through median filtering, taking the average value through mean filtering, retaining pixel details through Gaussian filtering, and filtering from coarse to fine; and then protecting the boundary through bilateral filtering to obtain an airbag image with smooth and complete edges;

[0019] S25) performing contour recognition and extraction on the airbag image, automatically identifying the main contour through the area threshold, drawing the object target contour, and marking it in the original image to obtain a complete airbag outer contour line.

[0020] In the step S22), the upper and lower limit pixel value intervals of the specified pixel values ​​are lower_color=np.array([3,0,70]) and upper_color=np.array([179,85,255]).

[0021] The step S3) further comprises:

[0022] S31) performing shape matching on the Hu moment of the outer contour of the airbag, using the function cv2.matchShapes() to compare the Hu moments of the two images, wherein the cv2.matchShapes() function is a function in the OpenCV library for comparing the similarity between two shapes or contours;

[0023] S32) Obtain the phase angle difference of the outer contour line of the airbag, and analyze the phase angle difference of the outer contour line of the airbag.

[0024] When the output value of the function in step S31) is less than 0.1, the two pictures are highly similar; when the output value is greater than 1, the two pictures are not similar, and the Hu moment value of the airbag of each frame of the picture is obtained.

[0025] The phase angle difference acquisition method used in step S32) is as follows: first, the two airbag outer contour lines extracted in step S25) are scaled proportionally until they have the same standard resolution, and then one of the outer contour lines is rotated about the center point. When the overlapping area of ​​the two outer contour lines is the largest, the rotation angle of the outer contour line at this time is output, and the rotation angle is the phase angle difference between the two outer contour lines.

[0026] When the phase angle difference output in step S32) is less than 10 degrees, the two pictures are highly similar; when the phase angle difference output is greater than 30 degrees, the two pictures are not similar.

[0027] The step S4) further comprises:

[0028] S41) performing statistical display of the Hu moment value and the phase angle difference, drawing the quantitative evaluation results into a bar graph, a line graph, and a cotton swab graph, and obtaining a statistical graph of the quantitative evaluation results of frame-by-frame image comparison;

[0029] S42) automatically outputting the statistical graph of the frame-by-frame image comparison quantitative evaluation results and the identified airbag outer contour line into a PDF document, and automatically writing and generating a PDF file through docx2pdf;

[0030] The user interface in step S5) is designed using PyQt5.

[0031] The method further comprises a feedback step, which comprises: comparing the Hu moment value and the phase angle difference value of the airbag outer contour line with a preset qualification standard, and directly feeding back the comparison result in a visual form on the user interface. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A flowchart of a method for analyzing an airbag deployment posture preferably used in an embodiment of the present invention;

[0033] Figure 2 This is a preferred colored airbag deployment diagram to be identified in an embodiment of the present invention;

[0034] Figure 3 This is a preferred HSV color mode diagram of an airbag according to an embodiment of the present invention;

[0035] Figure 4 It is a binary image of an airbag after filtering pixels by saturation and brightness, which is preferred in the embodiment of the present invention;

[0036] Figure 5 The preferred embodiment of the present invention is an airbag binary image after noise point edge optimization;

[0037] Figure 6 A comparison diagram of the experimental and simulated airbag contour line markings preferred by the embodiment of the present invention;

[0038] Figure 7 A statistical diagram of the airbag similarity quantification evaluation results preferred in an embodiment of the present invention;

[0039] Figure 8 This is a user interface design effect diagram that is preferred for an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical scheme and advantages of the implementation of this application clearer, the technical scheme in the embodiment of this application will be described in more detail below in conjunction with the drawings in the embodiment of this application. In the drawings, the same or similar reference numerals represent the same or similar elements or elements with the same or similar functions. The described embodiments are part of the embodiments of this application, not all of them. The embodiments described below with reference to the drawings are exemplary and are intended to be used to explain this application, and cannot be understood as limiting this application. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application. In addition, it should be noted that, unless otherwise clearly specified and limited, the similar words such as "installation", "connection", "connection" used in the description of this application should be understood in a broad sense. For example, the connection can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected, it can be indirectly connected through an intermediate medium, or it can be the internal connection of two components. The technicians in the field can understand its specific meaning in this application according to the specific circumstances.

[0041] Some of the drawings in the present invention use color images, because there are many images in the drawings of the present invention that need to be distinguished in status, and the use of color images can better display different statuses, which is conducive to understanding the present invention.

[0042] The present invention provides an airbag deployment posture analysis method which does not require human intervention, can quickly identify the outer contour line of each frame of the airbag after it is deployed in the experimental image and the simulation animation, and automatically make a similarity quantitative evaluation between the two contour lines of each frame.

[0043] Figure 1FIG. 1 is a flowchart of a method for analyzing the posture of airbag deployment preferably used in an embodiment of the present invention. Figure 1 As shown, the present invention provides an airbag deployment posture analysis method comprising:

[0044] S1) extracting images, extracting the shape and posture contour of each frame of the airbag from the image of the airbag being detonated and deployed;

[0045] S2) Image recognition, processing the contour color image of each frame of the airbag to be identified to obtain the outer contour line of the airbag;

[0046] S3) quantitative calculation, performing Hu rectangular matching on the outer contour of the airbag, calculating the Hu moment value and phase angle difference of the outer contour of the airbag and performing evaluation and analysis;

[0047] S4) statistical evaluation, performing statistical analysis on the Hu moment value and phase angle difference of the outer contour of the airbag;

[0048] S5) providing and displaying an interactive interface, providing an interactive interface and displaying the statistical results of step S4) on the interactive interface.

[0049] Figure 2 This is a preferred colored airbag deployment diagram to be identified in an embodiment of the present invention. Figure 3 This is a preferred airbag HSV color mode diagram for an embodiment of the present invention. Figure 4 This is a preferred airbag binary image after saturation and brightness filtering of pixels in the embodiment of the present invention. Figure 5 This is an airbag binary image after noise point and edge optimization, which is preferred in the embodiment of the present invention. Figure 6 This is a comparison diagram of the experimental and simulated airbag contour line markings preferred in an embodiment of the present invention.

[0050] Figure 7 This is a statistical diagram of the airbag similarity quantification evaluation results preferred in an embodiment of the present invention. Figure 8 This is a user interface design effect diagram that is preferred for an embodiment of the present invention.

[0051] Figure 2 and Figure 6 The "4000fps" shown here means 4000 frames per second. "1280×1024" is the resolution of the image. "frame" means the number of frames. "frame:63" means the 63rd frame is displayed. "15.75ms" means the image is 15.75 milliseconds after the airbag is deployed. "test" means experiment. "simulation" means simulation.

[0052] Figure 7The "import and export chart" shown in the upper left corner of the chart shows the import and export chart. "Similarity Matching" means similarity graph matching. "experiment" means experiment. "simulation" means simulation. "matchshapes" means contour matching. "dif_angle" means angle difference. "max_iou" means maximum intersection-over-union ratio.

[0053] Figure 7 The “experimental and simulation airbag matching results” shown in the upper right corner of the graph represents the matching results of the experimental and simulation airbags.

[0054] Figure 7 The “max area similarity between experimental and simulation airbag” shown in the lower left corner of the graph indicates the maximum area similarity between the experimental and simulation airbags.

[0055] Figure 7 The “angle difference between experimental and simulation airbag” shown in the lower right corner of the graph shows the angle difference between the experimental and simulation airbags.

[0056] Figure 8The “Welcome to the image similarity matching program” shown means welcome to use the image similarity matching program. “The program is mainly applied to the similarity matching of experimental and, simulation images” means that the program is mainly used for the similarity comparison between experimental and simulation images. “The output value:similarity and Angledifference of twoimages” means the output value: the similarity and angular difference of the two images. “Auxiliary reference value:Maxintersection over union,contour area,perimeter” means the auxiliary reference value: maximum intersection over union, contour area, perimeter. “Before you start,you need to enter several sets of images to matchso that the program can identify them and the output address of the result” means that before you start, you need to enter several sets of images to matchso that the program can identify them and output the result address. “Address” means address. “input” means input. “Output” means output. “match” means match.

[0057] Combine the following Figures 1 to 8 The airbag deployment posture analysis method provided by the present invention is further described in detail.

[0058] Step S1) extracts the image, extracting the shape and posture contour of each frame from the image of the airbag being detonated and deployed.

[0059] Preferably, in step S1), the color image to be identified is pre-simplified to remove pixel modules irrelevant to the airbag body in the image to obtain a color image of the airbag body. Pre-processing will simplify subsequent identification operations.

[0060] Step S2) Image recognition, processing the contour color image of each frame of the airbag to be identified to obtain the outer contour line of the airbag.

[0061] Further, the color image of the airbag body is converted into an HSV color image, and the pixel points are filtered by saturation and brightness to obtain an airbag binary image. The upper and lower limits of the pixel value are preferably lower_color=np.array([3,0,70]) and upper_color=np.array([179,85,255]). The array lower_color=np.array([3,0,70]) defines the lower limit of the color range in the HSV color space. Specifically, it means that the lower limit of the hue is 3, the lower limit of the saturation is 0, and the lower limit of the brightness is 70. The array upper_color=np.array([179,85,255]) defines the upper limit of the color range in the HSV color space. Specifically. It means that the upper limit of the hue is 179, the upper limit of the saturation is 85, and the upper limit of the brightness is 255. These two arrays together define a color range in an HSV color space, which is used to filter out a specific color area from the image. In this preferred embodiment, these colors correspond to the airbag part in the image. For a grayscale image, its saturation is 0. Using this feature, in the HSV color space, by filtering pixels by saturation and brightness, the influence of shadow parts can be avoided.

[0062] Furthermore, the airbag binary image is opened to process the external noise of the airbag main part, and then the internal noise of the airbag is processed by first expanding and then corroding to obtain the airbag main image. The morphological opening operation can process the external noise of the main part of the airbag image, and then the internal noise is processed by first expanding and then corroding, thereby removing the shadow part of the airbag and the white gas released after the airbag is detonated.

[0063] Furthermore, the contour edge of the airbag main body image is smoothed by filtering from coarse to fine by using median filtering to obtain the middle value, mean filtering to obtain the average value, Gaussian filtering to retain pixel details; and then bilateral filtering to protect the boundary to obtain an airbag image with smooth and complete edges. The three steps of median, mean, and Gaussian filtering are filtered from coarse to fine to remove burrs and unnecessary miscellaneous lines on the outer contour line of the airbag main body; and then the outer contour line of the airbag main body is made smoother by using bilateral filtering.

[0064] Furthermore, the contour of the airbag image is identified and extracted, and the main contour is automatically identified through the area threshold. The object target contour is drawn and marked in the original image to obtain a complete airbag outer contour line.

[0065] Step S3) quantifies the calculation, performs Hu rectangular matching on the outer contour of the airbag, calculates the Hu moment value and phase angle difference of the outer contour of the airbag, and performs evaluation and analysis.

[0066] Preferably, the outer contour of the airbag is matched in a Hu rectangle. The Hu moment, also known as the Hu invariant moment, is a feature descriptor widely used in computer vision and image processing. It is achieved by calculating a specific type of moment in the image and constructing seven invariant moments, which have a certain invariance to the translation, rotation and scale change of the image. By calculating the Hu moment value of the outer contour of the airbag, a shape feature description of the contour can be obtained. These features do not depend on the size, direction or position of the contour, and are therefore suitable for shape recognition and matching. The function cv2.matchShapes() is used to compare the Hu moments of the two images. The cv2.matchShapes() function is a function in the OpenCV library for comparing the similarity between two shapes or contours. When the output value is less than 0.1, the two images are highly similar; when the output value is greater than 1, they are completely unrelated, and the Hu moment value of the airbag in each frame of the image is obtained.

[0067] Preferably, by scaling and rotating the contour lines in equal proportion, the rotation angle when the overlapping area of ​​the two contour lines is the largest is the angle difference between the two contour lines. When the output phase angle difference is less than 10 degrees, the two images are highly similar; when the output phase angle difference is greater than 30 degrees, they are completely unrelated, and the phase angle difference between the airbags in each frame of the image is obtained.

[0068] Preferably, the two extracted airbag contours are scaled to the same standard resolution, and then one of the contours is rotated about the center point. After cyclic calculation, when the overlapping area of ​​the two contours is the largest, the rotation angle at this time is output as the phase angle difference between the two contours. By judging the difference in rotation angles by the maximum area, the interference caused by the airbag contour being close to a circle can be avoided, making the result more accurate.

[0069] Step S4) Statistical evaluation is performed to perform statistical analysis on the Hu moment value and phase angle difference of the airbag outer contour line.

[0070] Preferably, the quantitative evaluation results are plotted into a bar graph, a line graph, or a cotton swab graph to obtain a statistical graph of the quantitative evaluation results of frame-by-frame image comparison.

[0071] Preferably, the statistical graph of the frame-by-frame image comparison quantitative evaluation results and the identified airbag outer contour line are automatically output into a PDF document, and the PDF file is automatically written and generated through docx2pdf.

[0072] Step S5) provides and displays an interactive interface, provides an interactive interface and displays the statistical results of step S4) on the interactive interface.

[0073] Preferably, the user interface is designed using PyQt5.

[0074] The present invention comprises a feedback step, which comprises: comparing the Hu moment value and the phase angle difference value of the airbag outer contour line with the preset qualified standard, and directly feeding back the comparison result in a visual form on the user interface.

[0075] The present invention has the following beneficial effects:

[0076] 1. The present invention provides an airbag deployment posture analysis method, which can quickly identify the outer contour line of each frame of the airbag after detonation without human intervention, thereby reducing labor costs.

[0077] 2. The airbag deployment posture analysis method of the present invention can automatically make a quantitative evaluation of the similarity between two contour lines in each frame, thereby reducing time cost and improving efficiency.

[0078] 3. The judgment criteria of the airbag deployment posture analysis method of the present invention are unified, and the benchmarking similarity between the experiment and the simulation model can be given more objectively, conveniently, quantitatively and accurately, thereby improving the benchmarking accuracy of the simulation and the experiment.

[0079] Those skilled in the art will appreciate that information, signals, and data may be represented using any of a variety of different technologies and techniques. For example, data, instructions, commands, information, signals, bits, symbols, and chips cited throughout the above description may be represented by voltage, current, electromagnetic waves, magnetic fields or magnetic particles, optical fields or optical particles, or any combination thereof.

[0080] Those skilled in the art will further appreciate that the various illustrative logic blocks, modules, circuits, and algorithm steps described in conjunction with the embodiments disclosed herein can be implemented as electronic hardware, computer software, or a combination of the two. To clearly illustrate this interchangeability of hardware and software, various illustrative components, boxes, modules, circuits, and steps are generally described above in the form of their functionality. Whether such functionality is implemented as hardware or software depends on the specific application and the design constraints imposed on the overall system. The technician can implement the described functionality in different ways for each specific application, but such implementation decisions should not be interpreted as resulting in a departure from the scope of the present application.

[0081] The various illustrative logic modules and circuits described in conjunction with the embodiments disclosed herein may be implemented or executed with a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof designed to perform the functions described herein. A general purpose processor may be a microprocessor, but in the alternative, the processor may be any conventional processor, controller, microcontroller, or state machine. The processor may also be implemented as a combination of computing devices, such as a combination of a DSP and a microprocessor, a plurality of microprocessors, one or more microprocessors in cooperation with a DSP core, or any other such configuration.

[0082] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be embodied directly in hardware, in a software module executed by a processor, or in a combination of the two. The software module may reside in a RAM memory, a flash memory, a ROM memory, an EPROM memory, an EEPROM memory, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art. An exemplary storage medium is coupled to a processor so that the processor can read and write information from / to the storage medium. In an alternative, a storage medium may be integrated into a processor. The processor and the storage medium may reside in an ASIC. The ASIC may reside in a user terminal. In an alternative, the processor and the storage medium may reside in a user terminal as discrete components.

[0083] In one or more exemplary embodiments, the functions described may be implemented in hardware, software, firmware, or any combination thereof. If implemented as a computer program product in software, each function may be stored on or transmitted by a computer-readable medium as one or more instructions or codes. Computer-readable media include both computer storage media and communication media, including any medium that facilitates the transfer of a computer program from one place to another. Storage media may be any available medium that can be accessed by a computer. As an example and not limitation, such a computer-readable medium may include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, disk storage or other magnetic storage device, or any other medium that can be used to carry or store the desired program code in the form of an instruction or data structure and can be accessed by a computer. Any connection is also properly referred to as a computer-readable medium. For example, if the software is transmitted from a website, a server, or other remote source using a coaxial cable, a fiber optic cable, a twisted pair, a digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwaves, the coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwaves are included in the definition of the medium. Disk and disc as used herein include compact disc (CD), laser disc, optical disc, digital versatile disc (DVD), floppy disk and Blu-ray disc, wherein disk often reproduces data magnetically, while disc reproduces data optically with lasers. Combinations of the above should also be included within the scope of computer-readable media.

[0084] The above-described embodiments are only further explanations of the present invention, and are not intended to limit the present invention in other forms. The present invention may also have other various embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art may make various corresponding modifications and changes according to the present invention, but these corresponding modifications and changes should all fall within the protection scope of the present invention.

Claims

1. A method for analyzing airbag deployment posture, characterized in that: include: S1) extracting images, extracting the shape and posture contour of each frame of the airbag from the image of the airbag being detonated and deployed; S2) Image recognition, processing the contour color image of each frame of the airbag to be identified to obtain the outer contour line of the airbag; S3) quantitative calculation, performing Hu rectangular matching on the outer contour of the airbag, calculating the Hu moment value and phase angle difference of the outer contour of the airbag and performing evaluation and analysis; S4) statistical evaluation, performing statistical analysis on the Hu moment value and phase angle difference of the outer contour of the airbag; S5) providing and displaying an interactive interface, providing an interactive interface and displaying the statistical results of step S4) on the interactive interface.

2. The airbag deployment posture analysis method according to claim 1, characterized in that: The step S2) further comprises: S21) performing pre-simplification processing on the shape and posture contour color image of each frame of the airbag to be identified, removing pixel modules in the image that are not related to the airbag body, and obtaining a color image of the airbag body; S22) converting the airbag main body color image into an HSV color image, filtering pixel points by saturation and brightness, removing interference from the airbag surface and surrounding shadow parts, and obtaining an airbag binary image; S23) performing an opening operation on the binary image of the airbag to process the external noise points of the airbag main body, and then processing the internal noise points of the airbag by first inflating and then corroding, to obtain an image of the airbag main body; S24) performing contour edge smoothing processing on the main image of the airbag, taking the middle value through median filtering, taking the average value through mean filtering, retaining pixel details through Gaussian filtering, and filtering from coarse to fine; and then protecting the boundary through bilateral filtering to obtain an airbag image with smooth and complete edges; S25) performing contour recognition and extraction on the airbag image, automatically identifying the main contour through the area threshold, drawing the object target contour, and marking it in the original image to obtain a complete airbag outer contour line.

3. The airbag deployment posture analysis method according to claim 2, characterized in that: In the step S22), the upper and lower limit pixel value intervals of the specified pixel values ​​are lower_color=np.array([3,0,70]) and upper_color=np.array([179,85,255]).

4. The airbag deployment posture analysis method according to claim 1, characterized in that: The step S3) further comprises: S31) performing shape matching on the Hu moment of the outer contour of the airbag, using the function cv2.matchShapes() to compare the Hu moments of the two images, wherein the cv2.matchShapes() function is a function in the OpenCV library for comparing the similarity between two shapes or contours; S32) Obtain the phase angle difference of the outer contour line of the airbag, and analyze the phase angle difference of the outer contour line of the airbag.

5. The airbag deployment posture analysis method according to claim 4, characterized in that: When the output value of the function in step S31) is less than 0.1, the two pictures are highly similar; when the output value is greater than 1, the two pictures are not similar, and the Hu moment value of the airbag of each frame of the picture is obtained.

6. The airbag deployment posture analysis method according to claim 2 or 4, characterized in that: The phase angle difference acquisition method used in step S32) is as follows: first, the two airbag outer contour lines extracted in step S25) are scaled proportionally until they have the same standard resolution, and then one of the outer contour lines is rotated about the center point. When the overlapping area of ​​the two outer contour lines is the largest, the rotation angle of the outer contour line at this time is output, and the rotation angle is the phase angle difference between the two outer contour lines.

7. The airbag deployment posture analysis method according to claim 4, characterized in that: When the phase angle difference output in step S32) is less than 10 degrees, the two pictures are highly similar; when the phase angle difference output is greater than 30 degrees, the two pictures are not similar.

8. The airbag deployment posture analysis method according to claim 1, characterized in that: The step S4) further comprises: S41) performing statistical display of the Hu moment value and the phase angle difference, drawing the quantitative evaluation results into a bar graph, a line graph, and a cotton swab graph, and obtaining a statistical graph of the quantitative evaluation results of frame-by-frame image comparison; S42) The statistical graph of the frame-by-frame image comparison quantitative evaluation result and the identified airbag outer contour line are automatically output into a PDF document, and the PDF file is automatically written and generated through docx2pdf.

9. The airbag deployment posture analysis method according to claim 1, characterized in that: The user interface in step S5) is designed using PyQt5.

10. The airbag deployment posture analysis method according to claim 1, characterized in that: The method further comprises a feedback step, which comprises: comparing the Hu moment value and the phase angle difference value of the airbag outer contour line with a preset qualification standard, and directly feeding back the comparison result in a visual form on the user interface.

Images