Automobile seat defect detection method, equipment and medium based on image recognition

Abstract

The present invention discloses a method, device and medium for detecting defects in automobile seats based on image recognition, and relates to the technical field of processing seat detection data, and comprises the following steps: obtaining a seat image, pre-processing the obtained seat image to obtain automobile seat detection data, wherein the seat detection data comprises safety performance data of the automobile seat, comfort performance data of the automobile seat and durability data of the automobile seat; constructing an automobile seat use defect objective function according to the obtained seat detection data to obtain a seat defect degree coefficient; comparing the obtained seat defect degree coefficient with a preset defect degree standard threshold to obtain a comparison result; and analyzing the obtained comparison result to obtain a defect degree category of the automobile seat surface.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle seat surface defect detection, and more specifically, to a vehicle seat defect detection method, equipment and medium based on image recognition. Background Art

[0002] With the continuous advancement of science and technology, automotive technology has experienced rapid development and has gone through many important milestones and technological innovations. With the advancement of automotive technology, such as electrification and the development of autonomous driving technology, seats not only need to provide comfort, but also need to meet more stringent safety standards, such as collision safety performance, passenger posture control, etc. The developing automotive technology and seat design require higher precision and quality control, which also promotes the development of seat surface defect detection technology.

[0003] As consumers pay more attention to the appearance and interior quality of cars, defects on the surface of seats, and surface defect detection of car seats are important steps to ensure the quality and appearance of seats. The quality and design of car seats directly affect the comfort and driving experience of passengers, and have an important impact on the brand image and market competitiveness of car manufacturers. Defects, stitching problems, etc. have become the focus of the public. However, the current car seat defect detection still requires manual operation and inspection, such as checking the data of pressure sensors or visual inspection results. At the same time, the existing detection technology has a single dimension, focusing only on defects on the surface of seats, such as damage or stains, and cannot detect physical defects due to the degree of use.

[0004] In view of the above problems, the present invention proposes a solution.

[0005] The present application provides a method, device and medium for detecting defects in automobile seats based on image recognition to perform multi-dimensional detection of automobile seats. The method can detect physical defects of automobile seats due to the degree of use. Summary of the invention

[0006] In order to overcome the above-mentioned defects of the prior art, the embodiments of the present invention provide a method, device and medium for detecting defects in automobile seats based on image recognition, which solve the problems raised in the above-mentioned background technology by processing seat detection data.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] In a preferred embodiment, the steps include: obtaining a seat picture, preprocessing the obtained seat picture to obtain car seat detection data, wherein the seat detection data includes car seat safety performance data, car seat comfort performance data and car seat durability data; constructing a car seat usage defect objective function based on machine learning according to the obtained seat detection data to obtain a seat defect degree coefficient; comparing the obtained seat defect degree coefficient with a preset defect degree standard threshold to obtain a comparison result; performing data analysis on the comparison result to obtain a defect degree category of the car seat surface.

[0009] In a preferred embodiment, the safety performance data of the automobile seat is obtained by: performing a stress analysis on the identified seat support points and seat fixing points, wherein the stress analysis includes the pressure and tension stress conditions when a collision occurs; based on the stress analysis, calculating the maximum strength of the seat support points and the seat fixing points for evaluating the safety performance of the automobile seat.

[0010] In a preferred embodiment, the comfort performance data of the automobile seat is obtained by the following method: based on the acquired seat picture, the shape of the seat cushion and backrest in the image is identified; the shape curves of the seat cushion and backrest and the angles at which these curves contact the human body are calculated to obtain the shape curve matching degree of the seat and the contact angle deviation between the seat and the human body, which are used to evaluate the comfort performance of the automobile seat.

[0011] In a preferred embodiment, the durability data of the car seat is obtained by the following method: the durability data of the car seat includes color balance parameters; the pressure level of the corresponding material of the car seat cushion is obtained, and different pressure compressions are applied to the cushion within the pressure level range, and comparison pictures before and after the pressure is applied are obtained, and the elastic compression length of each pressure compression is measured and recorded; the obtained seat picture is digitized according to the elastic compression length to obtain the color balance parameter.

[0012] In a preferred embodiment, the obtained seat defect degree coefficient is compared with a preset defect degree standard threshold, including: performing absolute value processing on the seat defect degree coefficient; comparing the seat defect degree coefficient obtained by using a defect objective function for the automobile seat with a preset defect degree standard threshold; if the seat defect degree coefficient is less than or equal to the preset defect degree standard threshold, the seat is considered to have no obvious defects and meet the conditions for use; when the seat defect degree coefficient is greater than the preset defect degree standard threshold, performing a damage analysis on the comparison result obtained.

[0013] In a preferred embodiment, when the seat defect degree coefficient is greater than the preset defect degree standard threshold, the comparison result is further analyzed, including: when the seat defect degree coefficient is greater than the preset defect degree standard threshold, the preset defect degree standard threshold is compared with the seat defect degree coefficient; when the ratio is between 1 and 0.75, the defect degree category of the car seat surface is slight damage; when the ratio is between 0.75 and between 0.75 and 0.3, the defect degree category of the car seat surface is moderate wear; when the ratio is less than 0.3, the defect degree category of the car seat surface is severe damage.

[0014] In a preferred embodiment, the device of the automobile seat defect detection method based on image recognition includes: an image collection module: responsible for collecting seat images required for automobile seat detection from different sources, including obtaining seat images from cameras, sensors or image databases; a data processing module: preprocessing the collected seat images to obtain seat detection data; a result output module: constructing an automobile seat usage defect objective function based on the obtained seat detection data, and the module outputs a seat defect degree coefficient; an analysis result module: comparing the defect degree coefficient in the seat detection data with a preset defect degree standard threshold, and analyzing the defect degree of each detected seat based on the comparison result, and classifying and evaluating according to preset standards; a result output module: based on the output of the analysis result module, presenting the obtained automobile seat surface defect degree category to a user or other system in a visual manner.

[0015] In a preferred embodiment, the electronic device includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the image recognition-based automobile seat defect detection method as described in any one of claims 1 to 7.

[0016] The technical effects and advantages of the automobile seat defect detection method, device and medium based on image recognition of the present invention are as follows:

[0017] 1. The present invention uses an automobile seat defect detection method based on image recognition to detect physical defects caused by the degree of seat usage, effectively solving the problem in the prior art that the detection technology has a single dimension and only focuses on defects on the seat surface but cannot detect physical defects caused by the degree of usage. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flow chart of the method for detecting defects of automobile seats based on image recognition according to the present invention;

[0019] Figure 2 It is a functional module diagram of a processing device of the automobile seat defect detection method based on image recognition of the present invention;

[0020] Figure 3 The present invention is a schematic diagram of the structure of an electronic device for implementing the method for detecting automobile seat defects based on image recognition.

[0021] The purpose of the present invention, its features and advantages will be described in detail with reference to the accompanying drawings in conjunction with the embodiments. DETAILED DESCRIPTION

[0022] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0023] Embodiment 1, Figure 1 A flow chart of the method for detecting defects in automobile seats based on image recognition of the present invention is given. In this embodiment, the method for detecting defects in automobile seats based on image recognition includes:

[0024] S1, obtaining a seat image, and preprocessing the obtained seat image to obtain automobile seat detection data, wherein the seat detection data includes safety performance data of the automobile seat, comfort performance data of the automobile seat, and durability data of the automobile seat;

[0025] S2, constructing the automobile seat use defect objective function based on the obtained seat inspection data, and obtaining the seat defect degree coefficient;

[0026] S3, comparing the obtained seat defect degree coefficient with a preset defect degree standard threshold to obtain a comparison result;

[0027] S4, analyzing the obtained comparison results to obtain the defect degree category of the automobile seat surface.

[0028] Obtaining the safety performance data of the car seat has the following importance:

[0029] By identifying the support points and fixing points in the seat structure, force analysis can be performed. This analysis can help evaluate the pressure and tension that the seat will withstand in a collision event. The safety performance data of the car seat is crucial for evaluating the stability, compression resistance and load-bearing capacity of the seat in an accident.

[0030] Obtaining the structural and mechanical performance data of the seat can directly affect the design and development process of the seat. Designers can use this data to optimize material selection, structural design and production process, thereby improving the safety and reliability of the seat;

[0031] In the automotive industry, the safety performance of seats needs to comply with strict regulations and standards. By obtaining and analyzing this data, automakers can ensure that their products meet regulatory requirements and successfully pass relevant safety certifications and tests. This data can also serve as an important basis for the production and sales of seat products, ensuring that the products can be recognized and widely accepted in the market.

[0032] The safety performance data of the automobile seat is obtained in the following manner:

[0033] Adjust the size of the acquired seat image and identify the positions of the seat support points and seat fixing points in the seat structure;

[0034] Performing force analysis on the identified seat support points and seat fixing points, wherein the force analysis includes the pressure and tension force when a collision occurs;

[0035] Based on the force analysis, calculate the maximum strength of the seat support points and seat fixing points.

[0036] The maximum strength of the seat support point and the seat fixing point is calculated as follows:

[0037]

[0038] Where: h is the yield strength of the material, H is the ultimate strength of the material, F is the force, and m is the effective cross-sectional area of ​​the support point and the fixed point.

[0039] Obtaining the comfort performance data of the automobile seat has the following importance:

[0040] The shape curve matching of the seat refers to the degree to which the curve design of the seat cushion and backrest matches the anatomical curve of the human body. By analyzing the shape of the seat in the image and the key contact points of the human body, it can be evaluated whether the seat design conforms to the principles of ergonomics. Such a highly matching seat can reduce discomfort during long-term driving and improve driving comfort and health;

[0041] The seat contact angle deviation describes the angle difference between the curve of the seat cushion and backrest and the contact surface of the human body in the seat design. This data can help designers adjust the seat's tilt angle, curve shape and support area to minimize pressure points or discomfort that may occur during driving, thereby improving the riding experience and comfort during long driving;

[0042] Based on the comfort performance data of car seats, designers can optimize the structure and material selection of seats according to different human body sizes, driving habits and usage environments. By ensuring that the shape of the seat matches the human anatomy, the driver's comfort and health can be improved, and physical fatigue or discomfort that may be caused by long-term driving can be reduced.

[0043] It should be noted that the key contact points of the human body include the waist, back, thigh support, etc.

[0044] The comfort performance data of the automobile seat is obtained in the following manner:

[0045] According to the acquired seat picture, the shape of the seat cushion and backrest in the image is identified; the shape curve of the seat cushion and backrest and the angle at which these curves contact the human body are calculated to obtain the shape curve matching degree of the seat and the contact angle deviation between the seat and the human body.

[0046] The shape curve matching degree of the seat and the contact angle deviation between the seat and the human body are calculated as follows:

[0047]

[0048]

[0049] Where: S is the matching degree of the shape curve of the seat, Q is the contact angle deviation between the seat and the human body, θ is the normal angle of the contact point between the human body and the seat, β is the normal angle of the corresponding point on the human body model, l is the standard curve of the human body model, c is the point distance between the seat shape curve and the human body model, and t is the index of the contact angle deviation between the seat and the human body.

[0050] Obtaining the durability data of the vehicle seat has the following importance:

[0051] By testing the compression and elastic recovery performance of seat materials, manufacturers can optimize the design to ensure that the seats maintain good support and comfort during long-term use, thereby improving the market competitiveness of the products;

[0052] The durability data of the seats can ensure the safety of passengers in unexpected situations and avoid potential safety hazards caused by seat failure. At the same time, high-quality seat design can also improve riding comfort and enhance the driving experience;

[0053] By digitally processing the color balance parameters obtained from the seat images, it is possible to ensure that the appearance of the seats remains consistent across different production batches and usage environments, thus enhancing the overall product's visual appeal and brand image.

[0054] The durability data of the automobile seat is obtained in the following manner:

[0055] The durability data of the automobile seat includes a color balance parameter;

[0056] Get the pressure level of the corresponding material of the car seat cushion, apply different pressure compressions to the seat cushion within the pressure level range, and obtain comparison pictures before and after the pressure is applied. Test Measure and record the elastic compression length for each pressure compression;

[0057] The acquired seat image is digitally processed according to the elastic compression length to obtain the color balance parameter.

[0058] The color balance parameter is calculated as follows:

[0059]

[0060] Where: N is the color balance parameter calculation formula, d is the elastic compression length of the seat, p is the hue of the seat picture, and j is the saturation of the seat picture.

[0061] The automobile seat uses a defect objective function, and the calculation formula is as follows:

[0062]

[0063] Where: Q is the objective function of automobile seat use defects, n is the contact angle deviation between the seat and the human body, y is the shape curve matching degree of the seat, c is the standard shape curve matching degree of the seat, s is the actual strength of the seat support point and the fixed point, s max is the maximum strength of the seat support and fixing points, m is the ideal value of the color balance parameter, and k is the actual color balance parameter.

[0064] It should be noted that by calculating the objective function, a numerical value can be obtained as the seat defect degree coefficient. The larger the seat defect degree coefficient, the more serious the seat defect is, and the smaller the seat defect degree coefficient, the less obvious the seat defect is.

[0065] The specific steps of comparing the obtained seat defect degree coefficient with the preset defect degree standard threshold are as follows:

[0066] The seat defect degree coefficient is set to an absolute value, and the preset defect degree standard threshold is 39;

[0067] Compare the seat defect degree coefficient obtained by the automobile seat use defect objective function with the preset defect degree standard threshold;

[0068] If the seat defect degree coefficient is less than or equal to the preset defect degree standard threshold, the seat is considered to have no obvious defects and meet the use conditions;

[0069] If the seat defect degree coefficient is greater than the preset defect degree standard threshold, the seat is considered to have a certain degree of defects and needs to be considered whether it needs to be repaired or replaced.

[0070] When the seat defect degree coefficient is greater than the preset defect degree standard threshold, a damage analysis is performed on the obtained comparison results, including:

[0071] The degree of defects on the surface of the car seat is classified into slight damage, moderate wear and severe damage;

[0072] Minor damage means that the defect does not affect the use of the seat system function and the user can continue to use the seat;

[0073] Moderate wear means that the defect has a certain degree of impact on the system function of the seat, causing some functions to not work properly or performance to decline;

[0074] Severe damage means the defect has completely impaired the seat's system functionality and requires immediate repair.

[0075] When the seat defect degree coefficient is greater than the preset defect degree standard threshold, the preset defect degree standard threshold is compared with the seat defect degree coefficient;

[0076] When the ratio is between 1 and 0.75, the defect level of the car seat surface is classified as slight damage;

[0077] When the ratio is 0.75 and between 0.75 and 0.3, the defect level of the car seat surface is moderate wear;

[0078] When the ratio is less than 0.3, the degree of defect on the surface of the car seat is classified as severe damage.

[0079] like Figure 2 The figure shows a functional module diagram of a seat detection data processing device. According to the functions to be implemented, the seat detection data processing device may include an image collection module, a data processing module, a result output module, and an analysis result module. The module described in the present invention may also be referred to as a unit, which refers to a series of computer program segments that can be executed by a processor of the seat detection data processing device and can complete fixed functions, which are stored in the memory of the seat detection data processing device.

[0080] In this embodiment, the functions of each module / unit are as follows:

[0081] Image collection module: responsible for collecting seat images required for car seat detection from different sources, including obtaining seat images from cameras, sensors or image databases;

[0082] Data processing module: pre-process the collected seat images to obtain seat detection data;

[0083] Result output module: constructs the automobile seat use defect objective function based on the seat inspection data, and the module outputs the seat defect degree coefficient;

[0084] Analysis result module: compares the defect degree coefficient in the seat inspection data with the preset defect degree standard threshold, and analyzes the defect degree of each detected seat according to the comparison result, and classifies and evaluates it according to the preset standard;

[0085] Result output module: Based on the output of the analysis result module, the defect degree category of the obtained car seat surface is presented to the user or other systems in a visual manner.

[0086] In detail, the modules described in the device of the method for detecting defects of automobile seats based on image recognition in the embodiment of the present invention adopt the same technical means as the method for detecting defects of automobile seats based on image recognition described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0087] like Figure 3 FIG. 1 is a schematic diagram of the structure of an electronic device for implementing the method for detecting defects of automobile seats based on image recognition according to the present invention.

[0088] The electronic device may include a processor, a memory, a communication bus, and a communication interface, and may also include a computer program stored in the memory and executable on the processor, such as a method for detecting defects in a car seat based on image recognition.

[0089] Among them, the processor is the control core (Control Unit) of the electronic device, which uses various interfaces and lines to connect the various components of the entire electronic device, and executes various functions of the electronic device and processes data by running or executing programs or modules stored in the memory and calling data stored in the memory.

[0090] The memory includes at least one type of readable storage medium, and in some embodiments, the memory may be an internal storage unit of the electronic device, such as a mobile hard disk of the electronic device. The memory may be used to store not only application software installed in the electronic device but also various data.

[0091] The communication bus is configured to realize connection and communication between the memory and at least one processor.

[0092] The communication interface is used for communication between the above electronic device and other devices, including a network interface and a user interface.

[0093] The figure only shows an electronic device with components. Those skilled in the art will understand that the structure shown in the figure does not constitute a limitation on the electronic device, and may include fewer or more components than shown in the figure, or combine certain components, or arrange the components differently.

[0094] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0095] The automobile seat surface defect detection method based on image recognition stored in the memory of the electronic device is a combination of multiple instructions. When running in the processor, the steps in the above-mentioned automobile seat surface defect detection method based on image recognition can be implemented.

[0096] Specifically, the specific implementation system of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0097] The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor of an electronic device, it can implement the steps in the above-mentioned image recognition-based automobile seat defect detection method.

[0098] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0099] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments may be implemented in whole or in part in the form of a computer program product.

[0100] Those of ordinary skill in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0101] In addition, each functional module in each embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.

[0102] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0103] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for detecting defects in automobile seats based on image recognition, characterized in that: The steps include: Acquire a seat image, and pre-process the acquired seat image to obtain automobile seat detection data, wherein the seat detection data includes safety performance data of the automobile seat, comfort performance data of the automobile seat, and durability data of the automobile seat; According to the obtained seat inspection data, the automobile seat use defect objective function is constructed based on machine learning to obtain the seat defect degree coefficient; Compare the obtained seat defect degree coefficient with a preset defect degree standard threshold to obtain a comparison result; Performing data analysis on the comparison results to obtain a defect degree category of the automobile seat surface; The automobile seat uses a defect objective function, and the calculation formula is as follows: Where: Q is the seat defect coefficient, n is the contact angle deviation between the seat and the human body, y is the shape curve matching degree of the seat, c is the standard shape curve matching degree of the seat, s is the actual strength of the seat support point and fixed point, s max is the maximum strength of the seat support and fixing points, m is the ideal value of the color balance parameter, and k is the actual color balance parameter.

2. The method for detecting defects in automobile seats based on image recognition according to claim 1, characterized in that: The safety performance data of the automobile seat is obtained in the following manner: The safety performance data include the maximum strength of the seat support points and the seat fixing points; Obtain seat support points and seat fixing points, and perform stress analysis; Based on the force analysis, calculate the maximum strength of the seat support points and seat fixing points.

3. The method for detecting defects in automobile seats based on image recognition according to claim 2, characterized in that: The comfort performance data of the automobile seat is obtained in the following manner: The comfort performance data of the automobile seat includes the shape curve matching degree of the seat and the contact angle deviation between the seat and the human body; According to the acquired seat image, a shape curve of a seat cushion backrest in the image is identified; The shape curve of the seat cushion backrest and the angle at which the curve contacts the human body are calculated to obtain the shape curve matching degree of the seat and the contact angle deviation between the seat and the human body.

4. The method for detecting defects in automobile seats based on image recognition according to claim 3 is characterized in that: The durability data of the automobile seat is obtained in the following manner: The durability data of the automobile seat includes a color balance parameter; Obtain the pressure level of the corresponding material of the car seat cushion, apply different pressure compressions to the seat cushion within the pressure level range, obtain comparison pictures before and after the pressure is applied, and measure and record the elastic compression length of each pressure compression; The acquired seat image is digitally processed according to the elastic compression length to obtain the color balance parameter.

5. The method for detecting defects in automobile seats based on image recognition according to claim 4, characterized in that: The step of comparing the obtained seat defect degree coefficient with a preset defect degree standard threshold comprises: Performing absolute value processing on the seat defect degree coefficient; Comparing the seat defect degree coefficient with a preset defect degree standard threshold; If the seat defect degree coefficient is less than or equal to the preset defect degree standard threshold, the seat is considered to have no obvious defects and meet the use conditions; When the seat defect degree coefficient is greater than the preset defect degree standard threshold, a damage analysis is performed on the obtained comparison results.

6. The method for detecting defects in automobile seats based on image recognition according to claim 5, characterized in that: When the seat defect degree coefficient is greater than the preset defect degree standard threshold, a damage analysis is performed on the obtained comparison result, including: When the seat defect degree coefficient is greater than the preset defect degree standard threshold, the preset defect degree standard threshold is compared with the seat defect degree coefficient; When the ratio is between 1 and 0.75, the defect level of the car seat surface is classified as slight damage; When the ratio is 0.75 and between 0.75 and 0.3, the defect level of the car seat surface is moderate wear; When the ratio is less than 0.3, the degree of defect on the surface of the car seat is classified as severe damage.

7. The device for detecting defects of automobile seats based on image recognition according to any one of claims 1 to 6, characterized in that: include: Image collection module: responsible for collecting seat images required for car seat detection from different sources, including obtaining seat images from cameras, sensors or image databases; Data processing module: pre-process the collected seat images to obtain seat detection data; Result output module: constructs the automobile seat use defect objective function based on the seat inspection data, and the module outputs the seat defect degree coefficient; Analysis result module: compares the defect degree coefficient in the seat inspection data with the preset defect degree standard threshold, and analyzes the defect degree of each detected seat according to the comparison result, and classifies and evaluates it according to the preset standard; Result output module: Based on the output of the analysis result module, the defect degree category of the obtained car seat surface is presented to the user or other systems in a visual manner.

8. An electronic device, characterized in that: The electronic device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the image recognition-based automobile seat defect detection method as described in any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for detecting defects in automobile seats based on image recognition as described in any one of claims 1 to 6 is implemented.

Images