Vehicle appearance part matching fillet detection method, vehicle and storage medium

Abstract

The invention relates to the technical field of vehicle design, and discloses a vehicle appearance part matching fillet detection method, a vehicle and a storage medium, and the vehicle appearance part matching fillet detection method comprises the steps: obtaining fillet parameters of two parts which are matched with each other; obtaining a visual score according to the fillet parameter; obtaining a touch score according to the fillet parameter; obtaining a region score according to the visual score and the touch score; and judging whether the area score is not less than a preset target value, and when the area score is not less than the preset target value, judging that the area score is qualified. According to the invention, for the detection of the matching fillets of the parts of the vehicle appearance, systematic scoring is carried out from visual sense and touch sense, the unification of detection standards is facilitated, the detection accuracy is improved, and the improvement and control of the matching fillets of the parts are better realized.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle design, and in particular to a method for detecting the rounded corners of vehicle appearance parts, a vehicle and a storage medium. Background Art

[0002] With the rapid development of the automobile industry, good appearance and exquisite perception have gradually become one of the important factors affecting users' purchasing desire. The rounded corners of automobile appearance are a common feature in the styling design process. The size of the rounded corners directly affects the exquisiteness of the entire vehicle. Too large rounded corners will make the product look rough, while too small rounded corners will affect visual and tactile perception. Therefore, the design of the rounded corners of automobile appearance needs to find a balance between the manufacturing process of parts and the appearance perception, so that the final product reflects the exquisite manufacturing process and high-quality appearance quality.

[0003] There are many types of fillets on the exterior of a vehicle, such as styling fillets and engineering fillets. After two parts are matched, there will be gaps or exposure between the fillets of the two parts, which will have a significant impact on the appearance of the two parts. Currently, the coordination between the two fillets is limited to subjective perception, and there is a lack of systematic testing and evaluation, which makes it difficult to unify the appearance of the matched fillets in different positions, ultimately having an adverse effect on the user's perspective and touch. Summary of the invention

[0004] The object of the present invention is to provide a method for detecting the fillet of vehicle appearance parts, a vehicle and a storage medium to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.

[0005] A method for detecting fillet matching of vehicle appearance parts according to an embodiment of the first aspect of the present invention includes: Get the fillet parameters of two mating parts; Obtaining a visual score based on the rounded corner parameter; Obtaining a tactile score according to the fillet parameter; Obtaining a regional score according to the visual score and the tactile score; It is determined whether the regional score is not less than a preset target value. When the regional score is not less than the preset target value, the regional score is determined to be qualified.

[0006] The technical solution has at least the following beneficial effects: when it is necessary to detect the fillet of parts in one area of ​​the vehicle, the fillets of the two mating parts in the area are analyzed visually and tactilely. Specifically, the fillet parameters of the two mating parts in the area are obtained, and visual and tactile scores are performed based on the fillet parameters, thereby obtaining the scores of the two mating areas. At this time, the area score is compared with a preset target value. The target value can be a historical value compared with itself, or an expected value that needs to be improved. When it is determined that the area score is not less than the preset target value, the area score is determined to be qualified, and the fillet detection of the two mating parts meets the standard. In this way, the detection of the fillet of parts on the vehicle appearance is systematically scored visually and tactilely, which is conducive to unifying the detection standards, improving the accuracy of detection, and better realizing the improvement and control of the fillet of parts.

[0007] According to some embodiments of the present invention, the fillet parameters include the outer diameter of the mating fillet, the distance between the root of the mating inner fillet and the straight line where the root of the mating outer fillet is located, and obtaining the fillet parameters of two mating parts includes: The outer diameter of the mating fillet, the distance between the root of the mating inner fillet and the straight line where the root of the mating outer fillet of the two mating parts are located are obtained respectively.

[0008] According to some embodiments of the present invention, obtaining a visual score according to the rounded corner parameter includes: Calculating the absolute value of the difference between the outer diameters of the two matching fillets to obtain a first absolute value; Compare the outer diameters of the two matching fillets, the distances between the two matching inner fillet roots and the straight line where the matching outer fillet roots are located, and obtain the fillet exposure state; Get the preset visual scoring model; A visual score is obtained from the visual score model according to the first absolute value and the rounded corner exposure state.

[0009] According to some embodiments of the present invention, the outer diameters of the two matching fillets are PR1 and PR2 respectively, and the distances between the two matching inner fillet roots and the straight lines where the matching outer fillet roots are located are D1 and D2 respectively, and the comparison of the values ​​of the sizes of the two matching fillet outer diameters and the distances between the two matching inner fillet roots and the straight lines where the matching outer fillet roots are located, and obtaining the fillet exposure state, includes: When PR1<PR2 and D1<D2, or PR1>PR2 and D1>D2, the rounded corner exposure state is a high exposure risk.

[0010] According to some embodiments of the present invention, when PR1≤PR2 and D1≥D2, or when PR1≥PR2 and D1≤D2, the rounded corner exposure state is a low exposure risk.

[0011] According to some embodiments of the present invention, obtaining a tactile score according to the fillet parameter includes: Calculating the absolute value of the difference between the outer diameters of the two matching fillets to obtain a second absolute value; Obtain a preset tactile scoring model; A tactile score is obtained from the tactile score model according to the second absolute value.

[0012] According to some embodiments of the present invention, obtaining a region score according to the visual score and the tactile score includes: Get the preset part attention level model; Obtaining a scoring coefficient from the part attention level model according to the two cooperating parts; According to the calculation formula The regional score is calculated, where Score the region. is the rating coefficient, For visual rating, Score the sense of touch.

[0013] According to some embodiments of the present invention, the present invention further comprises: Obtain multiple areas to be inspected on the vehicle appearance; Obtain two mutually matching parts at corresponding positions according to the plurality of areas to be detected; Repeat the steps of obtaining fillet parameters of two mating parts, obtaining a visual score according to the fillet parameters, obtaining a tactile score according to the fillet parameters, and obtaining a regional score according to the visual score and the tactile score; Calculate the vehicle appearance score based on the scores of the multiple areas; The whole vehicle appearance information is obtained according to the whole vehicle appearance score.

[0014] A vehicle according to an embodiment of the second aspect of the present invention is detected using the above method.

[0015] This technical solution has at least the following beneficial effects: the above method is used to detect the fillet of the parts on the vehicle, and systematic scoring is performed through vision and touch, which is conducive to unifying the detection standards, improving the accuracy of detection, and better realizing the improvement and control of the fillet of the parts. It can achieve comparative improvement of the appearance of the vehicle itself, and can also compare the differences between different models to improve the overall appearance of the vehicle.

[0016] According to a computer-readable storage medium of an embodiment of the third aspect of the present invention, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned vehicle appearance parts matching fillet detection method.

[0017] This technical solution has at least the following beneficial effects: since the computer-readable storage medium can execute the above-mentioned vehicle exterior parts fitting fillet detection method, the vehicle exterior parts fitting fillet detection can be systematically scored from a visual and tactile perspective, which is conducive to unifying the detection standards, improving the accuracy of detection, and better realizing the improvement and control of the parts fitting fillet.

[0018] Additional aspects and advantages of the present invention will be described in part in the following description and will be apparent from the following description. This disclosure may be apparent or learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly describes the drawings required for use in the description of the embodiments. Obviously, the drawings described are only part of the embodiments of the present invention, not all of the embodiments, and those skilled in the art can also obtain other design solutions and drawings based on these drawings without creative work.

[0020] Figure 1 It is a flow chart of the vehicle appearance parts matching fillet detection method of the present invention.

[0021] Figure 2 The present invention obtains a visual scoring flow chart based on the fillet parameters.

[0022] Figure 3 The present invention is a flow chart of obtaining a tactile scoring according to fillet parameters.

[0023] Figure 4 The fillet parameters of two mutually matching parts of the present invention are shown in FIG. Figure 1 .

[0024] Figure 5 The fillet parameters of two mutually matching parts of the present invention are shown in FIG. Figure 2 . DETAILED DESCRIPTION

[0025] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, and cannot be understood as limiting the present invention.

[0026] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0027] In the description of the present invention, "several" means one or more, "more" means more than two, "greater than", "less than", "exceed" etc. are understood as not including the number itself, and "above", "below", "within" etc. are understood as including the number itself. If there is a description of "first" or "second", it is only used for the purpose of distinguishing the technical features, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features or implicitly indicating the order of the indicated technical features.

[0028] In the description of the present invention, unless otherwise clearly defined, terms such as setting, installing, connecting, etc. should be understood in a broad sense, and technicians in the relevant technical field can reasonably determine the specific meanings of the above terms in the present invention based on the specific content of the technical solution.

[0029] Reference Figure 1 According to a first aspect of the present invention, a method for detecting the fillet of vehicle exterior parts includes but is not limited to the following steps: Step S100, obtaining the fillet parameters of two mating parts. For the mating fillets of two mating parts, the parameters such as the outer diameter, the distance between the inner and outer fillet roots, etc., will affect the visual effect of whether the fillets of the mating parts are exposed and the tactile effect of whether they are uncomfortable to the hand. Therefore, the fillet parameters of the two mating parts are obtained for subsequent visual and tactile evaluation.

[0030] Step S200, obtaining a visual score based on the fillet parameters. Gaps and exposure at the fillet positions of parts will affect the visual appearance. At this time, data is obtained from the fillet parameters, and the subjective visual appearance is quantitatively evaluated and analyzed through the data, which is conducive to unified guidance and control standards.

[0031] Step S300, obtaining a tactile score based on the fillet parameters. Whether the part matching position is sharp or uncomfortable will affect the tactile sense. Similarly, obtaining data from the fillet parameters at this time and quantitatively evaluating and analyzing the subjectively perceived tactile sense through the data is conducive to unified guidance and control standards.

[0032] Step S400, obtaining a regional score based on the visual score and the tactile score. By comprehensively analyzing the visual and tactile senses, unified comparative data, namely the regional score, is obtained. The regional score can be used for direct evaluation, comparative analysis, etc. of the fillet of the part fit.

[0033] Step S500, determine whether the regional score is not less than the preset target value. When the regional score is not less than the preset target value, execute step S600 to determine that the regional score is qualified. The detection of the fillet of the part can be based on different purposes, such as longitudinal comparison and improvement of itself, or horizontal comparison of different models. According to different purposes, different target values ​​can be preset for comparison with the regional score.

[0034] From the above, it can be seen that when it is necessary to detect the fillet of parts in one area of ​​the vehicle, the fillets of the two mating parts in this area are analyzed visually and tactilely. Specifically, the fillet parameters of the two mating parts in the area are obtained, and visual and tactile scores are performed based on the fillet parameters, thereby obtaining the scores of the two mating areas. At this time, the area score is compared with a preset target value. The target value can be a historical value compared with itself, or an expected value that needs to be improved. When it is determined that the area score is not less than the preset target value, the area score is determined to be qualified, and the fillet detection of the two mating parts meets the standards. In this way, the detection of the fillet of parts on the vehicle appearance is systematically scored visually and tactilely, which is conducive to unifying the detection standards, improving the accuracy of detection, and better realizing the improvement and control of the fillet of parts.

[0035] In step S100, the fillet parameters include the outer diameter of the mating fillet, the distance between the root of the mating inner fillet and the root of the mating outer fillet, and obtaining the fillet parameters of two mating parts includes but is not limited to the following steps: Get the outer diameter of the mating fillet, the distance between the root of the mating inner fillet and the straight line where the root of the mating outer fillet lies of the two mating parts respectively.

[0036] In this step S100, it is necessary to obtain the outer diameters of the fillets of the two mating parts on the mating side, that is, the outer diameter of the mating fillet, and for the fillets of the two mating parts, on the side of the mating connection, it is necessary to obtain the distance between the straight line where the inner fillet root and the outer fillet root are located, that is, the distance between the straight line where the mating inner fillet root and the mating outer fillet root are located, so as to be practical for subsequent visual and tactile scoring.

[0037] like Figure 2 As shown, in step S200, a visual score is obtained according to the rounded corner parameters, including but not limited to the following steps: Step S210, calculate the absolute value of the difference between the outer diameters of the two matching fillets to obtain the first absolute value. Determine whether the first absolute value is greater than 1. When the first absolute value is greater than 1, the final output of the visual score is defined as a low score interval; when the first absolute value is less than or equal to 1, the final output of the visual score is defined as a high score interval. The lower the interval, the lower the final visual score. Conversely, the higher the interval, the higher the final visual score. When the first absolute value is greater than 1, the final output visual score value still needs to be determined according to subsequent steps, but the score of the interval is lower; and when the first absolute value is less than or equal to 1, the final output visual score value also needs to be determined according to subsequent steps, but the score of the interval will be higher.

[0038] Step S220, compare the outer diameters of the two matching fillets, the distances between the two matching inner fillet roots and the straight line where the matching outer fillet roots are located, and obtain the fillet exposure state. The first absolute value can only be used to preliminarily determine the interval state of the visual score, so in this step, determine whether the fillet is exposed, whether there is a flange, whether the boundary is exposed, etc. The fillet exposure state can be further determined by the fillet exposure state. The score corresponding to the interval state can be further determined.

[0039] Step S230, obtaining a preset visual scoring model. The visual scoring model records the corresponding scores of different visual scores and different fillet exposure states, which can provide a scoring basis for the numerical results obtained in the above steps.

[0040] Step S240 , obtaining a visual score from a visual score model according to the first absolute value and the rounded corner exposure state.

[0041] like Figure 4 and Figure 5 As shown, the two matching fillet outer diameters are PR1 and PR2 respectively, and the distances between the two matching inner fillet roots and the straight line where the matching outer fillet roots are located are D1 and D2 respectively. When comparing, the same reference line must be used, and the reference line is not between the two inner fillet roots. For example, for parts A and B, the reference line can be the connecting line of the outer fillet roots of part A, or the connecting line of the outer fillet roots of part B. In step S220, the sizes of the two matching fillet outer diameters and the numerical values ​​of the distances between the two matching inner fillet roots and the straight line where the matching outer fillet roots are located are compared, and the fillet exposure state is obtained, including but not limited to the following steps: Step S221: When PR1<PR2 and D1<D2, or PR1>PR2 and D1>D2, the rounded corner exposure state is a high risk of exposure. At this time, the part boundary with a smaller rounded corner is in an exposed state, with the risk of flange or boundary exposure. Regardless of whether it is in the low score interval or the high score interval, the final score determined is the low score value of the interval.

[0042] Step S222: When PR1≤PR2 and D1≥D2, or when PR1≥PR2 and D1≤D2, the rounded corner exposure state is low exposure risk. At this time, the part with a smaller rounded corner has an inner boundary, and there is no risk of flange or border exposure. Regardless of whether it is in the low score interval or the high score interval, the final score determined is the high score value of the interval.

[0043] In summary of the above step S200, taking the outputted visual score of 1 to 4 as an example, the visual score is obtained from the visual score model according to the first absolute value and the rounded corner exposure state: When |PR1-PR2|>1, the final visual score output is in the low score range; when PR1<PR2 and D1<D2, or PR1>PR2 and D1>D2, the boundary of the part with smaller rounded corners is exposed, with the risk of flanging or boundary exposure, and the output visual score is 1 point; when PR1≤PR2 and D1≥D2, or PR1≥PR2 and D1≤D2, the boundary of the part with smaller rounded corners is hidden, without the risk of flanging or boundary exposure, and the output visual score is 2 points; When |PR1-PR2|≤1, the final visual score output is in the high score range; when PR1<PR2 and D1<D2, or PR1>PR2 and D1>D2, the boundary of the part with smaller rounded corners is exposed, and there is a risk of flanging or boundary exposure but it is not large, and the output visual score is 3 points; when PR1≤PR2 and D1≥D2, or PR1≥PR2 and D1≤D2, the boundary of the part with smaller rounded corners is hidden, and there is no risk of flanging or boundary exposure, and the output visual score is 4 points.

[0044] like Figure 3 As shown, in step S300, a tactile score is obtained according to the fillet parameter, including but not limited to the following steps: Step S310, calculate the absolute value of the difference between the outer diameters of the two matching fillets to obtain a second absolute value. Similarly, determine whether the second absolute value is greater than 1. When the second absolute value is greater than 1, the tactile score is finally output as a low score interval; when the second absolute value is less than or equal to 1, the tactile score is finally output as a high score interval. The lower the interval, the lower the final tactile score. Conversely, the higher the interval, the higher the final tactile score. When the second absolute value is greater than 1, the final tactile score value output at this time still needs to be determined according to subsequent steps, but the score of the interval is lower; and when the second absolute value is less than or equal to 1, the final tactile score value output also needs to be determined according to subsequent steps, but the score of the interval will be higher.

[0045] Step S320, obtaining a preset tactile scoring model. The tactile scoring model records the scores corresponding to different tactile scores, which can provide a scoring basis for the numerical results obtained in the above steps.

[0046] Step S330, obtaining a tactile score from a tactile score model according to the second absolute value. Taking a tactile score of 1 to 4 as an example: When |PR1-PR2|>1, it is necessary to further determine the values ​​of the two fillet values. When PR1<1mm or PR2<1mm, the part boundary has a high risk of scratching hands, and the output tactile score is 1 point; when PR1≥1mm and PR2≥1mm, the part boundary has a high risk of scratching hands, and the output tactile score is 2 points; When |PR1-PR2|≤1, it is necessary to further judge the size of the two fillet values. When PR1<1mm or PR2<1mm, there is a low scratch risk at the part boundary, and the output tactile score is 3 points; when PR1≥1mm and PR2≥1mm, there is no low scratch risk at the part boundary, and the output tactile score is 4 points.

[0047] In step S400, the region score is obtained according to the visual score and the tactile score, including but not limited to the following steps: Step S410, obtaining a preset part attention level model. Parts at different locations of the vehicle will have different levels of attention to the appearance of the vehicle. Some locations have a greater impact on the appearance of the vehicle, and the regional score obtained at this time needs to account for a larger weight. Conversely, locations with less impact on the appearance of the vehicle have a smaller weight for their regional score. For example: High concern level: headlights, hood, fenders, front bumpers, front doors, rear doors, front door frames, rear door frames, side and rear triangular windows, side lights, back door lights, back door, rear bumper, charging port cover or fuel filler cap, side panels, external opening handles, instrument panel, door guards, A-pillar upper guards, large screen, left lower guard periphery, right lower guard, glove box, and auxiliary instrument panel upper cover; Medium attention level: front windshield, side panel trim, rear windshield, side end panels of the sub-panel, sub-panel armrest, rear end panel, B-pillar guard plate; Low concern level: roof cover, front fog lamps, front door sills, rear door sills, rear fog lamps, front door sill trims, rear door sill trims, C-pillar guards, back door guards, back door sill trims.

[0048] Step S420, obtaining a scoring coefficient from the part attention level model according to the two mutually matched parts. Different attention levels can be preset to correspond to different scoring coefficients, for example, a scoring coefficient corresponding to a high attention level is 10 points, a scoring coefficient corresponding to a medium attention level is 5 points, and a scoring coefficient corresponding to a low attention level is 1 point.

[0049] Step S430, according to the calculation formula The regional score is calculated, where Score the region. is the rating coefficient, For visual rating, The visual score, tactile score and the scoring coefficient of the corresponding attention level of the part are input into this calculation formula to obtain the regional score.

[0050] The regional scoring is used to score the fillet of the parts at a single position in the whole vehicle. In practical applications, the appearance of the whole vehicle can also be analyzed by combining multiple regional scores. Therefore, the present invention also includes: Step S710, obtaining multiple areas to be inspected of the vehicle appearance that need to be inspected. For example, the locations listed in the above multiple different attention levels may be inspected.

[0051] Step S720, two mutually fitting parts at corresponding positions are obtained according to the plurality of areas to be inspected. In the area to be inspected, there are two parts that cooperate with each other to form a matching fillet, so the matching fillet to be inspected is determined.

[0052] Step S730, repeatedly obtain the fillet parameters of the two mating parts, obtain the visual score according to the fillet parameters, obtain the tactile score according to the fillet parameters, and obtain the regional score according to the visual score and the tactile score. Repeat steps S100 to S400 to obtain the regional score of the detection position.

[0053] Step S740, calculating the appearance score of the whole vehicle according to the multiple area scores. After the multiple area scores are superimposed, the appearance score of the whole vehicle can be obtained.

[0054] Step S750, obtaining the vehicle appearance information according to the vehicle appearance score. The higher the vehicle appearance score, the better the appearance of the matching fillet at each position of the vehicle. In actual production, when the vehicle appearance score is too low, it is necessary to improve the assembly and production processes at multiple positions of the vehicle.

[0055] A vehicle according to an embodiment of the second aspect of the present invention is obtained by detection using the above method. The vehicle can be a private car, such as a sedan, SUV, MPV or pickup truck. The vehicle can also be an operating vehicle, such as a van, bus, small truck or large trailer. The vehicle needs to have an electric motor that can output power or store mechanical energy as a generator. When the vehicle is a new energy vehicle, it can be a hybrid vehicle or a pure electric vehicle.

[0056] The above method is used to detect the fillet of the parts on the vehicle, and systematically score them through vision and touch, which is conducive to unifying the inspection standards, improving the accuracy of inspection, and better realizing the improvement and control of the fillet of the parts. It can also achieve comparative improvement of the appearance of the vehicle itself, and compare the differences between different models to improve the overall appearance of the vehicle.

[0057] According to a computer-readable storage medium of an embodiment of the third aspect of the present invention, the computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the above-mentioned vehicle appearance parts matching fillet detection method.

[0058] Since the computer-readable storage medium can execute the above-mentioned vehicle exterior parts fit fillet detection method, the vehicle exterior parts fit fillet detection can be systematically scored from the visual and tactile perspectives, which is conducive to unifying the detection standards, improving the accuracy of detection, and better realizing the improvement and control of the part fit fillet.

[0059] An embodiment of the present invention also provides a vehicle control device, including a memory, a processor, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the vehicle appearance parts matching fillet detection method of the above embodiment.

[0060] Take the example that the processor and memory in the vehicle control device can be connected through a bus. The memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transitory memory, such as at least one disk memory, a flash memory device, or other non-transitory solid-state storage device. In some embodiments, the memory may optionally include a memory remotely arranged relative to the control processor, and these remote memories may be connected to the control device via a network.

[0061] The non-transient software program and instructions required to implement the control method of the above embodiment are stored in the memory, and when executed by the processor, the vehicle appearance parts matching fillet detection method in the above embodiment is executed.

[0062] The device embodiments described above are merely illustrative, and the units described as separate components may or may not be physically separated, that is, they may be located in one place or distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0063] In addition, an embodiment of the present invention also provides a computer program product, including a computer program or computer instructions, the computer program or computer instructions are stored in a computer-readable storage medium, the processor of a computer device reads the computer program or computer instructions from the computer-readable storage medium, and the processor executes the computer program or computer instructions, so that the computer device executes the above-mentioned vehicle appearance parts matching fillet detection method.

[0064] It is worth noting that since the computer program product of the embodiment of the present invention can execute the vehicle appearance parts fitting rounded corner detection method of any of the above-mentioned embodiments, the specific implementation manner and technical effects of the computer program product of the embodiment of the present invention can refer to the specific implementation manner and technical effects of the vehicle appearance parts fitting rounded corner detection method of any of the above-mentioned embodiments.

[0065] It will be appreciated by those skilled in the art that all or some of the steps and systems in the methods disclosed above may be implemented as software, firmware, hardware, and appropriate combinations thereof. Some or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor, or a microprocessor, or as hardware, or as an integrated circuit, such as an application-specific integrated circuit. Such software may be distributed on a computer-readable medium, which may include a computer storage medium (or non-transitory medium) and a communication medium (or transient medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules, or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disk (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that can be used to store desired information and can be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically include computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0066] The preferred embodiments of the present invention are specifically described above, but the invention is not limited to the embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of this application.

Claims

1. A method for detecting the fillet of vehicle exterior parts, characterized in that: include: Get the fillet parameters of two mating parts; Obtaining a visual score based on the rounded corner parameter; Obtaining a tactile score according to the fillet parameter; Obtaining a regional score according to the visual score and the tactile score; It is determined whether the regional score is not less than a preset target value. When the regional score is not less than the preset target value, the regional score is determined to be qualified.

2. A method for detecting fillet of vehicle exterior parts according to claim 1, characterized in that: The fillet parameters include the outer diameter of the matching fillet, the distance between the root of the matching inner fillet and the straight line where the root of the matching outer fillet is located, and the method of obtaining the fillet parameters of two mutually matching parts includes: The outer diameter of the mating fillet, the distance between the root of the mating inner fillet and the straight line where the root of the mating outer fillet of the two mating parts are located are obtained respectively.

3. A method for detecting fillet corners of vehicle exterior parts according to claim 2, characterized in that: The step of obtaining a visual score according to the rounded corner parameter comprises: Calculating the absolute value of the difference between the outer diameters of the two matching fillets to obtain a first absolute value; Compare the outer diameters of the two matching fillets, the distances between the two matching inner fillet roots and the straight line where the matching outer fillet roots are located, and obtain the fillet exposure state; Get the preset visual scoring model; A visual score is obtained from the visual score model according to the first absolute value and the rounded corner exposure state.

4. A method for detecting fillet corners of vehicle exterior parts according to claim 3, characterized in that: The outer diameters of the two matching fillets are PR1 and PR2 respectively, and the distances between the two matching inner fillet roots and the straight lines where the matching outer fillet roots are located are D1 and D2 respectively. The comparison of the values ​​of the two matching fillet outer diameters and the distances between the two matching inner fillet roots and the straight lines where the matching outer fillet roots are located, and obtaining the fillet exposure state, includes: When PR1<PR2 and D1<D2, or PR1>PR2 and D1>D2, the rounded corner exposure state is a high exposure risk.

5. A method for detecting fillet corners of vehicle exterior parts according to claim 4, characterized in that: When PR1≤PR2 and D1≥D2, or when PR1≥PR2 and D1≤D2, the rounded corner exposure state is a low exposure risk.

6. A method for detecting fillet corners of vehicle exterior parts according to claim 2, characterized in that: The step of obtaining a tactile score according to the fillet parameter comprises: Calculating the absolute value of the difference between the outer diameters of the two matching fillets to obtain a second absolute value; Obtain a preset tactile scoring model; A tactile score is obtained from the tactile score model according to the second absolute value.

7. A vehicle exterior parts matching fillet detection method according to claim 1, characterized in that: The obtaining of a regional score according to the visual score and the tactile score comprises: Get the preset part attention level model; Obtaining a scoring coefficient from the part attention level model according to the two cooperating parts; According to the calculation formula The regional score is calculated, where Score the region. is the rating coefficient, For visual rating, Score the sense of touch.

8. A method for detecting fillet corners of vehicle exterior parts according to claim 1, characterized in that: Also includes: Obtain multiple areas to be inspected on the vehicle appearance; Obtain two mutually matching parts at corresponding positions according to the plurality of areas to be detected; Repeat the steps of obtaining fillet parameters of two mating parts, obtaining a visual score according to the fillet parameters, obtaining a tactile score according to the fillet parameters, and obtaining a regional score according to the visual score and the tactile score; Calculate the vehicle appearance score based on the scores of the multiple areas; The whole vehicle appearance information is obtained according to the whole vehicle appearance score.

9. A vehicle, characterized in that: The method for detecting fillet of vehicle appearance parts as claimed in any one of claims 1 to 8 is used for detection.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the vehicle appearance parts matching fillet detection method according to any one of claims 1 to 8.

Images