Method and system for detecting surface defects of automobile parts

Abstract

The invention discloses a surface defect detection method and system for an automobile part, and the method comprises the steps: defining a corresponding detection mode based on a three-dimensional model of an automobile and the model of the automobile, and carrying out the abnormality detection of the three-dimensional model of the automobile in the detection mode, so as to carry out the targeted detection of the three-dimensional model of the automobile. Further, defining a corresponding surface defect detection mode according to the component type of the automobile component and the abnormal type of the abnormal component, performing surface defect detection on the corresponding automobile component based on the surface defect detection mode, and defining surface defect elements according to the surface defect image; the overall defect grade of the automobile is defined based on the multiple surface defect elements of the different automobile parts, multi-dimensional control over the multiple surface defect elements of the different automobile parts is achieved, overall control is carried out based on the dimensions of the automobile parts and the dimensions of the surface defect elements, the surface defect detection precision of the automobile parts is improved, and the detection efficiency of the automobile parts is improved. And thus, the accuracy of the overall defect grade of the automobile is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of automobile parts, and in particular to a surface defect detection method and system for automobile parts. Background Art

[0002] With the development of science and technology, automobiles are widely used in people's lives. Surface defect detection is required during the production process of automobiles. In the existing technology, the model of the automobile is collected, and the corresponding surface defect detection method is matched according to the model of the automobile, and the overall detection is performed along the surface defect detection method. However, the automobile contains multiple automobile parts, and the multiple automobile parts are distributed in different positions of the automobile. The existing surface defect detection method only controls along the dimension of the model, which affects the surface defect detection accuracy of the automobile parts, thereby affecting the accuracy of the overall defect level of the automobile. Summary of the invention

[0003] The purpose of the present invention is to overcome the shortcomings of the prior art. The present invention provides a surface defect detection method and system for automobile parts, which collects the location and model of the automobile, defines a traversal mode according to the location and model of the automobile; triggers the traversal of the automobile along the traversal mode, and builds a three-dimensional model of the automobile; defines a corresponding detection method based on the three-dimensional model of the automobile and the model of the automobile, and performs abnormality detection on the three-dimensional model of the automobile along the detection method, so as to facilitate targeted detection of the three-dimensional model of the automobile, and fully considers the various automobile parts in the three-dimensional model of the automobile.

[0004] Furthermore, each abnormal part is defined based on abnormality detection of the three-dimensional model of the automobile; corresponding abnormal components are defined based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and the type of corresponding automobile components is defined based on the abnormal components; corresponding surface defect detection methods are defined according to the component types of automobile components and the abnormal types of abnormal components, surface defect detection is performed on corresponding automobile components based on the surface defect detection methods, surface defect elements are defined based on surface defect images, and the overall defect level of the automobile is defined based on multiple surface defect elements of different automobile components, thereby achieving multi-dimensional control of multiple surface defect elements of different automobile components, and overall control is performed based on the dimensions of automobile components and the dimensions of surface defect elements, thereby improving the surface defect detection accuracy of automobile components, and thereby improving the accuracy of the overall defect level of the automobile.

[0005] The embodiment of the present invention provides a surface defect detection method for automobile parts, which is applied to the surface defect detection scenario of automobile parts;

[0006] The surface defect detection method of the automobile parts comprises:

[0007] Collect the location and model of the car, and define the traversal mode according to the location and model of the car;

[0008] triggering the traversal of the car along the traversal mode and constructing a three-dimensional model of the car;

[0009] A corresponding detection method is defined based on the three-dimensional model of the car and the model of the car, and an abnormality detection is performed on the three-dimensional model of the car according to the detection method;

[0010] Defining each abnormal part according to abnormality detection of the three-dimensional model of the vehicle;

[0011] Defining corresponding abnormal parts based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and defining the type of corresponding automobile parts based on the abnormal parts;

[0012] A corresponding surface defect detection method is defined according to the type of automobile parts and the abnormal type of the abnormal part, surface defect detection is performed on the corresponding automobile parts based on the surface defect detection method, surface defect elements are defined according to the surface defect image, and the overall defect level of the automobile is defined based on multiple surface defect elements of different automobile parts.

[0013] Optionally, the collecting of the location of the car and the model of the car, and defining a traversal mode according to the location of the car and the model of the car, includes:

[0014] Locate the car to be detected and collect the location of the car;

[0015] Perform positioning detection based on the location of the car and define the posture of the car;

[0016] Defining a first parameter according to the position of the vehicle and the posture of the vehicle;

[0017] Collecting the model of the car, associating the model of the car with the location of the car, and defining a second parameter according to the model of the car and the location of the car;

[0018] The first parameter and the second parameter are associated, and a corresponding traversal mode is defined based on the first parameter, the second parameter, and the traversal matching table.

[0019] Optionally, triggering the traversal of the car along the traversal pattern and constructing a three-dimensional model of the car includes:

[0020] The traversal mode is frozen, and the traversal of the car is triggered along the traversal mode;

[0021] During the traversal process, corresponding dynamic shooting is performed at different positions of the car;

[0022] Collect multiple car images in different directions based on dynamic shooting of the car;

[0023] A plurality of stereo features are defined according to a plurality of car images in different directions, and the plurality of stereo features are distributed in different directions of the car;

[0024] A three-dimensional model of the car is constructed based on multiple three-dimensional features and the car model. At this time, a preliminary three-dimensional model is defined based on the synthesis of multiple three-dimensional features, and the three-dimensional model of the car is constructed based on the preliminary three-dimensional model and a reference model corresponding to the car model.

[0025] Optionally, defining a corresponding detection method based on the three-dimensional model of the car and the model of the car, and performing abnormality detection on the three-dimensional model of the car according to the detection method, includes:

[0026] freeze-frame car dioramas;

[0027] Defining detection coefficients based on a three-dimensional model of the vehicle and a model of the vehicle;

[0028] Define the corresponding detection method according to the detection coefficient and the corresponding detection method matching table;

[0029] Freeze the detection method;

[0030] Associating the three-dimensional model of the vehicle and the detection method, and defining a corresponding matching coefficient according to the three-dimensional model of the vehicle and the detection method;

[0031] Comparing the matching coefficient with a preset matching coefficient threshold, where the preset matching coefficient threshold corresponds to the model of the corresponding car;

[0032] If the matching coefficient is greater than a preset matching coefficient threshold, abnormality detection is performed on the three-dimensional model of the car according to the detection method.

[0033] Optionally, the step of defining each abnormal part according to abnormality detection of the three-dimensional model of the automobile includes:

[0034] freeze-frame car dioramas;

[0035] A plurality of sub-models are defined according to the division of the three-dimensional model of the car, and the plurality of sub-models are distributed at different positions of the car;

[0036] Associate multiple sub-models and corresponding detection methods;

[0037] Defining a plurality of sub-anomaly parts based on anomaly detection of a plurality of sub-models and corresponding detection methods;

[0038] In each sub-model, each sub-abnormal part constructs a corresponding abnormal part. In this case, there are multiple abnormal parts in the three-dimensional model of the car.

[0039] Optionally, the defining corresponding abnormal parts based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and defining the type of the corresponding automobile part based on the abnormal parts, includes:

[0040] Freeze each abnormal part and mark the corresponding position;

[0041] defining an anomaly contour based on the identification of each anomaly portion;

[0042] The corresponding abnormal area is defined according to the abnormal contour and the corresponding position.

[0043] Optionally, the defining corresponding abnormal parts based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and defining the type of the corresponding automobile part based on the abnormal parts, further includes:

[0044] Correlate the three-dimensional model of each abnormal area and the car;

[0045] Defining corresponding abnormal parts according to each abnormal area and the three-dimensional model of the car;

[0046] The type of the corresponding automobile part is defined based on the abnormal part and the automobile structure classification table.

[0047] Optionally, the method of defining a corresponding surface defect detection method according to the type of automobile parts and the abnormal type of abnormal parts, performing surface defect detection on the corresponding automobile parts based on the surface defect detection method, defining surface defect elements according to the surface defect image, and defining the overall defect level of the automobile based on multiple surface defect elements of different automobile parts includes:

[0048] Associate the component types of the automobile components and the abnormal types of the abnormal components;

[0049] The corresponding surface defect detection method is defined according to the component type of the automobile component and the abnormal type of the abnormal component. At this time, the corresponding surface defect detection method is matched based on different automobile components.

[0050] Optionally, the method of defining a corresponding surface defect detection method according to the component type of the automobile component and the abnormal type of the abnormal component, performing surface defect detection on the corresponding automobile component based on the surface defect detection method, defining surface defect elements according to the surface defect image, and defining the overall defect level of the automobile based on multiple surface defect elements of different automobile components, further includes:

[0051] Performing surface defect detection on corresponding automobile parts based on the surface defect detection method;

[0052] Collecting corresponding surface defect images according to surface defect detection of automobile parts;

[0053] Define corresponding surface defect elements based on each surface defect image;

[0054] Multiple surface defect elements are distributed in a three-dimensional model of a car, and defect levels of different car parts are defined based on the multiple surface defect elements of different car parts. A defect level set is constructed according to the defect levels of each car part, and the overall defect level of the car is defined based on the defect level set.

[0055] In addition, an embodiment of the present invention further provides a surface defect detection system for automobile parts, the surface defect detection system for automobile parts comprising:

[0056] A collection module is used to collect the location of the car and the model of the car, and define a traversal mode according to the location of the car and the model of the car;

[0057] A three-dimensional model module, used for triggering the traversal of the car along the traversal mode and building a three-dimensional model of the car;

[0058] An anomaly detection module, used to define a corresponding detection method based on the three-dimensional model of the car and the model of the car, and perform anomaly detection on the three-dimensional model of the car according to the detection method;

[0059] An abnormal part module, for defining each abnormal part according to abnormality detection of the three-dimensional model of the car;

[0060] An automobile component module, used for defining corresponding abnormal components based on each abnormal part, a corresponding position and a three-dimensional model of the automobile, and defining the type of corresponding automobile components based on the abnormal components;

[0061] The defect module is used to define corresponding surface defect detection methods according to the types of automobile parts and the abnormal types of abnormal parts, perform surface defect detection on corresponding automobile parts based on the surface defect detection methods, define surface defect elements according to surface defect images, and define the overall defect level of the automobile based on multiple surface defect elements of different automobile parts.

[0062] In an embodiment of the present invention, through the method in the embodiment of the present invention, the location of the car and the model of the car are collected, and a traversal mode is defined according to the location of the car and the model of the car; the traversal of the car is triggered along the traversal mode, and a three-dimensional model of the car is constructed; a corresponding detection method is defined based on the three-dimensional model of the car and the model of the car, and the three-dimensional model of the car is detected for abnormalities along the detection method, so as to facilitate targeted detection of the three-dimensional model of the car, and fully consider the various different car parts in the three-dimensional model of the car.

[0063] Furthermore, each abnormal part is defined based on abnormality detection of the three-dimensional model of the automobile; corresponding abnormal components are defined based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and the type of corresponding automobile components is defined based on the abnormal components; corresponding surface defect detection methods are defined according to the component types of automobile components and the abnormal types of abnormal components, surface defect detection is performed on corresponding automobile components based on the surface defect detection methods, surface defect elements are defined based on surface defect images, and the overall defect level of the automobile is defined based on multiple surface defect elements of different automobile components, thereby achieving multi-dimensional control of multiple surface defect elements of different automobile components, and overall control is performed based on the dimensions of automobile components and the dimensions of surface defect elements, thereby improving the surface defect detection accuracy of automobile components, and thereby improving the accuracy of the overall defect level of the automobile. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 is a schematic flow chart of a surface defect detection method for automobile parts in an embodiment of the present invention;

[0066] Figure 2 is a schematic flow chart of S11 in the surface defect detection method for automobile parts in an embodiment of the present invention;

[0067] Figure 3 is a schematic flow chart of S12 in the surface defect detection method for automobile parts in an embodiment of the present invention;

[0068] Figure 4 is a schematic flow chart of S13 in the surface defect detection method for automobile parts in an embodiment of the present invention;

[0069] Figure 5 is a schematic flow chart of S14 in the surface defect detection method for automobile parts in an embodiment of the present invention;

[0070] Figure 6 is a schematic flow chart of S15 in the surface defect detection method for automobile parts in an embodiment of the present invention;

[0071] Figure 7 is a schematic flow chart of S16 in the surface defect detection method for automobile parts in an embodiment of the present invention;

[0072] Figure 8Schematic diagram of the structure of the surface defect detection system for automobile parts in an embodiment of the present invention;

[0073] Fig. 9 The figure is a hardware diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0074] 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.

[0075] See also Figures 1 to 9 , a surface defect detection method for automobile parts, applied to the surface defect detection scene of automobile parts; the surface defect detection method for automobile parts includes:

[0076] Step S11: collecting the location of the car and the model of the car, and defining a traversal mode according to the location of the car and the model of the car;

[0077] Step S12: triggering the traversal of the car along the traversal pattern, and constructing a three-dimensional model of the car;

[0078] Step S13: defining a corresponding detection method based on the three-dimensional model of the car and the model of the car, and performing abnormality detection on the three-dimensional model of the car according to the detection method;

[0079] Step S14: defining each abnormal part according to abnormality detection of the three-dimensional model of the car;

[0080] Step S15: defining corresponding abnormal parts based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and defining the type of corresponding automobile parts based on the abnormal parts;

[0081] Step S16: Define corresponding surface defect detection methods according to the types of automobile parts and the abnormal types of abnormal parts, perform surface defect detection on corresponding automobile parts based on the surface defect detection methods, define surface defect elements according to surface defect images, and define the overall defect level of the automobile based on multiple surface defect elements of different automobile parts.

[0082] In an embodiment of the present invention, through the method in the embodiment of the present invention, the location of the car and the model of the car are collected, and a traversal mode is defined according to the location of the car and the model of the car; the traversal of the car is triggered along the traversal mode, and a three-dimensional model of the car is constructed; a corresponding detection method is defined based on the three-dimensional model of the car and the model of the car, and the three-dimensional model of the car is detected for abnormalities along the detection method, so as to facilitate targeted detection of the three-dimensional model of the car, and fully consider the various different car parts in the three-dimensional model of the car.

[0083] Furthermore, each abnormal part is defined based on abnormality detection of the three-dimensional model of the automobile; corresponding abnormal components are defined based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and the type of corresponding automobile components is defined based on the abnormal components; corresponding surface defect detection methods are defined according to the component types of automobile components and the abnormal types of abnormal components, surface defect detection is performed on corresponding automobile components based on the surface defect detection methods, surface defect elements are defined based on surface defect images, and the overall defect level of the automobile is defined based on multiple surface defect elements of different automobile components, thereby achieving multi-dimensional control of multiple surface defect elements of different automobile components, and overall control is performed based on the dimensions of automobile components and the dimensions of surface defect elements, thereby improving the surface defect detection accuracy of automobile components, and thereby improving the accuracy of the overall defect level of the automobile.

[0084] refer to Figure 2 , in step S11, the location of the car and the model of the car are collected, and a traversal mode is defined according to the location of the car and the model of the car;

[0085] In the specific implementation process of the present invention, the specific steps may be:

[0086] S111: Locate the car to be detected and collect the location of the car;

[0087] S112: Performing positioning detection based on the location of the car and defining the posture of the car;

[0088] S113: defining a first parameter according to the position of the vehicle and the posture of the vehicle;

[0089] S114: collecting the model of the car, associating the model of the car with the location of the car, and defining a second parameter according to the model of the car and the location of the car;

[0090] S115: Associating the first parameter with the second parameter, and defining a corresponding traversal mode based on the first parameter, the second parameter and the traversal matching table.

[0091] In an embodiment of the present application, the car to be detected is located, and the position of the car is collected, and further information is obtained regarding the position of the car, so that positioning detection is performed based on the position of the car, and the posture of the car is defined, thereby introducing the position of the car and the corresponding posture.

[0092] Furthermore, the position of the car and the corresponding posture are associated, so that the first parameter is defined according to the position of the car and the posture of the car, which is compatible with the overall consideration of the position of the car and the corresponding posture and ensures the accuracy of the first parameter.

[0093] At the same time, the model of the car is collected and associated with the model of the car and the location of the car, and the second parameter is defined based on the model of the car and the location of the car, which is compatible with the overall consideration of the model of the car and the location of the car and ensures the accuracy of the second parameter.

[0094] Therefore, the first parameter and the second parameter are associated, and a corresponding traversal mode is defined based on the first parameter, the second parameter and the traversal matching table. The first parameter, the second parameter and the traversal matching table are introduced to achieve multi-dimensional control of the first parameter, the second parameter and the traversal matching table, thereby ensuring the accuracy of the traversal mode. Optionally, the traversal mode includes overall traversal or local traversal.

[0095] refer to Figure 3 , in step S12, triggering the traversal of the car along the traversal pattern, and constructing a three-dimensional model of the car;

[0096] In the specific implementation process of the present invention, the specific steps may be:

[0097] S121: freeze the traversal pattern, and trigger the traversal of the vehicle along the traversal pattern;

[0098] S122: performing corresponding dynamic shooting of different positions of the vehicle during the traversal process;

[0099] S123: collecting multiple images of the car in different directions based on the dynamic shooting of the car;

[0100] S124: defining a plurality of three-dimensional features according to the plurality of car images in different directions, wherein the plurality of three-dimensional features are distributed in different directions of the car;

[0101] S125: Constructing a three-dimensional model of the car based on multiple three-dimensional features and the car model. At this time, a preliminary three-dimensional model is defined based on the synthesis of multiple three-dimensional features, and the three-dimensional model of the car is constructed based on the preliminary three-dimensional model and a reference model corresponding to the car model.

[0102] In an embodiment of the present application, the traversal mode is frozen and the traversal of the car is triggered along the traversal mode to realize the traversal of the car. At this time, corresponding dynamic photography is performed on different directions of the car during the traversal process, so as to collect multiple car images in different directions based on the dynamic photography of the car, thereby realizing the dynamic photography of the car and ensuring the correspondence of multiple car images in different directions, so as to facilitate further processing of the multiple car images.

[0103] Therefore, multiple stereo features are defined according to multiple car images in different directions, and the multiple stereo features are distributed in different directions of the car; a three-dimensional model of the car is constructed based on the multiple stereo features and the model of the car. At this time, a preliminary three-dimensional model is defined based on the synthesis of the multiple stereo features, and the three-dimensional model of the car is constructed according to the preliminary three-dimensional model and a reference model corresponding to the model of the car. The preliminary three-dimensional model is further controlled, and the overall consideration of the preliminary three-dimensional model and the reference model corresponding to the model of the car is compatible, thereby ensuring the accuracy of the three-dimensional model of the car.

[0104] refer to Figure 4 , in step S13, a corresponding detection method is defined based on the three-dimensional model of the car and the model of the car, and abnormality detection is performed on the three-dimensional model of the car along the detection method;

[0105] In the specific implementation process of the present invention, the specific steps may be:

[0106] S131: freeze-frame car stereo model;

[0107] S132: defining a detection coefficient based on a three-dimensional model of the car and a model of the car;

[0108] S133: defining a corresponding detection method according to the detection coefficient and a corresponding detection method matching table;

[0109] S134: freeze the detection method; associate the three-dimensional model of the car with the detection method, and define a corresponding matching coefficient according to the three-dimensional model of the car and the detection method;

[0110] S135: comparing the matching coefficient with a preset matching coefficient threshold, where the preset matching coefficient threshold corresponds to the model of the corresponding car;

[0111] S136: If the matching coefficient is greater than a preset matching coefficient threshold, abnormality detection is performed on the three-dimensional model of the automobile according to the detection method.

[0112] In an embodiment of the present application, the location of the car and the model of the car are collected, and a traversal pattern is defined according to the location of the car and the model of the car; the traversal of the car is triggered along the traversal pattern, and a three-dimensional model of the car is constructed; a corresponding detection method is defined based on the three-dimensional model of the car and the model of the car, and the three-dimensional model of the car is detected for abnormalities along the detection method, so as to facilitate targeted detection of the three-dimensional model of the car, and fully consider the various different car parts in the three-dimensional model of the car.

[0113] At this time, freeze the three-dimensional model of the car, further control the three-dimensional model of the car, associate the three-dimensional model of the car and the model of the car, and define the detection coefficient based on the three-dimensional model of the car and the model of the car. Perform multi-dimensional control on the three-dimensional model of the car and the model of the car to ensure the accuracy of the detection coefficient, and further process the detection coefficient.

[0114] Furthermore, a corresponding detection method is defined according to the detection coefficient and the corresponding detection method matching table, and matching is performed on the detection coefficient and the corresponding detection method matching table, thereby ensuring the accuracy of the detection method.

[0115] Therefore, the detection method is fixed; the three-dimensional model of the car and the detection method are associated, and the corresponding matching coefficient is defined according to the three-dimensional model of the car and the detection method, and the matching coefficient is introduced. The matching coefficient is further controlled, and at the same time, the matching coefficient is compared with the preset matching coefficient threshold. At this time, the preset matching coefficient threshold corresponds to the corresponding car model; if the matching coefficient is greater than the preset matching coefficient threshold, the three-dimensional model of the car is detected for abnormalities along the detection method, which ensures the targeted detection of the three-dimensional model and the accuracy of abnormality detection of the three-dimensional model of the car.

[0116] refer to Figure 5 , S14: defining each abnormal part according to abnormality detection of the three-dimensional model of the car;

[0117] In the specific implementation process of the present invention, the specific steps may be:

[0118] S141: Freeze-frame car diorama;

[0119] S142: defining a plurality of sub-models according to the division of the three-dimensional model of the automobile, wherein the plurality of sub-models are distributed at different positions of the automobile;

[0120] S143: Associating multiple sub-models and corresponding detection methods;

[0121] S144: defining a plurality of sub-abnormal parts based on the abnormality detection of the plurality of sub-models and the corresponding detection methods;

[0122] S145: In each sub-model, each sub-abnormal part constructs a corresponding abnormal part. At this time, there are multiple abnormal parts in the three-dimensional model of the car.

[0123] In an embodiment of the present application, the three-dimensional model of the car is frozen, and the three-dimensional model of the car is further processed. At this time, multiple sub-models are defined according to the division of the three-dimensional model of the car. The multiple sub-models are distributed in different positions of the car. Multiple sub-models and corresponding detection methods are introduced, thereby associating the multiple sub-models and the corresponding detection methods, thereby ensuring targeted control of the multiple sub-models and the corresponding detection methods.

[0124] Therefore, based on the abnormal detection of multiple sub-models and corresponding detection methods, multiple sub-abnormal parts are defined, and multi-dimensional control is performed on the abnormal detection of multiple sub-models and corresponding detection methods, thereby introducing multiple sub-abnormal parts and realizing targeted control of multiple sub-abnormal parts. At the same time, in each sub-model, each sub-abnormal part constructs a corresponding abnormal part, and there are multiple abnormal parts in the three-dimensional model of the car, and multi-dimensional control is performed on the multiple abnormal parts.

[0125] refer to Figure 6 , S15: defining corresponding abnormal parts based on each abnormal part, the corresponding position and the three-dimensional model of the car, and defining the type of the corresponding car part based on the abnormal parts;

[0126] In the specific implementation process of the present invention, the specific steps may be:

[0127] S151: freeze each abnormal part and mark the corresponding position;

[0128] S152: defining an abnormal contour based on the identification of each abnormal part;

[0129] S153: defining a corresponding abnormal area according to the abnormal contour and the corresponding position;

[0130] S154: Associating each abnormal area with the three-dimensional model of the car;

[0131] S155: defining corresponding abnormal parts according to each abnormal area and the three-dimensional model of the car;

[0132] S156: Based on the abnormal component and the automobile structure classification table, the type of the corresponding automobile component is defined.

[0133] In the embodiment of the present application, each abnormal part is frozen and the corresponding position is marked, each abnormal part and the corresponding position are introduced, so that an abnormal contour is defined based on the identification of each abnormal part, and a corresponding abnormal contour is introduced.

[0134] Furthermore, corresponding abnormal areas are defined according to abnormal contours and corresponding positions, and overall control is performed on the abnormal contours and corresponding positions. At the same time, association is made between each abnormal area and the three-dimensional model of the car; corresponding abnormal parts are defined according to each abnormal area and the three-dimensional model of the car; and corresponding types of automobile parts are defined based on the abnormal parts and the structural classification table of the car, thereby ensuring the accuracy of the types of automobile parts and realizing multi-dimensional control of each abnormal area, the three-dimensional model of the car and the structural classification table of the car.

[0135] refer to Figure 7 , S16: defining a corresponding surface defect detection method according to the component type of the automobile component and the abnormal type of the abnormal component, performing surface defect detection on the corresponding automobile component based on the surface defect detection method, defining surface defect elements according to the surface defect image, and defining the overall defect level of the automobile based on multiple surface defect elements of different automobile components;

[0136] In the specific implementation process of the present invention, the specific steps may be:

[0137] S161: associate component types of automobile components and abnormal types of abnormal components;

[0138] S162: defining a corresponding surface defect detection method according to the type of automobile parts and the abnormal type of the abnormal parts. At this time, the corresponding surface defect detection method is matched based on different automobile parts;

[0139] S163: Performing surface defect detection on the corresponding automobile component based on the surface defect detection method;

[0140] S164: collecting corresponding surface defect images according to the surface defect detection of the automobile parts;

[0141] S165: defining corresponding surface defect elements based on each surface defect image;

[0142] S166: Distribute multiple surface defect elements in the three-dimensional model of the automobile, and define defect levels of different automobile parts based on the multiple surface defect elements of different automobile parts, construct a defect level set according to the defect levels of each automobile part, and define the overall defect level of the automobile based on the defect level set.

[0143] In the specific implementation process of the present invention, each abnormal part is defined according to the abnormal detection of the three-dimensional model of the automobile; the corresponding abnormal components are defined based on the various abnormal parts, the corresponding positions and the three-dimensional model of the automobile, and the types of corresponding automobile components are defined based on the abnormal components; the corresponding surface defect detection method is defined according to the component type of the automobile component and the abnormal type of the abnormal component, surface defect detection is performed on the corresponding automobile component based on the surface defect detection method, surface defect elements are defined according to the surface defect image, and the overall defect level of the automobile is defined based on multiple surface defect elements of different automobile components, thereby realizing multi-dimensional control of multiple surface defect elements of different automobile components, and performing overall control based on the dimensions of automobile components and the dimensions of surface defect elements, thereby improving the surface defect detection accuracy of automobile components, and thereby improving the accuracy of the overall defect level of the automobile.

[0144] At this time, the component types of automobile parts and the abnormal types of abnormal parts are associated, and the component types of automobile parts and the abnormal types of abnormal parts are controlled as a whole. At the same time, corresponding surface defect detection methods are defined according to the component types of automobile parts and the abnormal types of abnormal parts. At this time, corresponding surface defect detection methods are matched based on different automobile parts to facilitate targeted detection of different automobile parts, thereby ensuring the matching of surface defect detection methods.

[0145] Furthermore, surface defect detection is performed on corresponding automobile parts based on the surface defect detection method, so that corresponding surface defect images are collected according to the surface defect detection of automobile parts, and each surface defect image is introduced to further identify the surface defect images.

[0146] Therefore, corresponding surface defect elements are defined based on each surface defect image; multiple surface defect elements are distributed in the three-dimensional model of the automobile, and different defect levels of automobile parts are defined based on the multiple surface defect elements of different automobile parts, a defect level set is constructed according to the defect levels of each automobile part, and the overall defect level of the automobile is defined based on the defect level set, thereby realizing multi-dimensional control of multiple surface defect elements of different automobile parts, and overall control is performed based on the dimensions of automobile parts and the dimensions of surface defect elements, thereby improving the surface defect detection accuracy of automobile parts, and thereby improving the accuracy of the overall defect level of the automobile.

[0147] In an embodiment of the present invention, through the method in the embodiment of the present invention, the location of the car and the model of the car are collected, and a traversal mode is defined according to the location of the car and the model of the car; the traversal of the car is triggered along the traversal mode, and a three-dimensional model of the car is constructed; a corresponding detection method is defined based on the three-dimensional model of the car and the model of the car, and the three-dimensional model of the car is detected for abnormalities along the detection method, so as to facilitate targeted detection of the three-dimensional model of the car, and fully consider the various different car parts in the three-dimensional model of the car.

[0148] Furthermore, each abnormal part is defined based on abnormality detection of the three-dimensional model of the automobile; corresponding abnormal components are defined based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and the type of corresponding automobile components is defined based on the abnormal components; corresponding surface defect detection methods are defined according to the component types of automobile components and the abnormal types of abnormal components, surface defect detection is performed on corresponding automobile components based on the surface defect detection methods, surface defect elements are defined based on surface defect images, and the overall defect level of the automobile is defined based on multiple surface defect elements of different automobile components, thereby achieving multi-dimensional control of multiple surface defect elements of different automobile components, and overall control is performed based on the dimensions of automobile components and the dimensions of surface defect elements, thereby improving the surface defect detection accuracy of automobile components, and thereby improving the accuracy of the overall defect level of the automobile.

[0149] See also Figure 8 , Figure 8 It is a schematic diagram of the structural composition of a surface defect detection system for automobile parts in an embodiment of the present invention.

[0150] like Figure 8 As shown, a surface defect detection system for automobile parts, the surface defect detection system for automobile parts comprises:

[0151] The collection module 21 is used to collect the location of the car and the model of the car, and define the traversal mode according to the location of the car and the model of the car;

[0152] A three-dimensional model module 22, used to trigger the traversal of the car along the traversal mode and build a three-dimensional model of the car;

[0153] The anomaly detection module 23 is used to define a corresponding detection method based on the three-dimensional model of the car and the model of the car, and perform anomaly detection on the three-dimensional model of the car according to the detection method;

[0154] An abnormal part module 24, for defining various abnormal parts according to abnormality detection of the three-dimensional model of the vehicle;

[0155] The automobile component module 25 is used to define corresponding abnormal components based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and to define the type of corresponding automobile components based on the abnormal components;

[0156] The defect module 26 is used to define corresponding surface defect detection methods according to the types of automobile parts and the abnormal types of abnormal parts, perform surface defect detection on corresponding automobile parts based on the surface defect detection methods, define surface defect elements according to surface defect images, and define the overall defect level of the automobile based on multiple surface defect elements of different automobile parts.

[0157] See also Fig. 9 , refer to the following Fig. 9 The electronic intelligent device 40 according to this embodiment of the present invention is described. Fig. 9 The electronic intelligent device 40 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0158] like Fig. 9 As shown, the electronic intelligent device 40 is in the form of a general computing intelligent device. The components of the electronic intelligent device 40 may include but are not limited to: at least one processing unit 41, at least one storage unit 42, and a bus 43 connecting different system components (including the storage unit 42 and the processing unit 41).

[0159] The storage unit stores program codes, which can be executed by the processing unit 41, so that the processing unit 41 executes the steps according to various exemplary embodiments of the present invention described in the above “Embodiment Method” section of this specification.

[0160] The storage unit 42 may include a readable medium in the form of a volatile storage unit, such as a random access memory unit (RAM) 421 and / or a cache memory unit 422 , and may further include a read-only memory unit (ROM) 423 .

[0161] The storage unit 42 may also include a program / utility 424 having a set (at least one) of program modules 425, such program modules 425 including but not limited to: an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment.

[0162] Bus 43 may represent one or more of several types of bus structures, including a memory unit bus or memory unit controller, a peripheral bus, an accelerated graphics port, a processing unit, or a local bus using any of a variety of bus architectures.

[0163] The electronic smart device 40 may also communicate with one or more external smart devices (e.g., keyboards, pointing smart devices, Bluetooth smart devices, etc.), one or more smart devices that enable a user to interact with the electronic smart device 40, and / or any smart device that enables the electronic smart device 40 to communicate with one or more other computing smart devices (e.g., routers, modems, etc.). Such communication may be performed through an input / output (I / O) interface 44. Furthermore, the electronic smart device 40 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) through a network adapter 45. Fig. 9 As shown, the network adapter 45 communicates with other modules of the electronic intelligent device 40 via the bus 43. It should be understood that although Fig. 9 Not shown, other hardware and / or software modules may be used in conjunction with the electronic intelligent device 40, including but not limited to: microcode, intelligent device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup planning systems.

[0164] Through the description of the above implementation, it is easy for those skilled in the art to understand that the example implementation described here can be implemented by software, or by software combined with necessary hardware. Therefore, the technical solution according to the implementation of the present disclosure can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.) or on a network, including several instructions to enable a computing intelligent device (which can be a personal computer, a server, a terminal device, or a network intelligent device, etc.) to execute the method according to the implementation of the present disclosure.

[0165] Those skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable storage medium, and the storage medium can include: a read-only memory (ROM), a random access memory (RAM), a disk or an optical disk, etc. In addition, it stores computer program instructions, and when the computer program instructions are executed by a computer, the computer executes the above method.

[0166] In addition, the surface defect detection method and system for automobile parts provided by the embodiments of the present invention are introduced in detail above. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea. At the same time, for those skilled in the art, according to the ideas of the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as limiting the present invention.

Claims

1. A method for detecting surface defects of automobile parts, characterized in that: Applied to surface defect detection scenarios of automotive parts; The surface defect detection method of the automobile parts comprises: Collect the location and model of the car, and define the traversal mode according to the location and model of the car; triggering the traversal of the car along the traversal mode and constructing a three-dimensional model of the car; A corresponding detection method is defined based on the three-dimensional model of the car and the model of the car, and an abnormality detection is performed on the three-dimensional model of the car according to the detection method; Defining each abnormal part according to abnormality detection of the three-dimensional model of the vehicle; Defining corresponding abnormal parts based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and defining the type of corresponding automobile parts based on the abnormal parts; A corresponding surface defect detection method is defined according to the type of automobile parts and the abnormal type of the abnormal part, surface defect detection is performed on the corresponding automobile parts based on the surface defect detection method, surface defect elements are defined according to the surface defect image, and the overall defect level of the automobile is defined based on multiple surface defect elements of different automobile parts.

2. The surface defect detection method of automobile parts according to claim 1, characterized in that: The collecting of the location of the car and the model of the car, and defining a traversal mode according to the location of the car and the model of the car, include: Locate the car to be detected and collect the location of the car; Perform positioning detection based on the location of the car and define the posture of the car; Defining a first parameter according to the position of the vehicle and the posture of the vehicle; Collecting the model of the car, associating the model of the car with the location of the car, and defining a second parameter according to the model of the car and the location of the car; The first parameter and the second parameter are associated, and a corresponding traversal mode is defined based on the first parameter, the second parameter, and the traversal matching table.

3. The surface defect detection method of automobile parts according to claim 2, characterized in that: The triggering of the traversal of the car along the traversal mode and constructing the three-dimensional model of the car includes: The traversal mode is frozen, and the traversal of the car is triggered along the traversal mode; During the traversal process, corresponding dynamic shooting is performed at different positions of the car; Collect multiple car images in different directions based on dynamic shooting of the car; A plurality of stereo features are defined according to a plurality of car images in different directions, and the plurality of stereo features are distributed in different directions of the car; A three-dimensional model of the car is constructed based on multiple three-dimensional features and the car model. At this time, a preliminary three-dimensional model is defined based on the synthesis of multiple three-dimensional features, and the three-dimensional model of the car is constructed based on the preliminary three-dimensional model and a reference model corresponding to the car model.

4. The surface defect detection method of automobile parts according to claim 3, characterized in that: The method of defining a corresponding detection method based on the three-dimensional model of the car and the model of the car, and performing abnormality detection on the three-dimensional model of the car according to the detection method, includes: freeze-frame car dioramas; Defining detection coefficients based on a three-dimensional model of the vehicle and a model of the vehicle; Define the corresponding detection method according to the detection coefficient and the corresponding detection method matching table; Freeze the detection method; associate the three-dimensional model of the vehicle and the detection method, and define a corresponding matching coefficient according to the three-dimensional model of the vehicle and the detection method; Comparing the matching coefficient with a preset matching coefficient threshold, where the preset matching coefficient threshold corresponds to the model of the corresponding car; If the matching coefficient is greater than a preset matching coefficient threshold, abnormality detection is performed on the three-dimensional model of the car according to the detection method.

5. The surface defect detection method of automobile parts according to claim 4, characterized in that: The method of defining each abnormal part according to abnormality detection of the three-dimensional model of the automobile includes: freeze-frame car dioramas; A plurality of sub-models are defined according to the division of the three-dimensional model of the car, and the plurality of sub-models are distributed at different positions of the car; Associate multiple sub-models and corresponding detection methods; Defining a plurality of sub-anomaly parts based on anomaly detection of a plurality of sub-models and corresponding detection methods; In each sub-model, each sub-abnormal part constructs a corresponding abnormal part. In this case, there are multiple abnormal parts in the three-dimensional model of the car.

6. The surface defect detection method of automobile parts according to claim 5, characterized in that: The method of defining corresponding abnormal parts based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and defining the type of corresponding automobile parts based on the abnormal parts, includes: Freeze each abnormal part and mark the corresponding position; defining an anomaly contour based on the identification of each anomaly portion; The corresponding abnormal area is defined according to the abnormal contour and the corresponding position.

7. The surface defect detection method of automobile parts according to claim 6, characterized in that: The method further includes defining corresponding abnormal parts based on each abnormal part, the corresponding position and the three-dimensional model of the automobile, and defining the type of corresponding automobile parts based on the abnormal parts. Correlate the three-dimensional model of each abnormal area and the car; Defining corresponding abnormal parts according to each abnormal area and the three-dimensional model of the car; The type of the corresponding automobile part is defined based on the abnormal part and the automobile structure classification table.

8. The surface defect detection method of automobile parts according to claim 7, characterized in that: The method of defining a corresponding surface defect detection method according to the type of automobile parts and the abnormal type of abnormal parts, performing surface defect detection on the corresponding automobile parts based on the surface defect detection method, defining surface defect elements according to the surface defect image, and defining the overall defect level of the automobile based on multiple surface defect elements of different automobile parts includes: Associate the component types of the automobile components and the abnormal types of the abnormal components; The corresponding surface defect detection method is defined according to the component type of the automobile component and the abnormal type of the abnormal component. At this time, the corresponding surface defect detection method is matched based on different automobile components.

9. The surface defect detection method of automobile parts according to claim 8, characterized in that: The method further includes defining a corresponding surface defect detection method according to the type of automobile parts and the abnormal type of abnormal parts, performing surface defect detection on the corresponding automobile parts based on the surface defect detection method, defining surface defect elements according to the surface defect image, and defining the overall defect level of the automobile based on multiple surface defect elements of different automobile parts. Performing surface defect detection on corresponding automobile parts based on the surface defect detection method; Collecting corresponding surface defect images according to surface defect detection of automobile parts; Define corresponding surface defect elements based on each surface defect image; Multiple surface defect elements are distributed in a three-dimensional model of a car, and defect levels of different car parts are defined based on the multiple surface defect elements of different car parts. A defect level set is constructed according to the defect levels of each car part, and the overall defect level of the car is defined based on the defect level set.

10. A surface defect detection system for automobile parts, characterized in that: The surface defect detection system of an automobile part is applied to the surface defect detection method of an automobile part as claimed in any one of claims 1 to 9, and the surface defect detection system of an automobile part comprises: A collection module is used to collect the location of the car and the model of the car, and define a traversal mode according to the location of the car and the model of the car; A three-dimensional model module, used for triggering the traversal of the car along the traversal mode and building a three-dimensional model of the car; An anomaly detection module, used to define a corresponding detection method based on the three-dimensional model of the car and the model of the car, and perform anomaly detection on the three-dimensional model of the car according to the detection method; An abnormal part module, for defining each abnormal part according to abnormality detection of the three-dimensional model of the car; An automobile component module, used for defining corresponding abnormal components based on each abnormal part, a corresponding position and a three-dimensional model of the automobile, and defining the type of corresponding automobile components based on the abnormal components; The defect module is used to define corresponding surface defect detection methods according to the types of automobile parts and the abnormal types of abnormal parts, perform surface defect detection on corresponding automobile parts based on the surface defect detection methods, define surface defect elements according to surface defect images, and define the overall defect level of the automobile based on multiple surface defect elements of different automobile parts.

Images