Method and system for surface defect detection based on aerospace aluminum alloy

Abstract

The application discloses a kind of surface defect detection method and system based on aerospace aluminum alloy, belong to aluminum alloy technical field.The first image data of the aluminum alloy to be detected is obtained by the present application, the first image data is the image data collected by depth camera;According to the first image data, the polarization light source is controlled to irradiate the aluminum alloy to be detected, and the second image data is collected by controlling polarization camera;According to the first image data and the second image data, determine target fusion image data;According to the target fusion image data, the defect detection result of the aluminum alloy to be detected is identified, and the technical effect of improving the accuracy of aluminum alloy surface quality detection is realized.

Description

Technical Field

[0001] This invention relates to the field of aluminum alloy technology, and in particular to a method and system for detecting surface defects in aerospace aluminum alloys. Background Technology

[0002] In the aerospace industry, the surface requirements for aluminum alloys are stringent, directly impacting the safety, reliability, and lifespan of spacecraft. Industrial cameras are typically used to collect image data of the aluminum alloy surface for analysis and identification, thereby enabling the quality inspection of the surface. Currently, depth cameras are generally used to collect surface data of aluminum alloys. Depth cameras typically measure distance by calculating the flight time of a laser between the camera and the object. However, when inspecting smooth, rounded corners, specular reflection can easily occur, causing light from the depth camera to be reflected to other locations, resulting in missing point cloud data for that area and thus reducing the accuracy of aluminum alloy surface quality inspection. Summary of the Invention

[0003] The main objective of this invention is to provide a method and system for detecting surface defects in aerospace-grade aluminum alloys, aiming to improve the accuracy of quality inspection of aluminum alloy surfaces. To achieve the above objective, this invention provides a method for detecting surface defects in aerospace-grade aluminum alloys, which includes the following steps:

[0004] Acquire the first image data of the aluminum alloy to be detected, wherein the first image data is image data acquired by a depth camera;

[0005] Based on the first image data, control the polarization light source to illuminate the aluminum alloy to be detected, and control the polarization camera to acquire the second image data;

[0006] Target fused image data is determined based on the first image data and the second image data;

[0007] The defect detection results of the aluminum alloy to be detected are identified based on the target fused image data.

[0008] Optionally, the first image data includes: two-dimensional visual data and three-dimensional spatial data, and the step of controlling a polarized light source to irradiate the aluminum alloy to be detected based on the first image data includes:

[0009] Based on the three-dimensional spatial data, low-quality data regions are determined. The low-quality data regions are: regions without point cloud data, or regions where the point cloud density is less than a preset density.

[0010] The contour information of the aluminum alloy to be detected is determined based on the two-dimensional visual data;

[0011] Light source control data is generated based on the contour information and the low-quality data area;

[0012] The polarization light source is controlled according to the light source control data.

[0013] Optionally, the contour information includes: contour position coordinates, and the step of generating light source control data based on the contour information and the low-quality data area includes:

[0014] The cause of the low quality is determined based on the first location coordinates of the low-quality data area and the contour location coordinates.

[0015] When the cause of the low quality is edge reflection of the aluminum alloy to be tested, the orientation of the low quality data area is determined according to the first position coordinates and the contour position coordinates.

[0016] Light source control data is generated based on the orientation direction, and the light source control data includes: the light source illumination direction.

[0017] Optionally, the number of contour position coordinates is multiple, and the step of determining the orientation direction of the low-quality data region based on the first position coordinates and the contour position coordinates includes:

[0018] Calculate the first distance between the first position coordinates and each of the contour position coordinates to obtain multiple first distances;

[0019] The associated target contour position coordinates are determined based on multiple first distances;

[0020] The orientation direction is determined based on the positional relationship between the first position coordinates and the target contour position coordinates.

[0021] Optionally, the step of determining the target fused image data based on the first image data and the second image data includes:

[0022] Extract the first feature data from the first image data and the second feature data from the second image data respectively;

[0023] The first feature data and the second feature data are matched according to the feature matching algorithm to obtain the feature matching result, which includes: feature matching pairs;

[0024] The target fused image data is obtained by fusing the second image data with the first image data according to the feature matching pair.

[0025] Optionally, the step of determining the first type of detection result based on the first polarization degree of the target pixel and the second polarization degree of the neighborhood region of the target pixel includes:

[0026] The angle of the aluminum alloy surface corresponding to each pixel in the neighborhood area is determined according to the first degree of polarization, the second degree of polarization and the first preset mapping relationship. The first preset mapping relationship is the correspondence between the degree of polarization and the first included angle, where the first included angle is the angle between the shooting direction of the polarization camera and the reflected light.

[0027] The first type of detection result is determined based on the aluminum alloy surface angle corresponding to all the pixels.

[0028] Furthermore, to achieve the above objectives, the present invention also provides a surface defect detection system based on aerospace-grade aluminum alloy, the surface defect detection system based on aerospace-grade aluminum alloy comprising:

[0029] The acquisition module is used to acquire the first image data of the aluminum alloy to be detected, wherein the first image data is the image data acquired by the depth camera;

[0030] The control module is used to control the polarization light source to illuminate the aluminum alloy to be detected according to the first image data, and to control the polarization camera to acquire the second image data.

[0031] The fusion module is used to determine target fused image data based on the first image data and the second image data;

[0032] The detection module is used to identify the defect detection results of the aluminum alloy to be detected based on the target fused image data.

[0033] Furthermore, to achieve the above objectives, the present invention also provides a surface defect detection device based on aerospace aluminum alloy. The surface defect detection device based on aerospace aluminum alloy includes: a memory, a processor, and a surface defect detection program based on aerospace aluminum alloy stored in the memory and executable on the processor. The surface defect detection program based on aerospace aluminum alloy is configured to implement the steps of the above-described surface defect detection method based on aerospace aluminum alloy.

[0034] In addition, to achieve the above objectives, the present invention also provides a storage medium storing a surface defect detection program based on aerospace aluminum alloy, wherein the surface defect detection program based on aerospace aluminum alloy, when executed by a processor, implements the steps of the above-described surface defect detection method based on aerospace aluminum alloy.

[0035] This invention proposes a surface defect detection method for aerospace-grade aluminum alloys. The method acquires first image data of the aluminum alloy to be inspected (image data obtained from a depth camera), controls a polarized light source to illuminate the aluminum alloy based on the first image data, and controls the polarized camera to acquire second image data. Based on the first and second image data, a target fused image data is determined. Compared to direct monitoring by a depth camera, this method utilizes the depolarization effect of polarized light on the metal surface. Because the depolarization effect is related to the angle of the scattered light from the aluminum alloy, fusion identification is performed. The defect detection result of the aluminum alloy is identified based on the target fused image data, thereby improving the acquisition of effective image information and thus enhancing the accuracy of aluminum alloy surface quality inspection. Attached Figure Description

[0036] Figure 1 This is a schematic diagram of the structure of a surface defect detection device based on aerospace aluminum alloy, which is part of the hardware operating environment of the embodiment of the present invention.

[0037] Figure 2 This is a flowchart illustrating the first embodiment of the surface defect detection method for aerospace aluminum alloys according to the present invention.

[0038] Figure 3 This is a flowchart illustrating the second embodiment of the surface defect detection method for aerospace aluminum alloys according to the present invention;

[0039] Figure 4 This is a flowchart illustrating the third embodiment of the surface defect detection method for aerospace aluminum alloys of the present invention.

[0040] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0041] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0042] Reference Figure 1 , Figure 1 This is a schematic diagram of the surface defect detection equipment based on aerospace-grade aluminum alloy, which is part of the hardware operating environment of the embodiment of the present invention.

[0043] like Figure 1As shown, the surface defect detection device based on aerospace-grade aluminum alloy may include: a processor 1001, such as a central processing unit (CPU), a communication bus 1002, an interactive device 1003, a network interface 1004, and a memory 1005. The communication bus 1002 is used to enable communication between these components. The interactive device 1003 may include a display screen or an input unit such as a keyboard. Optionally, the interactive device 1003 may also connect to the communication bus via standard wired or wireless interfaces. The network interface 1004 may optionally include standard wired or wireless interfaces (such as a Wi-Fi interface). The memory 1005 may be a high-speed random access memory (RAM) or a stable non-volatile memory (NVM), such as a disk drive. Optionally, the memory 1005 may also be a storage device independent of the aforementioned processor 1001.

[0044] Furthermore, the surface defect detection equipment for aerospace-grade aluminum alloys includes a polarizing camera, a depth camera, and a polarizing light source. The polarizing camera and the depth camera have the same shooting direction, i.e., the same optical axis. Preferably, the illumination direction of the polarizing light source is perpendicular to the shooting direction of the polarizing camera, i.e., the plane perpendicular to the illumination direction and the shooting direction is parallel, and the setting position and illumination direction can be adjusted according to the data captured by the depth camera.

[0045] Those skilled in the art will understand that Figure 1 The structure shown does not constitute a limitation on surface defect detection equipment based on aerospace aluminum alloys and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0046] like Figure 1 As shown, the memory 1005, which serves as a storage medium, may include an operating system, a data storage module, a network communication module, a user interface module, and a surface defect detection program based on aerospace-grade aluminum alloy.

[0047] exist Figure 1In the surface defect detection device based on aerospace aluminum alloy shown, the network interface 1004 is mainly used for data communication with other devices; the interactive device 1003 is mainly used for data interaction with the user; the processor 1001 and memory 1005 in the surface defect detection device based on aerospace aluminum alloy can be set in the surface defect detection device based on aerospace aluminum alloy. The surface defect detection device based on aerospace aluminum alloy calls the surface defect detection program based on aerospace aluminum alloy stored in memory 1005 through processor 1001 and executes the surface defect detection method based on aerospace aluminum alloy provided in the embodiment of the present invention.

[0048] This invention provides a surface defect detection method based on aerospace-grade aluminum alloys, referring to... Figure 2 , Figure 2 This is a flowchart illustrating the first embodiment of a surface defect detection method for aerospace aluminum alloys according to the present invention.

[0049] In this embodiment, the surface defect detection method based on aerospace aluminum alloy includes:

[0050] Step S1: Obtain the first image data of the aluminum alloy to be detected. The first image data is the image data acquired by the depth camera.

[0051] In this embodiment, a depth camera is controlled to acquire image data of the aluminum alloy to be inspected. Currently, the depth camera outputs two-dimensional depth data, where each depth data represents the distance from the surface of the aluminum alloy to be inspected to the camera. Preferably, the depth camera can also integrate two-dimensional image data of infrared and visible light. Acquiring the first image data can determine whether there are defects on the surface of the aluminum alloy to be inspected.

[0052] Step S2: Control the polarization light source to illuminate the aluminum alloy to be tested according to the first image data, and control the polarization camera to acquire the second image data.

[0053] It should be noted that compared to defect detection in other fields, the surface of aerospace-grade aluminum alloys has high production standards and generally undergoes a cleaning process before inspection. The surface is prone to specular reflection, and compared to hardware such as circuit boards, aluminum alloys can be bent to form curved surfaces and can have rounded chamfers at the edges. When conventional depth cameras detect edge locations, the infrared laser emitted by the depth camera is reflected outside the camera, resulting in missing depth data in the edge area or reduced density of the point cloud data in the edge area. In this embodiment, the edge area of ​​the aluminum alloy and the area containing the actual point cloud data are determined based on the first image data, and the bending direction of the corresponding area is determined. The illumination direction of the polarized light source is then determined based on the bending direction. Preferably, in this embodiment, the illumination direction of the polarized light source is set to be perpendicular to the optical axis of the polarization camera. Optionally, in some embodiments, the illumination direction of the polarized light source can be at an angle close to 90° to the optical axis of the polarization camera, for example: 89°, 85°, and the range of 85° to 90°. It should be noted that the polarized light source here emits fully polarized light, which can be linearly polarized light or circularly polarized light. In this embodiment, the acquired second image data includes reflected polarization data and scattered polarization data. The reflected polarization data and scattered polarization data are determined based on the magnitude of the acquired light intensity value. Specifically, a light intensity threshold is set and compared with the acquired light intensity value to determine whether the acquired data is reflected or scattered polarization data. The reflected light intensity value is greater than the scattered light intensity value. In this embodiment, the normal direction of the position corresponding to the reflected polarization data is determined to form a 45° angle with the optical axis of the polarization camera. It should be noted that the scattering of polarized light on a metal surface will cause a depolarization effect. It should also be noted that the depth camera and the polarization camera have the same shooting direction.

[0054] Step S3: Determine the target fused image data based on the first image data and the second image data;

[0055] Preferably, the fusion method can be feature matching. The first image data and the second image data are fused to obtain the target fused image data.

[0056] Step S4: Identify the defect detection results of the aluminum alloy to be detected based on the target fused image data.

[0057] In this embodiment, the target fused image can be divided into multiple partitions, and different partitions use different methods to detect defects in the aluminum alloy to be detected, thereby achieving overall detection.

[0058] In this embodiment, by acquiring first image data of the aluminum alloy to be inspected (the first image data is image data acquired by a depth camera), a polarized light source is controlled to illuminate the aluminum alloy to be inspected based on the first image data, and a second image data is acquired by the polarized camera. Target fused image data is determined based on the first and second image data. Compared to the results of direct monitoring by the depth camera, the depolarization effect of polarized light on the metal surface is utilized. Due to the characteristic that the depolarization effect is related to the angle of the scattered light from the aluminum alloy, fusion identification is performed. The defect detection results of the aluminum alloy to be inspected are identified based on the target fused image data, thereby improving the acquisition of effective image information and thus improving the accuracy of aluminum alloy surface quality inspection.

[0059] Furthermore, based on the first embodiment, a second embodiment of the present invention for the surface defect detection method of aerospace aluminum alloys is proposed. In this embodiment, reference is made to... Figure 3 The first image data includes: two-dimensional visual data and three-dimensional spatial data. The step of controlling a polarized light source to irradiate the aluminum alloy to be tested based on the first image data includes:

[0060] Step S21: Determine the low-quality data region based on the three-dimensional spatial data. The low-quality data region is: a region with no point cloud data, or a region with a point cloud density less than a preset density.

[0061] Preferably, the three-dimensional spatial data here specifically refers to depth data, that is, the missing depth data in the low-quality data regions. Optionally, the collected data can be partitioned and labeled into different region types, including low-quality data regions.

[0062] Step S22: Determine the contour information of the aluminum alloy to be detected based on the two-dimensional visual data;

[0063] Here, the two-dimensional visual data can generally be infrared image data or visible light image data. In this embodiment, optionally, the contour information of the aluminum alloy to be detected is determined by an image edge extraction algorithm. The contour information includes the position coordinates of the contour, which generally refers to the position coordinates on the image. Optionally, an additional coordinate system can be preset to map the image data to the corresponding coordinate system.

[0064] Step S23: Generate light source control data based on the contour information and the low-quality data area;

[0065] In this embodiment, by setting the comparison result between the contour information and the low-quality data,

[0066] Optionally, the comparison result can be obtained by using the position coordinates in the contour information as the first position coordinates and the position coordinates of the low-quality data area as the second position coordinates, and determining whether the second position coordinate exists in the first neighborhood of the first position coordinates. Here, the first neighborhood is a set of points within a preset range of distance from the first position coordinates in the pixel coordinate system of the contour information. For example, the contour information includes multiple first position coordinates of the edge of a horizontal straight line in an image. It is determined whether the second position coordinate exists in the first neighborhood corresponding to the multiple first position coordinates. When the second position coordinate exists in the first neighborhood corresponding to the multiple first position coordinates, the comparison result is determined to be the presence of a curved surface. Further, the direction of the curved surface is determined based on the distribution of the second position coordinates. Specifically, when the second position coordinates are evenly distributed above the edge of the horizontal straight line, the orientation of the curved surface is determined to be perpendicular to the horizontal straight line, and the outer surface of the curved surface faces upwards from the edge of the horizontal straight line. Based on the comparison result, it can be determined whether the edge has a curved surface, the orientation of the curved surface, etc., and light source control data for controlling the light source can be generated based on the orientation of the curved surface.

[0067] Step S24: Control the polarization light source according to the light source control data.

[0068] In some embodiments, when there is only one light source, the position of the polarizing light source is adjusted so that the illumination direction of the polarizing light source meets the requirements of the light source control data. In other embodiments, there are multiple light sources, which are arranged on a plane perpendicular to the optical axis of a pre-polarized camera and facing the aluminum alloy to be tested. The operation of the specific polarizing light source is controlled according to the light source control data.

[0069] In this embodiment, low-quality data areas are determined by analyzing the three-dimensional spatial data, and the contour information of the aluminum alloy to be inspected is determined based on the two-dimensional visual data. Light source control data is generated based on the contour information and the low-quality data areas, and the polarized light source is controlled based on the light source control data. This achieves accurate illumination of the curved surface of the aluminum alloy to be inspected, improving the accuracy of subsequent defect detection using polarized light.

[0070] Furthermore, based on the first or second embodiment, a third embodiment of the present invention for the surface defect detection method of aerospace aluminum alloys is proposed. In this embodiment, reference is made to... Figure 3 The contour information includes: contour position coordinates, and the step of generating light source control data based on the contour information and the low-quality data area includes:

[0071] Step S231: Determine the cause of low quality based on the first position coordinates of the low quality data area and the contour position coordinates;

[0072] It should be noted that the types of reasons for poor signal quality include: environmental factors, such as ambient light interference that can overwhelm the signal, and light scattering and attenuation caused by smoke and dust. Additionally, reasons include: the edges of the aluminum alloy being tested, steep slopes, etc. Generally, identifying the edge reflection of the aluminum alloy being tested determines whether the problem is caused by edge reflection.

[0073] Step S232: When the cause of the low quality is edge reflection of the aluminum alloy to be tested, determine the orientation of the low quality data area based on the first position coordinates and the contour position coordinates;

[0074] In this embodiment, when the low quality is caused by edge reflection of the aluminum alloy to be detected, the orientation direction of the low quality data area is determined based on the first position coordinates and the contour position coordinates. Optionally, the orientation direction can be the direction of the normal vector of the surface center. Since the contour position coordinates are the coordinates of the image plane in this embodiment, the orientation direction can be the projection direction of the normal vector of the surface onto the image plane, generally based on the edge position of the aluminum alloy to be detected. Optionally, a dilation operation is performed on the first image data, and the dilation direction of each edge pixel in the first image is taken as the orientation direction. Preferably, there can be multiple orientation directions, which are grouped into up to three groups. The average angle of the average orientation direction of each group is taken as the light source illumination direction. This is because aluminum alloys may have multiple different rounded corners or curved surfaces, requiring multiple light source illumination directions to be set and multiple shots to obtain multiple second image data.

[0075] Optionally, the center coordinates of the first position coordinates and the contour position coordinates are compared. The orientation direction is the target direction connecting the first position coordinates to the center coordinates. Preferably, the orientation direction here only considers the direction on the two-dimensional plane, which is perpendicular to the optical axis of the depth camera. Additionally, it should be explained that the edges of the first image data have multiple [various parameters] on the two-dimensional plane.

[0076] Step S233: Generate light source control data based on the orientation direction, wherein the light source control data includes: light source illumination direction.

[0077] Specifically, the position of the light source and the direction of illumination are determined based on the orientation.

[0078] In this embodiment, the cause of the low quality is determined by the first position coordinates and the contour position coordinates of the low quality data area. When the cause of the low quality is the edge reflection of the aluminum alloy to be tested, the orientation direction of the low quality data area is determined according to the first position coordinates and the contour position coordinates. Light source control data is generated according to the orientation direction. The light source control data includes the light source illumination direction, thereby realizing targeted supplementary lighting for the low quality data area and improving the accuracy of subsequent polarization degree analysis.

[0079] Furthermore, the number of contour position coordinates is multiple, and the step of determining the orientation direction of the low-quality data region based on the first position coordinates and the contour position coordinates includes:

[0080] Calculate the first distance between the first position coordinates and each of the contour position coordinates to obtain multiple first distances;

[0081] The associated target contour position coordinates are determined based on multiple first distances;

[0082] The orientation direction is determined based on the positional relationship between the first position coordinates and the target contour position coordinates.

[0083] In this embodiment, by calculating distances and sorting multiple first distances, the contour position coordinates corresponding to the closest first distance are selected as the target contour position coordinates. The slope of the line connecting the target contour position coordinates and the first position coordinates is calculated to obtain an accurate orientation.

[0084] Furthermore, based on any of the above embodiments, a fourth embodiment of the present invention for the surface defect detection method of aerospace aluminum alloy is proposed. In this embodiment, the step of determining the target fused image data based on the first image data and the second image data includes:

[0085] Extract the first feature data from the first image data and the second feature data from the second image data respectively;

[0086] Specifically, representative corners and sides can be extracted as the feature data.

[0087] The first feature data and the second feature data are matched according to the feature matching algorithm to obtain the feature matching result, which includes: feature matching pairs;

[0088] Commonly, feature matching pairs are obtained by calculating the similarity between each feature in the first feature data and the second feature data using a feature matching algorithm.

[0089] The target fused image data is obtained by fusing the second image data with the first image data according to the feature matching pair.

[0090] The mapping relationship between pixels in the first image data and the second image data is determined based on the feature matching pairs, thereby mapping the polarization data of the second image data to the first image data according to the mapping relationship. It should be explained that a conventional polarization camera uses four adjacent basic pixels as a complete polarization state detection pixel. Common polarization cameras have polarizers placed in front of pixels; additionally, some pixels require waveplates to detect circularly polarized light. Typically, polarization cameras can directly calculate the complete polarization state of polarized light, i.e., the Stokes vector.

[0091] In this embodiment, the data for each pixel in the target fused image data may include: pixel horizontal coordinate, pixel vertical coordinate, pixel depth data, light intensity value, pixel polarization degree, and pixel polarization state. Furthermore, if the depth camera also includes the ability to acquire visible light or infrared light, the data for each pixel may also include: pixel infrared light intensity, pixel color, etc.

[0092] Furthermore, based on any of the above embodiments, a fifth embodiment of the surface defect detection method for aerospace aluminum alloys of the present invention is proposed. In this embodiment, the target fusion image data includes: multiple target pixels, and the step of identifying the defect detection result of the aluminum alloy to be detected based on the target fusion image data includes:

[0093] When the target pixel of the target fused image data is in the low-quality data region, the first type of detection result is determined based on the first polarization degree of the target pixel and the second polarization degree of the neighborhood region of the target pixel.

[0094] When the target pixel is outside the low-quality data region, a second type of detection result is determined based on the two-dimensional visual data and the three-dimensional spatial data.

[0095] The defect detection result is determined based on the first type of detection result and the second type of detection result.

[0096] In this embodiment, the neighborhood of the target pixel is defined as the region less than or equal to a preset distance from the target pixel. Optionally, when the target pixel is outside the low-quality data region, a digital twin model of the aluminum alloy surface, i.e., a three-dimensional model, is determined based on the two-dimensional visual data and three-dimensional spatial data. The surface flatness, location of abnormal changes, etc., of the digital twin model are analyzed. In some embodiments, it can also be compared with a standard product model to determine a second type of detection result. When both the first type of detection result and the second type of detection result are normal, the defect detection result is determined to be defect-free.

[0097] Furthermore, the step of determining the first type of detection result based on the first polarization degree corresponding to the target pixel and the second polarization degree of the neighborhood region of the target pixel includes:

[0098] The angle of the aluminum alloy surface corresponding to each pixel in the neighborhood area is determined according to the first degree of polarization, the second degree of polarization and the first preset mapping relationship. The first preset mapping relationship is the correspondence between the degree of polarization and the first included angle, where the first included angle is the angle between the shooting direction of the polarization camera and the reflected light.

[0099] The first type of detection result is determined based on the aluminum alloy surface angle corresponding to all the pixels.

[0100] In this embodiment, it should be noted that even seemingly smooth metal surfaces are rough at the microscopic scale. These micro-facets are oriented differently. In cases other than the initial angle of 45°, each micro-facet contributes a corresponding reflected light wave due to Fresnel reflection. Since the data collected by each pixel is scattered light at the macroscopic scale, the reflected light waves contributed by different micro-facets mix together, resulting in a situation of polarization cancellation, i.e., depolarization effect. In the depolarization effect, the degree of polarization changes with the observation angle, where the observation angle is described as the angle between the observation direction and the specular reflection direction. The closer the observation angle is to 0°, the higher the degree of polarization. Therefore, by collecting the correlation between the degree of polarization obtained from polarized light illuminating the aluminum alloy surface and the observation angle, a correlation between the degree of polarization and the angle of the aluminum alloy surface can be constructed.

[0101] Based on the angles of the aluminum alloy surface corresponding to all the pixels, it is determined whether there are locations on the aluminum alloy surface with discontinuous angular changes, thereby judging whether defects exist. A common method is to calculate the gradient values ​​of adjacent locations and determine whether the surface is smooth based on these gradient values.

[0102] Furthermore, this invention also proposes a surface defect detection system based on aerospace-grade aluminum alloy, the surface defect detection system based on aerospace-grade aluminum alloy comprising:

[0103] The acquisition module is used to acquire the first image data of the aluminum alloy to be detected, wherein the first image data is the image data acquired by the depth camera;

[0104] The control module is used to control the polarization light source to illuminate the aluminum alloy to be detected according to the first image data, and to control the polarization camera to acquire the second image data.

[0105] The fusion module is used to determine target fused image data based on the first image data and the second image data;

[0106] The detection module is used to identify the defect detection results of the aluminum alloy to be detected based on the target fused image data.

[0107] Furthermore, this invention also proposes a surface defect detection device based on aerospace aluminum alloy. The surface defect detection device based on aerospace aluminum alloy includes: a memory, a processor, and a surface defect detection program based on aerospace aluminum alloy stored in the memory and executable on the processor. The surface defect detection program based on aerospace aluminum alloy is configured to implement the steps of the above-described surface defect detection method based on aerospace aluminum alloy.

[0108] Furthermore, this embodiment of the invention also proposes a storage medium storing a surface defect detection program based on aerospace aluminum alloy. When the surface defect detection program based on aerospace aluminum alloy is executed by a processor, it implements the steps of the above-described surface defect detection method based on aerospace aluminum alloy.

[0109] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0110] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0111] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0112] The above are merely preferred embodiments of the present invention and do not limit the scope of the patent. Any equivalent structural or procedural transformations made based on the description and drawings of the present invention, or direct or indirect applications in other related technical fields, are similarly included within the scope of patent protection of the present invention.

Claims

1. A method for detecting surface defects in aerospace-grade aluminum alloys, characterized in that, The surface defect detection method based on aerospace-grade aluminum alloy includes the following steps: Acquire the first image data of the aluminum alloy to be detected, wherein the first image data is image data acquired by a depth camera; Based on the first image data, control the polarization light source to illuminate the aluminum alloy to be detected, and control the polarization camera to acquire the second image data; Target fused image data is determined based on the first image data and the second image data; Based on the target fused image data, the defect detection results of the aluminum alloy to be detected are identified; The first image data includes: two-dimensional visual data and three-dimensional spatial data. The step of controlling a polarized light source to irradiate the aluminum alloy to be tested based on the first image data includes: Based on the three-dimensional spatial data, low-quality data regions are determined. The low-quality data regions are: regions without point cloud data, or regions where the point cloud density is less than a preset density. The contour information of the aluminum alloy to be detected is determined based on the two-dimensional visual data; Light source control data is generated based on the contour information and the low-quality data area; The polarization light source is controlled according to the light source control data; The contour information includes: contour position coordinates, and the step of generating light source control data based on the contour information and the low-quality data region includes: The cause of the low quality is determined based on the first location coordinates of the low-quality data area and the contour location coordinates. When the cause of the low quality is edge reflection of the aluminum alloy to be tested, the orientation of the low quality data area is determined according to the first position coordinates and the contour position coordinates. Light source control data is generated based on the orientation direction, and the light source control data includes: the light source illumination direction; The target fused image data includes: multiple target pixels, and the step of identifying the defect detection result of the aluminum alloy to be detected based on the target fused image data includes: When the target pixel of the target fused image data is in the low-quality data region, the first type of detection result is determined based on the first polarization degree of the target pixel and the second polarization degree of the neighborhood region of the target pixel. When the target pixel is outside the low-quality data region, a second type of detection result is determined based on the two-dimensional visual data and the three-dimensional spatial data. The defect detection result is determined based on the first type of detection result and the second type of detection result.

2. The surface defect detection method based on aerospace aluminum alloy as described in claim 1, characterized in that, The number of contour position coordinates is multiple, and the step of determining the orientation direction of the low-quality data region based on the first position coordinates and the contour position coordinates includes: Calculate the first distance between the first position coordinates and each of the contour position coordinates to obtain multiple first distances; The associated target contour position coordinates are determined based on multiple first distances; The orientation direction is determined based on the positional relationship between the first position coordinates and the target contour position coordinates.

3. The surface defect detection method based on aerospace aluminum alloy as described in claim 2, characterized in that, The step of determining the target fused image data based on the first image data and the second image data includes: Extract the first feature data from the first image data and the second feature data from the second image data respectively; The first feature data and the second feature data are matched according to the feature matching algorithm to obtain the feature matching result, which includes: feature matching pairs; The target fused image data is obtained by fusing the second image data and the first image data according to the feature matching pair.

4. The surface defect detection method based on aerospace aluminum alloy as described in claim 1, characterized in that, The step of determining the first type of detection result based on the first polarization degree of the target pixel and the second polarization degree of the neighborhood region of the target pixel includes: The angle of the aluminum alloy surface corresponding to each pixel in the neighborhood area is determined according to the first degree of polarization, the second degree of polarization and the first preset mapping relationship. The first preset mapping relationship is the correspondence between the degree of polarization and the first included angle, where the first included angle is the angle between the shooting direction of the polarization camera and the reflected light. The first type of detection result is determined based on the aluminum alloy surface angle corresponding to all the pixels.

5. A surface defect detection system based on aerospace-grade aluminum alloy, characterized in that, The surface defect detection system based on aerospace-grade aluminum alloy includes: The acquisition module is used to acquire the first image data of the aluminum alloy to be detected, wherein the first image data is the image data acquired by the depth camera; The control module is used to control the polarization light source to illuminate the aluminum alloy to be detected according to the first image data, and to control the polarization camera to acquire the second image data. The first image data includes: two-dimensional visual data and three-dimensional spatial data. The step of controlling a polarized light source to irradiate the aluminum alloy to be tested based on the first image data includes: Based on the three-dimensional spatial data, low-quality data regions are determined. The low-quality data regions are: regions without point cloud data, or regions where the point cloud density is less than a preset density. The contour information of the aluminum alloy to be detected is determined based on the two-dimensional visual data; Light source control data is generated based on the contour information and the low-quality data area; The polarization light source is controlled according to the light source control data; The contour information includes: contour position coordinates, and the step of generating light source control data based on the contour information and the low-quality data region includes: The cause of the low quality is determined based on the first location coordinates of the low-quality data area and the contour location coordinates. When the cause of the low quality is edge reflection of the aluminum alloy to be tested, the orientation of the low quality data area is determined according to the first position coordinates and the contour position coordinates. Light source control data is generated based on the orientation direction, and the light source control data includes: the light source illumination direction; The fusion module is used to determine target fused image data based on the first image data and the second image data; The detection module is used to identify the defect detection results of the aluminum alloy to be detected based on the target fused image data; The target fused image data includes: multiple target pixels, and the step of identifying the defect detection result of the aluminum alloy to be detected based on the target fused image data includes: When the target pixel of the target fused image data is in the low-quality data region, the first type of detection result is determined based on the first polarization degree of the target pixel and the second polarization degree of the neighborhood region of the target pixel. When the target pixel is outside the low-quality data region, a second type of detection result is determined based on the two-dimensional visual data and the three-dimensional spatial data. The defect detection result is determined based on the first type of detection result and the second type of detection result.

6. A surface defect detection device based on aerospace-grade aluminum alloy, characterized in that, The surface defect detection device based on aerospace aluminum alloy includes: a memory, a processor, and a surface defect detection program based on aerospace aluminum alloy stored in the memory and executable on the processor, wherein the surface defect detection program based on aerospace aluminum alloy is configured to implement the steps of the surface defect detection method based on aerospace aluminum alloy as described in any one of claims 1 to 4.

7. A storage medium, characterized in that, The storage medium stores a surface defect detection program based on aerospace aluminum alloys, which, when executed by a processor, implements the steps of the surface defect detection method based on aerospace aluminum alloys as described in any one of claims 1 to 4.

Images