Gated imaging system and gated imaging method

Abstract

The application provides a regulated imaging system and a regulated imaging method, which can clearly image a complex metal device surface, obtain a high-quality surface defect image, and facilitate defect identification. The regulated imaging system comprises: an illumination unit configured to emit illumination light to illuminate a to-be-detected surface; an image acquisition unit configured to receive scattered light reflected by the to-be-detected surface to acquire image information of the to-be-detected surface; and an exposure regulation unit arranged in a light path between the image acquisition unit and the illumination unit, configured to regulate the relative exposure amount of different material surfaces on the to-be-detected surface according to the light scattering difference characteristics of the to-be-detected surface, so as to reduce the exposure difference of different material surfaces on the to-be-detected surface.

Description

Technical Field

[0001] This invention relates to the field of imaging technology, and in particular to a controllable imaging system and controllable imaging method. Background Technology

[0002] In recent years, with the implementation of cost reduction and efficiency improvement policies, automated industrial inspection has gradually replaced manual inspection. While automated machine vision inspection solutions are relatively mature for some routine industrial components, such as flat steel plates, mobile phone panels, or silk surfaces with simple shapes and uniform materials, automated defect image acquisition faces significant challenges in complex conditions, such as irregular surfaces of metal components. This is especially true for complex metal surfaces, such as the surface of a large diesel engine, which can reach 900mm*600mm in size and has complex morphology and material composition. This often results in significant differences in the surface's light scattering characteristics, making it extremely difficult to acquire clear, high-contrast images using conventional industrial cameras and light sources. Therefore, current inspection of such surfaces mainly relies on workers using strong flashlights to observe defects. This is not only inefficient due to the small observation area per instance, but also poses a significant challenge to workers working under strong light for extended periods, increasing the risk of subjective judgment errors.

[0003] However, since such complex metal surfaces typically refer to combinations of multiple materials, such as highly reflective polished surfaces and low-reflective sandblasted surfaces, and these surfaces are not planar but mostly composed of undulating curved surfaces, when ordinary planar light sources, divergent point light sources, or bowl-shaped light sources illuminate these surfaces, the images received by the camera after scattering are all low-quality images of polished surfaces being overexposed and sandblasted surfaces being underexposed. Furthermore, industrial cameras mostly use fixed-focus lenses, resulting in a small actual depth of field, making it impossible to clearly image complex surfaces with varying depths, and further hindering the provision of effective high-quality images for subsequent defect identification.

[0004] For example, existing metal surface defect acquisition schemes mainly include a light source illumination system, an industrial camera, and the metal surface to be inspected. On the one hand, since the conventional metal surface image acquisition objects are metal plates or strips, whose surfaces are planar and have uniform material, this scheme, although less difficult to light, has significant limitations in lighting conditions. That is, this lighting scheme is only suitable for image acquisition of surfaces with uniform light scattering direction and brightness. On the other hand, since the acquired images are all local magnified images with a small field of view, the actual object-side field of view of the acquired images is small, requiring scanning and traversing the entire surface, resulting in low efficiency. Summary of the Invention

[0005] One advantage of this invention is that it provides a controllable imaging system and a controllable imaging method, which can clearly image the surface of complex metal devices, obtain high-quality surface defect images, and facilitate defect identification.

[0006] Another advantage of the present invention is that it provides a controllable imaging system and a controllable imaging method. In one embodiment of the present invention, the controllable imaging system can adjust the relative exposure of different materials on the surface to be detected based on the differences in light scattering on complex metal surfaces, so as to obtain an image with relatively uniform overall exposure.

[0007] Another advantage of the present invention is that it provides a controllable imaging system and a controllable imaging method. In one embodiment of the present invention, the controllable imaging system can use polarization selection or transmission mask to control the intensity of scattered light corresponding to different material surfaces, so as to physically regulate the exposure and improve the quality of surface defect images.

[0008] Another advantage of the present invention is that it provides a controllable imaging system and a controllable imaging method, wherein, in one embodiment of the present invention, the controllable imaging system can be combined with a focusing component to achieve clear imaging of complex metal surfaces with surface height differences at multiple depths.

[0009] Another advantage of the present invention is that it provides a controllable imaging system and a controllable imaging method. In one embodiment of the present invention, the controllable imaging system can perform exposure processing on the image at the algorithm level to compensate for the lack of physical exposure and facilitate further improvement of image quality.

[0010] Another advantage of the present invention is that it provides a controllable imaging system and a controllable imaging method. In one embodiment of the present invention, the controllable imaging system can use a large field-of-view camera, eliminating the scanning and stitching process of the original small field-of-view camera, and facilitating the acquisition of defect images with high efficiency.

[0011] Another advantage of the present invention is that it provides a controllable imaging system and a controllable imaging method. In one embodiment of the present invention, the controllable imaging system is applicable to imaging most complex (metallic) surfaces with fewer scene limitations, which is of great significance for machine vision-based image acquisition.

[0012] Another advantage of this invention is that it provides a controllable imaging system and method that, to achieve the aforementioned objectives, does not require the use of expensive materials or complex structures. Therefore, this invention successfully and effectively provides a solution that not only offers a simple controllable imaging system and method, but also increases the practicality and reliability of said controllable imaging system and method.

[0013] To achieve at least one of the above-mentioned advantages or other advantages and objectives of the present invention, the present invention provides a controllable imaging system for imaging a surface to be inspected, the controllable imaging system comprising:

[0014] An illumination unit is used to emit illumination light to illuminate the surface to be inspected;

[0015] An image acquisition unit, configured to receive scattered light reflected back from the surface to be detected, thereby acquiring image information of the surface to be detected; and

[0016] An exposure control unit is disposed in the optical path between the image acquisition unit and the illumination unit. It is used to control the relative exposure of different material surfaces on the surface to be tested according to the light scattering difference characteristics of the surface to be tested, so as to reduce the exposure difference of different material surfaces on the surface to be tested.

[0017] According to one embodiment of this application, the illumination unit is a polarized diffuse light source, which is used to emit linearly polarized light so that the linearly polarized light, after being scattered by different material surfaces on the surface to be tested, forms scattered light with differences in polarization state degradation; the exposure control unit is a polarizer, which is disposed in the receiving optical path of the image acquisition unit, and is used to select the polarization state of the light entering the image acquisition unit according to the differences in polarization state degradation of the scattered light, so as to control the relative exposure of different material surfaces on the surface to be tested.

[0018] According to one embodiment of this application, the polarized diffuse light source includes a polarized light source panel and a light-receiving aperture formed in the polarized light source panel. The receiving optical path of the image acquisition unit passes through the light-receiving aperture of the polarized diffuse light source and is used to receive the scattered light reflected back by the surface to be detected via the light-receiving aperture.

[0019] According to one embodiment of this application, the polarizer is disposed within the light-receiving aperture of the polarizing diffuse light source.

[0020] According to one embodiment of this application, the polarizer is fitted onto the front end of the lens of the image acquisition unit via a collar.

[0021] According to one embodiment of this application, the illumination unit is a planar aperture light source, and the receiving optical path of the image acquisition unit passes through the aperture of the planar aperture light source; the exposure control unit is a transmittance mask, which is disposed in the emitting optical path of the planar aperture light source and the receiving optical path of the image acquisition unit. Regions with different transmittances on the transmittance mask are respectively used to align with different material surfaces of the surface to be tested, so as to control the relative exposure of different material surfaces on the surface to be tested.

[0022] According to one embodiment of this application, the transmittance mask is fabricated based on the distribution of polished and sandblasted surfaces on the surface to be tested, wherein the transmittance mask has a first region corresponding to the polished surface of the surface to be tested and a second region corresponding to the sandblasted surface of the surface to be tested, and the transmittance of the first region is less than the transmittance of the second region.

[0023] According to one embodiment of this application, the image acquisition unit is a camera, and the camera's lens has a diagonal field of view greater than or equal to 90°.

[0024] According to one embodiment of this application, the image acquisition unit is a camera, which includes a photosensitive component, an imaging lens disposed on the photosensitive side of the photosensitive component, and a focusing component. The focusing component is used to adjust the imaging focal length of the camera to focus on different height surfaces on the surface to be detected according to a lookup table of the height difference of the surface to be detected.

[0025] According to one embodiment of this application, the focusing component is a liquid lens correspondingly disposed on the imaging lens, so as to focus and adjust the focus by means of the focal length of the liquid lens.

[0026] According to one embodiment of this application, the controlled imaging system further includes an image processing unit communicatively connected to the image acquisition unit for performing exposure compensation processing on a preliminary image obtained via the image acquisition unit to obtain a final defect image.

[0027] According to one embodiment of this application, the image processing unit includes an acquisition module, an extraction module, and a fusion module that are communicatively connected to each other. The acquisition module is communicatively connected to the image acquisition unit and is used to acquire multiple preliminary images with different exposure levels acquired by the image acquisition unit. The extraction module is used to extract normally exposed areas from each preliminary image acquired by the acquisition module through image stabilization and feature region recognition to obtain multiple images of areas to be fused. The fusion module is used to perform fusion processing on the multiple images of areas to be fused through high dynamic range imaging to obtain a fused image as the final defect image.

[0028] According to one embodiment of this application, the image processing unit includes an acquisition module, a correction module, and an enhancement module that are communicatively connected to each other. The acquisition module is communicatively connected to the image acquisition unit and is used to acquire an unexposed image acquired by the image acquisition unit. The correction module is used to perform gamma correction on the unexposed image to obtain a corrected image. The enhancement module is used to perform contrast curve enhancement on the corrected image to obtain a contrast-enhanced image as the final defect image.

[0029] According to another aspect of this application, this application further provides a controlled imaging method, including the steps of:

[0030] Emit illumination light to illuminate the surface to be inspected;

[0031] Based on the light scattering differences of the surface to be tested, the relative exposure of different materials on the surface to be tested is adjusted to reduce the exposure differences between the different materials on the surface to be tested; and

[0032] The scattered light reflected back from the surface to be detected is received to acquire image information of the surface to be detected.

[0033] According to one embodiment of this application, the step of adjusting the relative exposure of different material surfaces on the surface to be tested based on the light scattering difference characteristics of the surface to be tested, so as to reduce the exposure difference of different material surfaces on the surface to be tested, includes the following steps:

[0034] Based on the difference in polarization state degradation of the scattered light, the polarization state of the received light is selected to control the relative exposure of different materials on the surface to be tested.

[0035] According to one embodiment of this application, the step of adjusting the relative exposure of different material surfaces on the surface to be tested based on the light scattering difference characteristics of the surface to be tested, so as to reduce the exposure difference of different material surfaces on the surface to be tested, includes the following steps:

[0036] Based on the distribution of polished and sandblasted surfaces on the surface to be tested, a transmittance mask is fabricated, wherein the transmittance mask has a first region corresponding to the polished surface of the surface to be tested and a second region corresponding to the sandblasted surface of the surface to be tested, and the transmittance of the first region is less than the transmittance of the second region.

[0037] The illumination light passes through the first and second regions of the transmittance mask and propagates accordingly to the polished and frosted surfaces of the surface to be inspected; and

[0038] The first and second regions of the transmittance mask transmit scattered light reflected back from the polished and frosted surfaces respectively for image reception.

[0039] According to one embodiment of this application, the controlled imaging method further includes the following steps:

[0040] Based on the height difference lookup table of the surface to be inspected, the imaging focal length is adjusted to focus on different height surfaces on the surface to be inspected, so as to obtain multiple images of the surface to be inspected at different depths.

[0041] According to one embodiment of this application, the controlled imaging method further includes the following steps:

[0042] Exposure compensation processing is performed on the acquired image information to obtain the final defect image.

[0043] According to one embodiment of this application, the step of performing exposure compensation processing on the acquired image information to obtain the final defective image includes the following steps:

[0044] Acquire multiple preliminary images with different exposure levels;

[0045] By employing image stabilization and feature region recognition, normally exposed areas are extracted from each preliminary image to obtain multiple images of the regions to be fused; and

[0046] The images of the multiple regions to be fused are fused using a high dynamic range imaging method to obtain a fused image as the final defect image.

[0047] According to one embodiment of this application, the step of performing exposure compensation processing on the acquired image information to obtain the final defective image includes the following steps:

[0048] Obtain an unexposed image;

[0049] Perform gamma correction on the non-overexposed image to obtain the corrected image; and

[0050] The contrast curve of the corrected image is then enhanced to obtain a contrast-enhanced image, which is then used as the final defect image. Attached Figure Description

[0051] Figure 1 This is a block diagram of a controllable imaging system according to an embodiment of this application;

[0052] Figure 2 A first example of a controllable imaging system according to the above embodiments of this application is shown;

[0053] Figure 3A second example of a controllable imaging system according to the above embodiments of this application is shown;

[0054] Figure 4 A schematic diagram of the structure of the controllable imaging system according to the above embodiments of this application when acquiring images at different depths is shown;

[0055] Figure 5 An example of an image processing unit in a controlled imaging system according to the above embodiments of this application is shown;

[0056] Figure 6 A schematic diagram illustrating the image fusion process performed by the image processing unit according to the above example of this application is shown;

[0057] Figure 7 Another example of an image processing unit in a controlled imaging system according to the above embodiments of this application is shown;

[0058] Figure 8 A schematic diagram illustrating the process of image correction performed by the image processing unit according to another example above in this application is shown;

[0059] Figure 9 This is a schematic flowchart of a controlled imaging method according to an embodiment of this application;

[0060] Figure 10 An example of the exposure control step in the controlled imaging method according to the above embodiments of this application is shown;

[0061] Figure 11 An example of the exposure compensation step in the controlled imaging method according to the above embodiments of this application is shown;

[0062] Figure 12 Another example of the exposure compensation step in the controlled imaging method according to the above embodiments of this application is shown;

[0063] Figure 13 An application example of the controlled imaging method according to the above embodiments of this application is shown.

[0064] Key component symbols: 1. Controlled imaging system; 10. Illumination unit; 11. Polarized diffuse light source; 111. Polarized light source panel; 112. Light receiving aperture; 12. Planar aperture light source; 120. Aperture; 20. Image acquisition unit; 21. Camera; 211. Photosensitive component; 212. Imaging lens; 213. Focusing component; 2130. Liquid lens; 30. Exposure control unit; 31. Polarizer; 32. Ring; 33. Transmittance mask; 331. First region; 332. Second region; 40. Image processing unit; 41. Acquisition module; 42. Extraction module; 43. Fusion module; 44. Correction module; 45. Enhancement module; W. Surface to be detected.

[0065] The above description of the main component symbols, together with the accompanying drawings and specific embodiments, provides a further detailed explanation of this application. Detailed Implementation

[0066] The following description is intended to disclose the present invention and enable those skilled in the art to implement it. The preferred embodiments described below are merely examples, and other obvious variations will occur to those skilled in the art. The basic principles of the invention defined in the following description can be applied to other embodiments, modifications, improvements, equivalents, and other technical solutions that do not depart from the spirit and scope of the invention.

[0067] Those skilled in the art should understand that, in the disclosure of this invention, the terms "longitudinal," "lateral," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. They are only for the convenience of describing this invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, the above terms should not be construed as limiting this invention.

[0068] In this invention, the term "a" in the claims and specification should be understood as "one or more," that is, in one embodiment, the number of an element can be one, while in another embodiment, the number of the element can be multiple. Unless explicitly indicated in the disclosure of this invention that the number of the element is only one, the term "a" should not be construed as unique or single, and the term "a" should not be construed as a limitation on the quantity.

[0069] In the description of this invention, it should be understood that terms such as "first," "second," etc., are used for descriptive purposes only and should not be construed as indicating or implying relative importance. In the description of this invention, it should be noted that, unless otherwise explicitly specified and limited, terms such as "connected" or "linked" should be interpreted broadly. For example, it can refer to a fixed connection, a detachable connection, or an integral connection; it can refer to a mechanical connection or an electrical connection; it can refer to a direct connection or an indirect connection through a medium. Those skilled in the art can understand the specific meaning of the above terms in this invention according to the specific circumstances.

[0070] In the description of this specification, the references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the present invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples. Moreover, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in this specification, as well as the features of different embodiments or examples.

[0071] Considering that existing metal surface defect acquisition methods primarily target metal plates or strips, whose surfaces are planar and uniform in material, while these methods are relatively easy to implement with lighting, they also have significant limitations in terms of lighting conditions. Specifically, these methods are only suitable for acquiring images of surfaces with uniform light scattering direction and brightness. This application creatively proposes a controllable imaging system and method that can achieve clear imaging of complex metal device surfaces, obtaining high-quality surface defect images for easier defect identification.

[0072] Specifically, refer to the accompanying drawings in the specification of this application. Figures 1 to 8 According to one embodiment of this application, a controllable imaging system 1 is provided for imaging a surface W to be inspected. The controllable imaging system 1 may include an illumination unit 10, an image acquisition unit 20, and an exposure control unit 30. The illumination unit 10 emits illumination light to illuminate the surface W to be inspected. The image acquisition unit 20 receives scattered light reflected back from the surface W to acquire image information of the surface. The exposure control unit 30 is disposed in the optical path between the image acquisition unit 20 and the illumination unit 10, and is used to control the relative exposure of different material surfaces on the surface W to be inspected according to the light scattering difference characteristics of the surface W, thereby reducing the exposure difference between the different material surfaces on the surface W.

[0073] It is worth noting that, since the controlled imaging system 1 of this application can reduce the exposure difference between different materials on the surface to be inspected W through the exposure control unit 30, the image acquisition unit 20 of the controlled imaging system 1 can obtain image information with more uniform exposure, which helps to improve the quality of defect images and facilitates subsequent defect identification. It is understood that the surface to be inspected W of this application can be, but is not limited to, a complex metal surface, such as the surface of an engine; furthermore, the different materials on the surface to be inspected W of this application can be, but is not limited to, a high-reflectivity polished surface and a low-reflectivity sandblasted surface, etc.

[0074] More specifically, in the first example of this application, such as Figure 2 As shown, the illumination unit 10 can be implemented as a polarized diffuse light source 11, which emits linearly polarized light so that the linearly polarized light, after being scattered by different material surfaces on the surface to be tested W, forms scattered light with differences in polarization state degradation. Simultaneously, the exposure control unit 30 is implemented as a polarizer 31, which is disposed in the receiving optical path of the image acquisition unit 20. It is used to select the polarization state of the light entering the image acquisition unit 20 based on the differences in polarization state degradation of the scattered light, thereby controlling the relative exposure of the different material surfaces on the surface to be tested W. It is understood that the polarizer 31 of this application itself plays a selective role; thus, after linearly polarized light is scattered by different materials on the surface W to be tested, the reflected scattered light will have a certain difference relative to the incident light; in other words, due to the difference in surface roughness between polished and frosted surfaces, the polarization state of the light before and after reflection will have a certain difference. Therefore, the controllable imaging system 1 of this application adds a selective polarizer at the front end of the lens to select the polarization state of the light entering the image acquisition unit 20 for imaging, so that the relative exposure of different materials on the surface W to be tested can be controlled to obtain a defect image with relatively uniform exposure.

[0075] Preferably, such as Figure 2 As shown, the polarized diffuse light source 11 may include a polarized light source panel 111 and a light-receiving aperture 112 formed in the polarized light source panel 111; the receiving optical path of the image acquisition unit 20 passes through the light-receiving aperture 112 of the polarized diffuse light source 11, and is used to receive the scattered light reflected back by the surface to be tested W through the light-receiving aperture 112, which helps to improve the image quality acquired by the image acquisition unit 20 while ensuring that the polarized diffuse light source 11 better illuminates the surface to be tested W.

[0076] More preferably, the polarizing light source panel 111 is implemented as a planar diffuse light source to better illuminate the surface W to be inspected, which has an irregular curved surface morphology. The light-receiving aperture 112 is preferably located in the central region of the polarizing light source panel 111 so that the illumination unit 10 and the image acquisition unit 20 cooperate to obtain a better angle and a higher quality defect image.

[0077] Optionally, such as Figure 2 As shown, the polarizer 31 of this application can be fitted onto the front end of the lens of the image acquisition unit 20 via a collar 32, so that the reflected scattered light passes through the polarizer 31 before entering the image acquisition unit 20 for imaging. Of course, in other examples of this application, the polarizer 31 can also be, but is not limited to, placed inside the light receiving aperture 112 of the polarizing diffuse light source 11. In this way, the exposure control effect can be achieved without changing the structure of the image acquisition unit 20 itself, which simplifies system assembly.

[0078] It is worth noting that, although in the first example of this application, by adding the polarizer 31 to the front end of the lens of the image acquisition unit 20, the polarization state of the light entering the image acquisition unit 20 can be effectively selected to control the relative exposure of different material surfaces, thereby obtaining a relatively uniformly exposed image, which is convenient for subsequent defect identification; however, in other examples of this application, in order to obtain a uniformly exposed defect image, the controllable imaging system 1 of this application can also adopt other methods.

[0079] For example, in the second example of this application, such as Figure 3 As shown, the illumination unit 10 can be implemented as a planar aperture light source 12, and the receiving optical path of the image acquisition unit 20 passes through the aperture 120 of the planar aperture light source 12. Meanwhile, the exposure control unit 30 can be implemented as a transmittance mask 33, which is disposed in the emitting optical path of the planar aperture light source 12 and the receiving optical path of the image acquisition unit 20. Regions with different transmittances on the transmittance mask 33 are used to align with different material surfaces of the surface to be tested W, thereby controlling the relative exposure of the different material surfaces on the surface to be tested W.

[0080] Preferably, such as Figure 3As shown, the transmittance mask 33 is fabricated according to the distribution of polished and sandblasted surfaces on the surface to be tested W; wherein the transmittance mask 33 has a first region 331 corresponding to the polished surface of the surface to be tested W and a second region 332 corresponding to the sandblasted surface of the surface to be tested W, and the transmittance of the first region 331 is less than the transmittance of the second region 332. Thus, although the reflectivity of the polished surface on the surface W to be inspected is greater than that of the frosted surface, on the one hand, the illumination light emitted by the planar aperture light source 12 will first pass through the first region 331 and the second region 332 respectively to the polished surface and the frosted surface, making the illumination intensity propagating to the polished surface less than that propagating to the frosted surface; on the other hand, the scattered light reflected by the polished surface and the frosted surface will pass through the first region 331 and the second region 332 respectively again, making the scattered light intensity corresponding to the polished surface received by the image acquisition unit 20 basically equal to the scattered light intensity corresponding to the sandblasted surface, thereby acquiring a uniformly exposed surface defect image.

[0081] According to the above embodiments of this application, as Figure 2 and Figure 3 As shown, the image acquisition unit 20 of the controllable imaging system 1 can be implemented as a camera 21, but is not limited to. The diagonal field of view of the lens of the camera 21 can be greater than or equal to 90°, so that when the shooting distance is 0.6m, the object-side image captured by the camera 21 can reach 0.6m*0.6m, which is suitable for completely covering the surface W to be inspected, so as to acquire the image of the surface W to be inspected at one time. This can eliminate the scanning and stitching process of the original small field of view camera, thereby achieving high-efficiency defect image acquisition.

[0082] For example, such as Figure 2 and Figure 3 As shown, the camera 21 may include a photosensitive element 211 and an imaging lens 212 disposed on the photosensitive side of the photosensitive element 211, such that the reflected scattered light first passes through the imaging lens 212 and is then received by the photosensitive element 211 for imaging. It is understood that the photosensitive element 211 is implemented as a high-resolution sensor in order to obtain clearer images of defects.

[0083] It is worth noting that, in addition to having different materials, the surface W to be inspected also has an irregular shape and a height difference. Therefore, existing industrial cameras, being fixed-focus, can only capture images within a certain depth range (beyond which the image becomes blurry), and cannot clearly image complex surfaces with varying depths. To solve this problem, such as... Figure 4As shown, the camera 21 of the controllable imaging system 1 of this application may further include a focusing component 213. The focusing component 213 is used to adjust the imaging focal length of the camera 21 to focus on different height surfaces on the surface to be inspected, according to a look-up table (LUT) of the surface to be inspected W, so that the camera 21 can obtain multiple images of the surface to be inspected at different depths. It is understood that because the focusing component 213 can adjust the imaging focal length of the camera 21 to focus on different height surfaces on the surface to be inspected, the camera 21 can clearly acquire images of different height surfaces on the surface to be inspected, thereby obtaining multiple clear images of different depths, facilitating subsequent defect identification.

[0084] Optionally, such as Figure 4 As shown, the focusing component 213 of this application can be, but is not limited to, implemented as a liquid lens 2130. The liquid lens 2130 is correspondingly disposed on the imaging lens 212 to form a liquid lens. Focusing is achieved by adjusting the focal length of the liquid lens 2130, allowing for rapid focusing onto the surface at the corresponding height on the surface to be detected, based on a lookup table of the height difference of the surface to be detected W, thereby obtaining a clear image. It is understood that the liquid lens 2130 of this application features fast focusing speed and small device size, making it well-suited for image acquisition operations on the surface to be detected W.

[0085] Of course, in other examples of this application, the focusing component 213 may also be implemented as a drive motor (not shown in the figure) set on the imaging lens 212, and the imaging focal length of the camera 21 can still be adjusted by the drive motor. This application will not elaborate further on this.

[0086] For example, in one application example of this application, for a surface structure map of a certain type of engine, a height difference LUT of the engine surface (i.e., the surface W to be detected) is obtained. Based on the LUT data, three depth planes (i.e., three surfaces at different heights) can be obtained, such as... Figure 4 The three dashed boxes shown; by controlling the focusing component 213 on the PC so that the camera 21 focuses on the three depth planes respectively to acquire image information of the engine surface, clear images of the three depths can be obtained.

[0087] It is worth noting that the above-mentioned solutions all obtain a clear defect image (i.e., a preliminary image) initially through physical means. To further improve image quality, the controllable imaging system 1 of this application can further perform exposure processing on the obtained preliminary image at the algorithm level to compensate for the shortcomings of physical exposure. It is understood that the preliminary image of this application may include a defect image obtained by using a polarization selection method; it may also include a defect image obtained by using a mask; and it may also include defect images of different depths obtained by combining a focusing component.

[0088] Specifically, such as Figure 1 and Figure 4 As shown, the controllable imaging system 1 of this application may further include an image processing unit 40, which is communicatively connected to the image acquisition unit 20. The image processing unit 40 is used to perform exposure compensation processing on the preliminary image obtained by the image acquisition unit 20 to obtain a higher quality defect image as the final defect image, which helps to improve the efficiency and accuracy of subsequent defect identification.

[0089] More specifically, in one example of this application, such as Figure 5 As shown, the image processing unit 40 may include an acquisition module 41, an extraction module 42, and a fusion module 43 that are communicatively connected to each other. The acquisition module 41 is communicatively connected to the image acquisition unit 20 and is used to acquire multiple preliminary images with different exposure levels acquired by the image acquisition unit 20. The extraction module 42 is used to extract normally exposed areas from each preliminary image acquired by the acquisition module 41 through image stabilization and feature region recognition to obtain multiple images of areas to be fused. The fusion module 43 is used to fuse these multiple images of areas to be fused using high dynamic range imaging to obtain a fused image as the final defect image. It is understood that the normally exposed area mentioned in this application refers to the area in the preliminary image that is neither overexposed nor underexposed, that is, the area in the preliminary image with a relatively good exposure state. For example, as... Figure 6 As shown, high dynamic range (HDR) imaging is performed on the three preliminary images with different exposure values ​​to obtain an image with better overall exposure as the final defect image, which facilitates subsequent surface defect identification.

[0090] It is worth noting that in another example of this application, such as Figure 7As shown, the image processing unit 40 may also include an acquisition module 41, a correction module 44, and an enhancement module 45 that are communicatively connected to each other. The acquisition module 41 is communicatively connected to the image acquisition unit 20 and is used to acquire an unexposed image acquired by the image acquisition unit 20. The correction module 44 is used to perform gamma correction on the unexposed image to obtain a corrected image. The enhancement module 45 is used to perform contrast curve enhancement on the corrected image to obtain a contrast-enhanced image as the final defect image.

[0091] It is understood that the non-overexposed image mentioned in this application refers to an underexposed image or a normally exposed image, in order to preserve the image's detail information as much as possible, because overexposure will cause the loss of detail information. In addition, the gamma correction in this application is gamma correction, which is a shadow enhancement algorithm that can brighten the shadow areas of the paint surface without losing detail information.

[0092] For example, such as Figure 8 As shown, a single image without overexposure is acquired to preserve as much detail as possible; shadow enhancement is performed through gamma correction to brighten the dark areas of the paint surface without losing detail; finally, contrast curve enhancement is applied to obtain an image with better contrast between the defect and the background, which is the final defect image.

[0093] It is worth noting that, in addition to correcting the initial image, the correction module 44 of this application can also perform minimal gamma correction on the image fused by the fusion module 43 to obtain a higher quality defect image. Similarly, the extraction module 42 of this application can extract not only the initial image but also the image enhanced by the enhancement module 45, and then fuse it through the fusion module 43 to obtain a higher quality defect image. In other words, the image processing units in the two examples above can be used individually or in combination, and when used in combination, their order can be interchanged, both achieving the effect of improving the quality of the defect image.

[0094] It is worth mentioning that, such as Figure 9 As shown, according to one embodiment of this application, a controllable imaging method is further provided, which may include the steps of:

[0095] S100: Emits illumination light to illuminate the surface to be inspected;

[0096] S200: Based on the light scattering differences of the surface to be tested, adjust the relative exposure of different materials on the surface to be tested to reduce the exposure differences between the different materials on the surface to be tested; and

[0097] S300: Receives the scattered light reflected back from the surface to be detected in order to acquire image information of the surface to be detected.

[0098] For example, such as Figure 10 As shown, step S200 of the controlled imaging method may include the following steps:

[0099] S210: Based on the difference in polarization state degradation of the scattered light, select the polarization state of the received light to adjust the relative exposure of different materials on the surface to be tested.

[0100] Of course, such as Figure 10 As shown, step S200 of this controlled imaging method may also include the following steps:

[0101] S210': Based on the distribution of polished surfaces and sandblasted surfaces on the surface to be tested, a transmittance mask is made, wherein the transmittance mask has a first region corresponding to the polished surface of the surface to be tested and a second region corresponding to the sandblasted surface of the surface to be tested, and the transmittance of the first region is less than the transmittance of the second region.

[0102] S220': The illumination light passes through the first and second regions of the transmittance mask, respectively, to the polished and frosted surfaces of the surface to be inspected; and

[0103] S230': The first and second regions of the transmittance mask respectively transmit the scattered light reflected back from the polished and frosted surfaces to be received and imaged.

[0104] It is worth noting that, according to one embodiment of this application, such as Figure 9 As shown, this controlled imaging method may further include the following steps:

[0105] S400: According to the height difference lookup table of the surface to be inspected, adjust the imaging focal length to focus on the surface at different heights on the surface to be inspected, so as to obtain multiple images of the surface at different depths.

[0106] Furthermore, according to one embodiment of this application, such as Figure 9 As shown, this controlled imaging method may further include the following steps:

[0107] S500: Performs exposure compensation processing on the acquired image information to obtain the final defect image.

[0108] Exemplarily, in one example of this application, such as Figure 11 As shown, step S500 of the controlled imaging method may include the following steps:

[0109] S510: Acquire multiple preliminary images with different exposure levels;

[0110] S520: Extracts normally exposed areas from each initial image using image stabilization and feature region recognition to obtain multiple images of the areas to be merged; and

[0111] S530: The multiple images of the regions to be fused are fused using a high dynamic range imaging method to obtain a fused image as the final defect image.

[0112] Of course, in another example of this application, such as Figure 12 As shown, step S500 of this controlled imaging method may also include the following steps:

[0113] S510': Obtain an unexposed image;

[0114] S520': Perform gamma correction on the non-overexposed image to obtain a corrected image; and

[0115] S530': Perform contrast curve enhancement on the corrected image to obtain a contrast-enhanced image as the final defect image.

[0116] It is worth noting that the step numbers mentioned in this application are only for the convenience of describing the various steps of the controlled imaging method, and do not mean that the steps are performed in the order of the step numbers; in other words, the order of the various steps in the controlled imaging method can be reasonably adjusted as needed, as long as a high-quality defect image can be obtained, and this application will not elaborate on this further.

[0117] For example, such as Figure 13 As shown, taking the image acquisition of complex metal surfaces as an example: First, by selecting polarization or adding a mask that increases the transmittance difference in the region, the intensity of scattered light entering the camera from different material surfaces (polished or sandblasted) is controlled to initially obtain an image with uniform overall exposure; Second, based on the height difference information of the complex metal surface, a lookup table (LUT) is created by pre-recording data, and the liquid lens is driven by computer control to focus to the corresponding depth to acquire clear images at different depths; Finally, for the acquired image, gamma correction and / or HDR operations are performed using a software development kit (SDK) to enhance dark areas and overall contrast, so as to output a high-quality surface defect image as a deep learning sample or for defect recognition.

[0118] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0119] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this invention patent should be determined by the appended claims.

Claims

1. A controllable imaging method, characterized in that, The imaging is performed using a controllable imaging system to image the surface to be inspected. The controllable imaging system includes: An illumination unit is provided to emit illumination light to illuminate the surface to be inspected; wherein the surface to be inspected is a complex metallic surface that simultaneously contains both high reflectivity and low reflectivity surfaces. An image acquisition unit, configured to receive scattered light reflected back from the surface to be detected, thereby acquiring image information of the surface to be detected; and An exposure control unit is disposed in the optical path between the image acquisition unit and the illumination unit, and is used to control the relative exposure of different material surfaces on the surface to be tested according to the light scattering difference characteristics of the surface to be tested, so as to reduce the exposure difference of different material surfaces on the surface to be tested. The illumination unit is a polarized diffuse light source, which emits linearly polarized light so that the linearly polarized light, after being scattered by different materials on the surface to be tested, forms scattered light with differences in polarization state degradation. The exposure control unit is a polarizer, which is disposed in the receiving optical path of the image acquisition unit and is used to select the polarization state of the light entering the image acquisition unit according to the differences in polarization state degradation of the scattered light, so as to control the relative exposure of different materials on the surface to be tested. The polarized diffuse light source includes a polarized light source panel and a light-receiving aperture formed in the polarized light source panel. The receiving optical path of the image acquisition unit passes through the light-receiving aperture of the polarized diffuse light source and is used to receive the scattered light reflected back by the surface to be detected through the light-receiving aperture. The polarizer is fitted onto the front end of the lens of the image acquisition unit via a collar; The controlled imaging method includes the following steps: Illumination light is emitted to illuminate the surface to be inspected; wherein the surface to be inspected is a complex metallic surface that simultaneously contains both high reflectivity and low reflectivity surfaces; Based on the light scattering differences of the surface to be tested, the relative exposure of different materials on the surface to be tested is adjusted to reduce the exposure differences between the different materials on the surface to be tested; and The scattered light reflected back from the surface to be detected is received to acquire image information of the surface to be detected.

2. The controllable imaging method according to claim 1, characterized in that, The polarizer is disposed within the light-receiving aperture of the polarizing diffuse light source.

3. The controllable imaging method according to claim 1 or 2, characterized in that, The image acquisition unit is a camera, and the camera's lens has a diagonal field of view of 90° or greater.

4. The controllable imaging method according to claim 1 or 2, characterized in that, The image acquisition unit is a camera, which includes a photosensitive component, an imaging lens disposed on the photosensitive side of the photosensitive component, and a focusing component. The focusing component is used to adjust the imaging focal length of the camera to focus on different height surfaces on the surface to be detected according to a lookup table of the height difference of the surface to be detected.

5. The controllable imaging method according to claim 4, characterized in that, The focusing component is a liquid lens correspondingly disposed on the imaging lens, so as to focus and adjust the focus by means of the focal length of the liquid lens.

6. The controllable imaging method according to claim 1 or 2, characterized in that, The controlled imaging system further includes an image processing unit, which is communicatively connected to the image acquisition unit and is used to perform exposure compensation processing on the preliminary image obtained by the image acquisition unit to obtain the final defect image.

7. The controllable imaging method according to claim 6, characterized in that, The image processing unit includes an acquisition module, an extraction module, and a fusion module that are communicatively connected to each other. The acquisition module is communicatively connected to the image acquisition unit and is used to acquire multiple preliminary images with different exposure levels acquired by the image acquisition unit. The extraction module is used to extract normally exposed areas from each preliminary image acquired by the acquisition module through image stabilization and feature region recognition to obtain multiple images of areas to be fused. The fusion module is used to fuse multiple images of regions to be fused using a high dynamic range imaging method to obtain a fused image as the final defect image.

8. The controllable imaging method according to claim 6, characterized in that, The image processing unit includes an acquisition module, a correction module, and an enhancement module that are communicatively connected to each other. The acquisition module is communicatively connected to the image acquisition unit and is used to acquire an unexposed image acquired by the image acquisition unit. The correction module is used to perform gamma correction on the unexposed image to obtain a corrected image. The enhancement module is used to perform contrast curve enhancement on the corrected image to obtain a contrast-enhanced image as the final defect image.

9. The controllable imaging method according to claim 1, characterized in that, The controlled imaging method further includes the following steps: Based on the height difference lookup table of the surface to be inspected, the imaging focal length is adjusted to focus on different height surfaces on the surface to be inspected, so as to obtain multiple images of the surface to be inspected at different depths.

10. The controllable imaging method according to claim 1 or 9, characterized in that, The controlled imaging method further includes the following steps: Exposure compensation processing is performed on the acquired image information to obtain the final defect image.

11. The controllable imaging method according to claim 10, characterized in that, The step of performing exposure compensation processing on the acquired image information to obtain the final defective image includes the following steps: Acquire multiple preliminary images with different exposure levels; By using image stabilization and feature region recognition, the normally exposed area is extracted from each preliminary image to obtain multiple images of the areas to be fused. as well as The images of the multiple regions to be fused are fused using a high dynamic range imaging method to obtain a fused image as the final defect image.

12. The controllable imaging method according to claim 10, characterized in that, The step of performing exposure compensation processing on the acquired image information to obtain the final defective image includes the following steps: Obtain an unexposed image; Gamma correction is applied to the non-overexposed image to obtain the corrected image; as well as The contrast curve of the corrected image is then enhanced to obtain a contrast-enhanced image, which is then used as the final defect image.

Images