Vehicle body paint surface defect detection method and device, computer equipment and medium

Through deep learning technology of body digital model and image fusion, the image coordinates of the body paint defect detection camera are directly converted to the body coordinates, solving the problem that traditional detection relies on workers' experience and complex 3D reconstruction, and achieving efficient and accurate body paint surface Defect detection.

CN119086562AActive Publication Date: 2024-12-06SPEEDBOT ROBOTICS CO LTD

Patent Information

Application Number
CN202411183560.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-08-27
Publication Date
2024-12-06
Estimated Expiration
2044-08-27

AI Technical Summary

Technical Problem

Traditional body paint defect detection relies on workers' experience, the inspection accuracy and inefficiency are required, and complex 3D reconstruction processes are required, resulting in high cost and unstable accuracy.

Method used

By obtaining the digital model of the body and detecting the relative position relationship between the camera and the body, using image fusion and deep learning algorithms to detect paint defects, directly map the defect position under the camera coordinate system to the body coordinate system, and further convert it to the production line car To achieve efficient and accurate defect detection.

Benefits of technology

No complex 3D reconstruction is required, which significantly improves the efficiency of paint defect detection, reduces hardware cost and accuracy deviations, and achieves efficient and accurate body paint defect detection.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119086562A_ABST
    Figure CN119086562A_ABST
Patent Text Reader

Abstract

The invention relates to a vehicle body paint surface defect detection method and device, computer equipment, a storage medium and a computer program product, and the method comprises the steps: obtaining a vehicle body digital model; obtaining a relative position relation between the defect detection camera and the vehicle body and a relative position relation between the production line and the vehicle body; performing paint surface defect detection according to a production line vehicle body image acquired by the defect detection camera to obtain a paint surface defect position under a camera coordinate system; based on the relative position relation between the defect detection camera and the vehicle body, the paint surface defect position under the camera coordinate system is positioned to the vehicle body digital model, and the paint surface defect position under the vehicle body coordinate system is obtained; and according to the relative position relationship between the production line and the vehicle body, mapping the paint surface defect position under the vehicle body coordinate system to the production line vehicle body to obtain a paint surface defect detection result of the production line vehicle body.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the technical field of defect detection, and in particular to a method, apparatus, computer equipment, storage medium and computer program product for detecting vehicle body paint defects. Background Art

[0002] The aesthetics of the car body paint is a key component of automobile quality control and manufacturer brand marketing. However, during the spraying process of the car body surface, various defects are difficult to avoid. Generally, automobile manufacturers will inspect and repair the defects of the car body paint after spraying at the back end of the process, and the repair effect directly affects the final appearance quality of the car.

[0003] In traditional technology, most of the body paint defect inspection on production lines is completed by workers. The workers check the surface defects by visual inspection and touch, and repair them with grinding and polishing tools in subsequent operations.

[0004] Although the above traditional methods can realize the detection of paint defects on vehicle bodies and subsequent repairs, the detection and repair effects depend on the workers' experience and working conditions, and the detection accuracy and efficiency are low. Summary of the invention

[0005] Based on this, it is necessary to provide an efficient and accurate vehicle body paint defect detection method, device, computer equipment, storage medium and computer program product to address the above technical problems.

[0006] In a first aspect, the present application provides a method for detecting vehicle body paint defects. The method comprises:

[0007] Obtaining a digital model of the vehicle body;

[0008] Obtain the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body;

[0009] Perform paint defect detection based on the production line vehicle body image collected by the defect detection camera to obtain the paint defect position in the camera coordinate system;

[0010] Based on the relative position relationship between the defect detection camera and the vehicle body, the paint defect position in the camera coordinate system is located on the vehicle body digital model to obtain the paint defect position in the vehicle body coordinate system;

[0011] According to the relative position relationship between the production line and the vehicle body, the paint defect position in the vehicle body coordinate system is mapped to the production line vehicle body to obtain the paint defect detection result of the production line vehicle body.

[0012] In one embodiment, obtaining the relative position relationship between the defect detection camera and the vehicle body includes:

[0013] Acquire feature points of a calibration vehicle body captured by a defect detection camera, where the positions of the feature points on the calibration vehicle body are known;

[0014] Obtaining the positional relationship between the feature point and the defect detection camera through a camera optical model and ray tracing processing;

[0015] Based on the position of the feature point on the calibrated vehicle body and the positional relationship between the feature point and the defect detection camera, the relative positional relationship between the defect detection camera and the vehicle body is obtained.

[0016] In one embodiment, performing paint defect detection based on the production line vehicle body image captured by the defect detection camera to obtain the paint defect position in the camera coordinate system includes:

[0017] Acquire the production line vehicle body image captured by the defect detection camera;

[0018] Based on the vehicle body images of the production line, image fusion and deep learning algorithms are used to perform paint defect detection to obtain the paint defect positions in the camera coordinate system.

[0019] In one embodiment, the paint defect detection is performed based on the production line vehicle body image using image fusion and deep learning algorithm to obtain the paint defect position in the camera coordinate system, including:

[0020] Selecting the production line vehicle body images collected at adjacent times;

[0021] Perform defect enhancement processing on the selected vehicle body image through an image fusion algorithm to obtain a fused image;

[0022] The fused image is input into a trained deep learning model for paint defect detection to obtain the paint defect position in the camera coordinate system.

[0023] In one embodiment, obtaining the digital model of the vehicle body includes:

[0024] Obtain body appearance mapping data;

[0025] Based on the body appearance mapping data, a body digital model is constructed.

[0026] In one embodiment, according to the relative position relationship between the production line and the vehicle body, after mapping the paint defect position in the vehicle body coordinate system to the production line vehicle body and obtaining the paint defect detection result of the production line vehicle body, the method further includes:

[0027] The paint defect detection result of the production line vehicle body is sent to the paint defect repair device.

[0028] In one of the embodiments, the production line vehicle body image includes a plurality of 2D production line vehicle body images acquired continuously in time.

[0029] In a second aspect, the present application also provides a vehicle body paint defect detection device. The device comprises:

[0030] A digital model acquisition module is used to acquire a digital model of a vehicle body;

[0031] A relative position relationship acquisition module is used to obtain the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body;

[0032] A defect detection module, used to perform paint defect detection based on the production line body image collected by the defect detection camera, and obtain the paint defect position in the camera coordinate system;

[0033] A first mapping module is used to locate the paint defect position in the camera coordinate system to the vehicle body digital model based on the relative position relationship between the defect detection camera and the vehicle body, so as to obtain the paint defect position in the vehicle body coordinate system;

[0034] The second mapping module is used to map the paint defect position in the vehicle body coordinate system to the production line vehicle body according to the relative position relationship between the production line and the vehicle body, so as to obtain the paint defect detection result of the production line vehicle body.

[0035] In a third aspect, the present application further provides a computer device. The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the following steps when executing the computer program:

[0036] Obtaining a digital model of the vehicle body;

[0037] Obtain the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body;

[0038] Perform paint defect detection based on the production line vehicle body image collected by the defect detection camera to obtain the paint defect position in the camera coordinate system;

[0039] Based on the relative position relationship between the defect detection camera and the vehicle body, the paint defect position in the camera coordinate system is located on the vehicle body digital model to obtain the paint defect position in the vehicle body coordinate system;

[0040] According to the relative position relationship between the production line and the vehicle body, the paint defect position in the vehicle body coordinate system is mapped to the production line vehicle body to obtain the paint defect detection result of the production line vehicle body.

[0041] In a fourth aspect, the present application further provides a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0042] Obtaining a digital model of the vehicle body;

[0043] Obtain the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body;

[0044] Perform paint defect detection based on the production line vehicle body image collected by the defect detection camera to obtain the paint defect position in the camera coordinate system;

[0045] Based on the relative position relationship between the defect detection camera and the vehicle body, the paint defect position in the camera coordinate system is located on the vehicle body digital model to obtain the paint defect position in the vehicle body coordinate system;

[0046] According to the relative position relationship between the production line and the vehicle body, the paint defect position in the vehicle body coordinate system is mapped to the production line vehicle body to obtain the paint defect detection result of the production line vehicle body.

[0047] In a fifth aspect, the present application further provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0048] Obtaining a digital model of the vehicle body;

[0049] Obtain the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body;

[0050] Perform paint defect detection based on the production line vehicle body image collected by the defect detection camera to obtain the paint defect position in the camera coordinate system;

[0051] Based on the relative position relationship between the defect detection camera and the vehicle body, the paint defect position in the camera coordinate system is located on the vehicle body digital model to obtain the paint defect position in the vehicle body coordinate system;

[0052] According to the relative position relationship between the production line and the vehicle body, the paint defect position in the vehicle body coordinate system is mapped to the production line vehicle body to obtain the paint defect detection result of the production line vehicle body.

[0053] The above-mentioned vehicle body paint defect detection method, device, computer equipment, storage medium and computer program product obtain a vehicle body digital model; obtain the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body; perform paint defect detection based on the production line vehicle body image collected by the defect detection camera to obtain the paint defect position in the camera coordinate system; based on the relative position relationship between the defect detection camera and the vehicle body, locate the paint defect position in the camera coordinate system to the vehicle body digital model to obtain the paint defect position in the vehicle body coordinate system; based on the relative position relationship between the production line and the vehicle body, map the paint defect position in the vehicle body coordinate system to the production line vehicle body to obtain the paint defect detection result of the production line vehicle body. In the whole process, based on the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body, the paint defect position in the camera coordinate system is mapped to the production line vehicle body, without the need for complex 3D reconstruction, which significantly improves the efficiency of paint defect detection. Therefore, the whole solution can achieve efficient and accurate paint defect detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] Figure 1 A diagram showing an application environment of a vehicle body paint defect detection method in an embodiment;

[0055] Figure 2 A schematic diagram of a process of detecting vehicle body paint defects in one embodiment;

[0056] Figure 3 The image of the car body on the production line captured by the defect detection camera;

[0057] Figure 4 It is a schematic diagram of defect locations in the digital model of the vehicle body;

[0058] Figure 5 A schematic diagram of a process of detecting vehicle body paint defects in another embodiment;

[0059] Figure 6 is a structural block diagram of a vehicle body paint defect detection device in one embodiment;

[0060] Figure 7 FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0061] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] The vehicle body paint defect detection method provided in the embodiment of the present application can be applied to Figure 1In the application environment shown. Among them, the entire vehicle body paint defect detection and repair system includes a detection device 102, a defect detection camera 104 and a paint repair device 106; the defect detection camera 104 captures the image of the actual vehicle body on the production line, and sends the production line vehicle body image to the vehicle body paint defect detection device; the vehicle body paint defect detection device obtains the vehicle body digital model; obtains the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body; performs paint defect detection according to the production line vehicle body image collected by the defect detection camera, and obtains the paint defect position in the camera coordinate system; based on the relative position relationship between the defect detection camera and the vehicle body, locates the paint defect position in the camera coordinate system to the vehicle body digital model, and obtains the paint defect position in the vehicle body coordinate system; according to the relative position relationship between the production line and the vehicle body, maps the paint defect position in the vehicle body coordinate system to the production line vehicle body, and obtains the paint defect detection result of the production line vehicle body; further, the detection device 102 sends the paint defect detection result of the production line vehicle body to the paint repair device 106, so that the paint repair device 106 performs paint repair on the actual vehicle body on the production line.

[0063] In one embodiment, Figure 2 As shown, a method for detecting defects on a vehicle body paint surface is provided. Figure 1 Taking the detection device 102 in the example as an example, the method includes the following steps:

[0064] S100: Obtain a vehicle body digital model.

[0065] The digital model of the vehicle body is established using computer technology and simulation software to describe the three-dimensional digital representation of the vehicle body and its related components. It is the core of the development of the entire vehicle product, and is closely combined with the actual vehicle test for verification and optimization throughout the research and development process. Specifically, the digital model of the vehicle body to be tested can be obtained by obtaining the design model or surveying the actual vehicle. Generally speaking, the digital model of the vehicle body is generally directly taken from the design CAD model data of the automobile manufacturer, or a corresponding one-to-one digital model is obtained by measuring the appearance of the actual vehicle body.

[0066] S200: Obtaining the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body.

[0067] The relative position relationship between the defect detection camera and the vehicle body refers to the relative position relationship between the defect detection camera and the vehicle body. That is, the relative position relationship between the defect detection camera and the vehicle body when the vehicle body image is captured. The relative position relationship between the production line and the vehicle body refers to the relative position between the vehicle body and the production line during the actual production line generation process. Specifically, the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body here can be understood as the digital environment of the production line and the vehicle body. Here, in order to map the defects detected by the defect detection camera to the vehicle body of the actual production line, it is necessary to establish the digital environment of the defect detection camera, the vehicle, and the production line in advance.

[0068] S300: performing paint defect detection based on the production line vehicle body image collected by the defect detection camera to obtain the paint defect position in the camera coordinate system.

[0069] Paint defect detection is performed based on the production line body image captured by the defect detection camera. Specifically, the image fusion and deep learning methods can be used to detect paint defects on the production line body image to obtain the paint defect position. The paint defect position obtained here is the paint defect position in the camera coordinate system, that is, the defect position relative to the defect detection camera coordinate system is obtained. Specifically, the production line body image can be multiple 2D production line body images continuously captured by the defect detection camera.

[0070] S400: Based on the relative position relationship between the defect detection camera and the vehicle body, the paint defect position in the camera coordinate system is located on the vehicle body digital model to obtain the paint defect position in the vehicle body coordinate system.

[0071] Based on the relative position relationship between the defect detection camera and the vehicle body obtained in S300, the paint defect position in the camera coordinate system is located on the vehicle body digital model. Figure 3 and Figure 4 As shown, Figure 3 The following is an image of the car body on the production line captured by the defect detection camera. Based on this image, the following Figure 3 The defect position in the green rectangular frame is then located on the digital model of the vehicle body based on the relative position relationship between the defect detection camera and the vehicle body. Figure 4 The defect position shown in the digital model of the vehicle body is the paint defect position in the vehicle body coordinate system.

[0072] S500: According to the relative position relationship between the production line and the vehicle body, the paint defect position in the vehicle body coordinate system is mapped to the production line vehicle body, and the paint defect detection result of the production line vehicle body is obtained.

[0073] Then, based on the relative position relationship between the production line and the vehicle body, the paint defect position in the vehicle body coordinate system is mapped to the production line vehicle body, that is, the paint defect position is converted to the actual vehicle body on the production line, and the paint defect detection result of the production line vehicle body is obtained. The paint defect detection of the production line vehicle body is completed. In subsequent operations, the paint defect detection result of the production line vehicle body can be sent to the paint defect repair device, and the paint defect repair device will automatically repair the actual vehicle body on the production line.

[0074] In one embodiment, obtaining the relative position relationship between the defect detection camera and the vehicle body includes:

[0075] The feature points of the calibration vehicle body captured by the defect detection camera are obtained, and the positions of the feature points on the calibration vehicle body are known. The positional relationship between the feature points and the defect detection camera is obtained through the camera optical model and ray tracing processing. Based on the positions of the feature points on the calibration vehicle body and the positional relationship between the feature points and the defect detection camera, the relative positional relationship between the defect detection camera and the vehicle body is obtained.

[0076] Specifically, the process of obtaining the relative position relationship between the defect detection camera and the vehicle body can be summarized as follows:

[0077] 1) Calibrate the body feature points: First, select a series of feature points on the calibration body, the positions of these feature points on the body are known. These feature points can be fixed structural points, landmark points or specially designed calibration points of the body.

[0078] 2) Obtain feature point images: Use a defect detection camera to capture images containing these calibrated vehicle body feature points. Ensure that the feature point images captured by the camera are clear and recognizable.

[0079] 3) Camera optical model and ray tracing processing: Apply camera optical model (such as pinhole imaging model) and ray tracing technology to process the captured image. Through the method of ray intersection, connect the feature points in the image with the optical center of the camera, and simulate the emission of light until it intersects with the external object to be measured (i.e. the vehicle body). The intersection point is the point on the actual vehicle body corresponding to the feature point in the image.

[0080] 4) Position relationship calculation: Based on the camera optical model and ray tracing results, the position relationship (i.e., three-dimensional coordinates) between the feature points in the image and the defect detection camera is calculated. Combined with the known position of the feature points on the calibrated vehicle body, the relative position relationship between the defect detection camera and the vehicle body can be derived.

[0081] like Figure 5 As shown, in one embodiment, S300 includes:

[0082] S320: Acquire the production line vehicle body image captured by the defect detection camera.

[0083] Use the preset defect detection camera to capture images of the car body on the production line. Make sure the camera can capture the entire paint surface of the car body and the image clarity and resolution are high enough for subsequent accurate defect detection.

[0084] S340: Based on the production line body image, the paint defect detection is performed using image fusion and deep learning algorithms to obtain the paint defect position in the camera coordinate system.

[0085] Before defect detection, the captured images can be preprocessed. This includes but is not limited to steps such as image denoising, contrast enhancement, and color correction to improve image quality and reduce the impact of noise and interference factors on subsequent detection. Image fusion is the process of combining useful information from multiple images to generate an image containing more information. In paint defect detection, image fusion can help inspectors or algorithms observe the paint condition of the vehicle body more comprehensively and improve the accuracy and reliability of detection. Use pre-trained deep learning algorithms to perform paint defect detection on preprocessed and / or fused images. Deep learning algorithms, such as convolutional neural networks (CNNs), can learn the characteristics and patterns of paint defects from a large amount of training data and accurately identify and locate these defects in new images. After processing by the deep learning algorithm, the paint defect position in the camera coordinate system will be obtained. This position information is usually given in the form of pixel coordinates or coordinates in the image coordinate system. In order to convert this position information into a more intuitive and easy-to-understand coordinate system (such as the vehicle body coordinate system or the actual ground coordinate system) in practical applications, camera calibration technology and other space conversion algorithms may be required.

[0086] In one embodiment, based on the production line vehicle body image, the paint defect detection is performed using image fusion and deep learning algorithm, and the paint defect position in the camera coordinate system is obtained, including:

[0087] Step 1: Select the production line body images collected at adjacent times.

[0088] From the defect detection cameras on the production line, select the production line body images collected at adjacent times. These images should include the paint surface of the body, and there should be a certain overlap or continuity between the images collected at adjacent times to facilitate subsequent image fusion.

[0089] Step 2: Perform defect enhancement processing on the selected vehicle body image through an image fusion algorithm to obtain a fused image; input the fused image into a trained paint defect detection deep learning model to obtain the paint defect position in the camera coordinate system.

[0090] Image fusion algorithms can fuse useful information from multiple images, enhance information in defective areas, and improve detection accuracy. Commonly used image fusion algorithms include pixel-based weighted average methods, feature-based methods, and so on. During the fusion process, appropriate fusion algorithms and parameter settings can be selected according to the characteristics of the image and the needs of defect detection. For example, adjustments can be made based on factors such as the image's lighting conditions and noise levels to achieve better fusion effects. After image fusion processing, a fused image is obtained. This image contains useful information from multiple images collected at adjacent times, and the defective area is enhanced, making it easier for subsequent deep learning algorithms to detect. The fused image is input into a trained deep learning model for paint defect detection. This model should be trained for paint defect detection tasks and be able to identify and locate paint defects in images. Specifically, deep learning architectures such as convolutional neural networks (CNNs) can be used to train with a large amount of labeled data so that the model can learn the characteristics and patterns of paint defects. During the training process, appropriate optimization algorithms and loss functions can be used to improve the detection performance and generalization ability of the model. After the deep learning model processes the fused image, it outputs the paint defect position in the camera coordinate system.

[0091] In one embodiment, obtaining the digital model of the vehicle body includes:

[0092] Step 1: Obtain vehicle body appearance mapping data.

[0093] Before building a digital model of the vehicle body, you first need to obtain the appearance mapping data of the vehicle body. This is usually achieved in the following ways: 3D scanning: Use a high-precision 3D scanner to scan the vehicle body and obtain point cloud data on the surface of the vehicle body. These point cloud data record the 3D coordinate information of each point on the surface of the vehicle body. Measuring tools: Use traditional measuring tools such as calipers and gauges to measure the key dimensions and features of the vehicle body and record the measurement results. Photogrammetry: Use a multi-camera system or stereo vision technology to take multi-angle photos of the vehicle body and combine them with image processing algorithms to obtain the 3D shape data of the vehicle body.

[0094] Step 2: Build a digital model of the vehicle body based on the vehicle body appearance mapping data.

[0095] The construction of a digital model of the vehicle body specifically includes the following stages: 1) Data preprocessing: Clean, denoise, and smooth the acquired point cloud data or measurement data to improve the accuracy and reliability of the data. 2) Feature extraction: Extract key features and dimensions of the vehicle body, such as edges, curvatures, holes, etc., from the processed data. 3) Model construction: Based on the extracted features and dimensions, use 3D modeling software (such as SolidWorks, CATIA, UG, etc.) or reverse engineering software (such as Geomagic, PolyWorks, etc.) to build a 3D digital model of the vehicle body. During the construction process, curve fitting, surface reconstruction and other technologies can be used to ensure the accuracy and precision of the model. 4) Model optimization: Optimize the constructed 3D digital model, such as repairing small defects, smoothing transition surfaces, etc., to improve the quality and usability of the model.

[0096] In general, the above-mentioned vehicle body paint defect detection method has the following significant technical advantages over the existing technology: after traditional 3D captures 2D camera images, it needs to undergo 3D reconstruction to obtain the location of the defect point, and the accuracy of 3D reconstruction is affected by factors such as 3D camera performance, surrounding environment, and material of the captured object, which has a great impact on the deviation of the defect point position. To achieve high precision, expensive 3D equipment and a harsh installation and production environment are required, which are difficult for ordinary production lines and manufacturers to accept. The biggest improvement of this application is to convert the complex and sensitive 3D reconstruction process into a digital twin mapping process of the 2D camera and the vehicle body. By constructing the position relationship between the camera and the vehicle body in advance, the camera optical model and the vehicle body position are used to map the 2D defects to the vehicle body through digital ray tracing. This process reduces the complexity of the workflow, is not affected by reconstruction factors, saves hardware costs, and can meet high-precision conversion requirements.

[0097] It should be understood that, although the steps in the flowcharts involved in the above embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0098] Based on the same inventive concept, the embodiment of the present application also provides a vehicle body paint defect detection device for implementing the vehicle body paint defect detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more vehicle body paint defect detection device embodiments provided below can refer to the limitations of the vehicle body paint defect detection method above, and will not be repeated here.

[0099] In one embodiment, Figure 6 As shown, a vehicle body paint defect detection device is provided, comprising:

[0100] A digital model acquisition module 100 is used to acquire a digital model of a vehicle body;

[0101] The relative position relationship acquisition module 200 is used to acquire the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body;

[0102] The defect detection module 300 is used to detect paint defects based on the production line body image collected by the defect detection camera, and obtain the paint defect position in the camera coordinate system;

[0103] The first mapping module 400 is used to locate the paint defect position in the camera coordinate system to the vehicle body digital model based on the relative position relationship between the defect detection camera and the vehicle body, so as to obtain the paint defect position in the vehicle body coordinate system;

[0104] The second mapping module 500 is used to map the paint defect position in the vehicle body coordinate system to the production line vehicle body according to the relative position relationship between the production line and the vehicle body, so as to obtain the paint defect detection result of the production line vehicle body.

[0105] In one of the embodiments, the relative position relationship acquisition module 200 is also used to obtain feature points of the calibrated vehicle body captured by the defect detection camera, and the position of the feature points on the calibrated vehicle body is known; the position relationship between the feature points and the defect detection camera is obtained through the camera optical model and ray tracing processing; based on the position of the feature points on the calibrated vehicle body and the position relationship between the feature points and the defect detection camera, the relative position relationship between the defect detection camera and the vehicle body is obtained.

[0106] In one of the embodiments, the defect detection module 300 is also used to obtain the production line body image captured by the defect detection camera; based on the production line body image, image fusion and deep learning algorithm are used to perform paint defect detection to obtain the paint defect position in the camera coordinate system.

[0107] In one embodiment, the defect detection module 300 is also used to select production line body images collected at adjacent times; perform defect enhancement processing on the selected body images through an image fusion algorithm to obtain a fused image; and input the fused image into a trained paint defect detection deep learning model to obtain the paint defect position in the camera coordinate system.

[0108] In one embodiment, the digital model acquisition module 100 is further used to acquire vehicle body appearance mapping data; and construct a vehicle body digital model based on the vehicle body appearance mapping data.

[0109] In one of the embodiments, the above-mentioned vehicle body paint defect detection device also includes: a sending module, used to send the paint defect detection result of the production line vehicle body to the paint defect repair device.

[0110] In one embodiment, the production line vehicle body image includes a plurality of 2D production line vehicle body images acquired continuously in time.

[0111] Each module in the above-mentioned vehicle body paint defect detection device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute the operations corresponding to each of the above modules.

[0112] In one embodiment, a computer device is provided. The computer device may be a terminal, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be achieved through WIFI, a mobile cellular network, NFC (near field communication) or other technologies. When the computer program is executed by the processor, a method for detecting defects on a vehicle body paint surface is implemented. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covered on the display screen, or a button, a trackball or a touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0113] Those skilled in the art will understand that Figure 7The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0114] In one embodiment, a computer device is provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the above-mentioned vehicle body paint defect detection method when executing the computer program.

[0115] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned vehicle body paint defect detection method is implemented.

[0116] In one embodiment, a computer program product is provided, including a computer program, which implements the above-mentioned vehicle body paint defect detection method when executed by a processor.

[0117] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the above-mentioned computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0118] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, 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-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A method for detecting defects on a vehicle body paint surface, characterized in that: The method comprises: Obtaining a digital model of the vehicle body; Obtain the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body; Perform paint defect detection based on the production line vehicle body image collected by the defect detection camera to obtain the paint defect position in the camera coordinate system; Based on the relative position relationship between the defect detection camera and the vehicle body, the paint defect position in the camera coordinate system is located on the vehicle body digital model to obtain the paint defect position in the vehicle body coordinate system; According to the relative position relationship between the production line and the vehicle body, the paint defect position in the vehicle body coordinate system is mapped to the production line vehicle body to obtain the paint defect detection result of the production line vehicle body.

2. The method according to claim 1, characterized in that Obtaining the relative position relationship between the defect detection camera and the vehicle body includes: Acquire feature points of a calibration vehicle body captured by a defect detection camera, where the positions of the feature points on the calibration vehicle body are known; Obtaining the positional relationship between the feature point and the defect detection camera through a camera optical model and ray tracing processing; Based on the position of the feature point on the calibrated vehicle body and the positional relationship between the feature point and the defect detection camera, the relative positional relationship between the defect detection camera and the vehicle body is obtained.

3. The method according to claim 1, characterized in that The paint defect detection is performed based on the production line vehicle body image collected by the defect detection camera to obtain the paint defect position in the camera coordinate system, including: Acquire the production line vehicle body image captured by the defect detection camera; Based on the vehicle body images of the production line, image fusion and deep learning algorithms are used to perform paint defect detection to obtain the paint defect positions in the camera coordinate system.

4. The method according to claim 1, characterized in that: Based on the production line vehicle body image, the paint defect detection is performed using image fusion and deep learning algorithm to obtain the paint defect position in the camera coordinate system, including: Selecting the production line vehicle body images collected at adjacent times; Perform defect enhancement processing on the selected vehicle body image through an image fusion algorithm to obtain a fused image; The fused image is input into a trained deep learning model for paint defect detection to obtain the paint defect position in the camera coordinate system.

5. The method according to claim 1, characterized in that: The obtaining of the vehicle body digital model comprises: Obtain body appearance mapping data; Based on the body appearance mapping data, a body digital model is constructed.

6. The method according to claim 1, characterized in that After mapping the paint defect position in the body coordinate system to the production line body according to the relative position relationship between the production line and the body, and obtaining the paint defect detection result of the production line body, the method further includes: The paint defect detection result of the production line vehicle body is sent to the paint defect repair device.

7. The method according to claim 1, characterized in that The production line vehicle body image includes a plurality of 2D production line vehicle body images acquired in succession.

8. A vehicle body paint defect detection device, characterized in that: The device comprises: A digital model acquisition module is used to acquire a digital model of a vehicle body; A relative position relationship acquisition module is used to obtain the relative position relationship between the defect detection camera and the vehicle body, and the relative position relationship between the production line and the vehicle body; A defect detection module, used to perform paint defect detection based on the production line body image collected by the defect detection camera, and obtain the paint defect position in the camera coordinate system; A first mapping module is used to locate the paint defect position in the camera coordinate system to the vehicle body digital model based on the relative position relationship between the defect detection camera and the vehicle body, so as to obtain the paint defect position in the vehicle body coordinate system; The second mapping module is used to map the paint defect position in the vehicle body coordinate system to the production line vehicle body according to the relative position relationship between the production line and the vehicle body, so as to obtain the paint defect detection result of the production line vehicle body.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Citation Information

Patent Citations

  • Intelligent detecting and polishing system and method for automobile body paint surface defects

    CN114720475A

  • Panoramic calibration method and related device, equipment, system and medium

    CN115601450A

  • Vehicle defect positioning system, method and device and storage medium

    CN116148259A

  • Vehicle body paint surface defect video detection method and video detection system

    CN116930187A

  • Image mapping to vehicle surfaces

    GB2591445A

Cited By

  • Paint surface defect detection method, medium and equipment

    CN119959221A

  • Method and system for back projection of 2D defect to 3D digital model

    CN121414571A