Visual scanning point collecting device

Abstract

The utility model provides a visual scanning point acquisition device, comprising an image acquisition device comprising a high-resolution industrial camera and a light source; the positioning device comprises a high-precision pose sensor and is used for detecting the pose and position information of the industrial camera in real time; the moving assembly is used for driving the high-resolution industrial camera to perform spatial position change; and the central control assembly is connected with the image acquisition device, the positioning device and the moving assembly, and is used for controlling the visual scanning point acquisition device to automatically work and processing and outputting the circuit board image. By using the visual scanning point acquisition device, high-precision and high-efficiency acquisition of the PCB can be realized.

Description

Technical Field

[0001] The utility model relates to the field of circuit board manufacturing, in particular to a visual scanning and point sampling device. Background Art

[0002] In the modern electronic manufacturing industry, printed circuit boards (PCBs) are key components in electronic devices. As the basic platform for electronic products, they carry the installation and electrical connection of electronic components. Their design and manufacturing quality directly determine the stability and performance of electronic products.

[0003] Traditional PCB inspection and drawing methods mainly rely on manual use of computer image processing software. This method has the following significant disadvantages: low efficiency, manual image processing requires a lot of time and effort, especially when dealing with complex circuit designs, the efficiency of manual methods is difficult to meet the high-efficiency requirements of modern electronic manufacturing; high cost, manual operations require highly skilled labor, and the training and employment costs are high. With the rapid replacement of electronic products, the requirements for manual operations are further improved, resulting in an increase in the overall production cost; unstable accuracy, the accuracy of manual processing depends on the experience and skill level of the operator, and the processing results of different operators may vary greatly, unable to ensure the consistency and high accuracy of each processing result. This instability of accuracy has an adverse impact on the manufacturing of high-demand electronic products.

[0004] With the diversification and complexity of electronic products, it has become particularly important to quickly and accurately identify and draw PCB circuit board solutions. In the prior art, although some automated devices have emerged for image acquisition and processing of PCBs, most of these devices rely on simple image recognition algorithms. They use industrial cameras to directly take pictures of PCBs, and then perform image recognition to generate corresponding circuit diagrams, and then manual comparison and correction of details are required. This method has poor processing effects when facing circuit boards with fine and complex structures. These devices also have deficiencies in positioning accuracy and image processing speed, and cannot meet the requirements of high precision and fast processing. Summary of the Utility Model

[0005] To solve the problems existing in the prior art, the utility model provides a visual scanning and point sampling device, which introduces a high-precision positioning device and adopts the logic of local image acquisition and then stitching to collect images of the circuit board, and can perform high-precision and fast recognition on circuit boards with a relatively high degree of complexity.

[0006] To achieve the above object, the utility model adopts the following scheme:

[0007] The utility model provides a visual scanning and point sampling device, comprising:

[0008] An image acquisition device, comprising a high-resolution industrial camera and a light source;

[0009] A positioning device, including high-precision pose sensing, is used to detect the pose and position information of an industrial camera in real time;

[0010] A moving component is used to drive the high-resolution industrial camera to change its spatial position;

[0011] A central control component is connected to the image acquisition device, the positioning device, and the moving component, and is used to control the automatic operation of the visual scanning and sampling device and process and output the circuit board image.

[0012] In some embodiments, the high-precision pose sensing includes an inertial measurement unit and a displacement sensor. The inertial measurement unit is disposed on the high-resolution industrial camera and is used to detect the pose information of the industrial camera; the displacement sensor is disposed on the moving component and is used to detect the position information of the industrial camera.

[0013] In some embodiments, the displacement sensor is an encoder or a laser displacement sensor.

[0014] In some embodiments, the color temperature and brightness of the light source are adjustable, and the central control component adjusts the color temperature and brightness of the light source in real time according to the image collected by the high-resolution industrial camera to ensure uniform brightness of the collected image.

[0015] In some embodiments, the light source is an annular light source for providing uniform illumination.

[0016] In some embodiments, a light homogenizing plate is further included and is disposed on the light emitting surface of the light source to further make the illumination uniform.

[0017] In some embodiments, the moving component includes a high-precision linear guide and a translation platform. The image acquisition device is disposed on the translation platform and is driven by the high-precision linear guide to perform displacement.

[0018] In some embodiments, the moving component further includes a rotating platform. The rotating platform is disposed on the translation platform, and the image acquisition device is disposed on the rotating platform, so that the high-resolution industrial camera can perform translation and rotation.

[0019] In some embodiments, the moving component is a rotating platform, the image acquisition device is disposed on the rotating platform, and the high-resolution industrial camera can rotate.

[0020] In some embodiments, the central control component includes an image processing unit and a motion control unit. The image processing unit is used to receive and process the image data from the high-resolution industrial camera, and the motion control unit is used to control the motion of the moving component according to the pose and position information provided by the positioning device.

[0021] The beneficial effects of the present utility model are as follows:

[0022] The visual scanning and sampling device of the present utility model combines a high-resolution industrial camera with a positioning device to provide data for distortion correction and image stitching, improving the accuracy and efficiency of image acquisition. Moreover, by combining with a light source, the illumination uniformity is further enhanced, enabling better image acquisition. The present utility model is conducive to the mapping of PCB circuit board solutions and can output circuit board solutions with high efficiency, low cost, high precision, and low labor intensity. Description of the Drawings

[0023] Figure 1 It is a schematic diagram of the overall structure in an embodiment of the present utility model.

[0024] In the figure, 1 - high-resolution industrial camera; 2 - high-precision linear guide; 3 - PCB support base; 4 - bracket; 5 - translation platform. Detailed Embodiment

[0025] To make the technical solutions and advantages of the present utility model clearer, the technical solutions of the embodiments of the present utility model will be fully described below in conjunction with the drawings in the present utility model. Obviously, the described embodiments are some, but not all, of the embodiments of the present utility model. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present utility model without creative efforts shall fall within the protection scope of the present utility model.

[0026] The embodiments of the present utility model will be described in detail below. The examples of the embodiments are shown in the drawings, where the same or similar reference numerals denote the same or similar elements or elements with the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and are only used to explain the present utility model and should not be construed as a limitation of the present utility model.

[0027] In a specific application embodiment, the present utility model provides a visual scanning and sampling device, which mainly includes the following parts:

[0028] 1. Image acquisition device

[0029] High-resolution industrial camera: Camera model: Basler acA1920 - 40um (resolution of 1920x1200, 40 frames per second); Lens: Computar 12mm F1.4 high-resolution industrial lens; Light source: Ring light source, providing uniform illumination, with adjustable color temperature and brightness of the light source. The central control component adjusts the color temperature and brightness of the light source in real time according to the images collected by the high-resolution industrial camera to ensure uniform brightness of the collected images. In some embodiments, a light homogenizing plate is further included, which is arranged on the light emitting surface of the light source to further make the illumination uniform.

[0030] 2. Moving Component

[0031] Translation mechanism: Thorlabs LTS300 high-precision linear guide and translation stage, driven by a stepper motor; Rotation mechanism: Velmex B4872TS high-precision rotary stage, controlled by a microstep motor; Combining the translation and rotation mechanisms enables precise control of the XYZ axes and in-plane rotation of the high-resolution industrial camera.

[0032] In this embodiment, the image acquisition device is fixed on the bracket, and below it is the PCB board fixing seat. In other embodiments, the image acquisition device can be arranged above the PCB board by different means, as long as it can ensure the normal operation of the industrial camera. The image acquisition device and the PCB board can be relatively stationary or relatively movable.

[0033] 3. Positioning Device

[0034] High-precision pose sensor: Sensor model: Xsens MTi-30 IMU (Inertial Measurement Unit), providing high-precision attitude data;

[0035] Laser displacement sensor: Keyence LK-G5000 series, used for precise displacement measurement. In other embodiments, an encoder can also be used as the displacement sensor;

[0036] In this embodiment, both the high-precision pose sensor and the laser displacement sensor are used to monitor the position and attitude of the high-resolution industrial camera. In some other embodiments, corresponding pose sensors can also be set to monitor the position and attitude of the PCB board to be detected.

[0037] 4. Central Control Component

[0038] Connected to the image acquisition device, positioning device, and moving component, used to control the automatic operation of the visual scanning and sampling device and process and output the circuit board image. The central control component includes an image processing unit and a motion control unit. The image processing unit is used to receive and process the image data from the high-resolution industrial camera, and the motion control unit is used to control the motion of the moving component according to the attitude and position information provided by the positioning device.

[0039] In the central control system, the following operations are performed:

[0040] Image calibration and distortion correction: Geometric calibration: Using the pose sensor data, perform geometric calibration through OpenCV; Illumination correction: Use adaptive histogram equalization (CLAHE) for illumination equalization;

[0041] Circuit diagram generation: Image recognition technology: Use a CNN model based on TensorFlow to identify components and circuit paths; Vectorization processing: Use vectorization software (such as Inkscape) to convert the recognition results into a standardized circuit diagram; Manual correction: Provide a graphical user interface (GUI) based on Qt to allow users to make fine-tuning and correction.

[0042] Scanning path planning: Use a serpentine scanning path to ensure full coverage;

[0043] Image stitching algorithm: Use the SIFT algorithm for feature point matching and stitching;

[0044] Distortion correction processing: Use camera calibration parameters to correct image distortion; For different cameras and lenses, perform orthodontic calibration before actual use to ensure the accuracy of image acquisition.

[0045] System working process and principle

[0046] 1. Image acquisition stage: The industrial camera moves or rotates on a high-precision guide rail and translation platform to take high-resolution images of different areas of the PCB one by one; The high-precision pose sensor records the shooting position and angle of each image to ensure the accuracy of subsequent stitching.

[0047] 2. Image stitching stage: Perform geometric calibration and distortion correction processing based on the data of the pose sensor to ensure the accuracy and consistency of the stitched images; Use image processing algorithms for feature point matching to stitch the images taken multiple times into a complete PCB image.

[0048] 3. Circuit diagram generation stage: Use deep learning algorithms to automatically identify circuit paths and components in the stitched PCB image; Convert the recognition results into a vector format to generate a standardized circuit diagram; Provide a user interface to allow users to perform manual correction on the automatically generated circuit diagram to ensure the accuracy and usability of the final drawing.

[0049] In a specific embodiment, such as Figure 1, this solution includes an image acquisition device, which includes a high-resolution industrial camera 1 and a light source (not shown); a positioning device (not shown), which includes high-precision pose sensing for real-time detection of the pose and position information of the industrial camera; a moving component arranged on a bracket 4 for driving the high-resolution industrial camera to change its spatial position. In this embodiment, the moving component includes a high-precision linear guide rail 2 and a translation platform 5. The high-resolution industrial camera 1 is arranged on the translation platform 5 and is driven to move by the high-precision linear guide rail 2; a central control component (not shown), which is connected to the image acquisition device, the positioning device, and the moving component, is used to control the automatic operation of the vision scanning and sampling device, and processes and outputs the PCB board image; a PCB support base 3 for placing the PCB board to be detected. The settings of this solution are as follows:

[0050] 1. Initial settings:

[0051] Install the Basler acA1920-40um camera on the Thorlabs LTS300 linear guide rail.

[0052] Activate the Keyence LK-G5000 laser displacement sensor and the Xsens MTi-30 IMU.

[0053] Under the ring light source, adjust the lighting to obtain uniform illumination.

[0054] 2. Image acquisition:

[0055] Set a serpentine scanning path and move the camera to each scanning point in turn.

[0056] Take images at each point and record the data of the pose sensor.

[0057] 3. Image stitching:

[0058] Use the SIFT algorithm to match and stitch images in different regions.

[0059] Perform geometric calibration and distortion removal processing according to the pose sensor data.

[0060] 4. Circuit diagram generation:

[0061] Use the trained CNN model to identify the circuit paths and components in the stitched image.

[0062] Vectorize the recognition results to generate a standardized circuit diagram.

[0063] Perform manual correction in the Qt GUI and save the final result.

[0064] In some embodiments, the AI image processing function is used for intelligent repair after the generation of the PCB circuit board line drawing, preventing the occurrence of line drawing tilt and breakpoints after acquisition and positioning. After the acquisition is completed, the line drawing on the surface of the circuit board is automatically repaired and corrected through the AI image processing function.

[0065] In the description of this specification, reference terms such as "one embodiment" and "example" mean that the specific features, structures, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present utility model. In this specification, the schematic expressions of the above terms do not necessarily refer to the relative embodiments or examples in a suitable manner.

[0066] It must be pointed out that the description of the above embodiments is not for limitation but only for helping to understand the core idea of the present utility model. For those of ordinary skill in the art of this technology, any improvements made to the present utility model and equivalent alternative solutions to this product without departing from the principle of the present utility model also fall within the scope of protection of the claims of the present utility model.

Claims

1. A visual scanning and sampling device, characterized in that Comprising: An image acquisition device, including a high-resolution industrial camera and a light source; A positioning device, including high-precision pose sensing, for real-time detection of the pose and position information of the industrial camera; A moving component, for driving the high-resolution industrial camera to change its spatial position; A central control component, connected to the image acquisition device, the positioning device, and the moving component, for controlling the automatic operation of the vision scanning and sampling device and processing and outputting the circuit board image.

2. The visual scanning and point sampling device according to claim 1, wherein The high-precision pose sensing includes an inertial measurement unit and a displacement sensor. The inertial measurement unit is arranged on the high-resolution industrial camera for detecting the pose information of the industrial camera; the displacement sensor is arranged on the moving component for detecting the position information of the industrial camera.

3. The visual scanning and point sampling device according to claim 2, wherein The displacement sensor is an encoder or a laser displacement sensor.

4. The visual scanning and point sampling device according to claim 1, wherein The color temperature and brightness of the light source are adjustable. The central control component adjusts the color temperature and brightness of the light source in real time according to the image collected by the high-resolution industrial camera to ensure uniform brightness of the collected image.

5. The visual scanning and point sampling device according to claim 1, wherein The light source is a ring light source for providing uniform illumination.

6. The visual scanning and point sampling device according to claim 5, characterized in that, It further includes a light homogenizing plate, arranged on the light emitting surface of the light source to further homogenize the illumination.

7. The visual scanning and point sampling device according to claim 1, characterized in that, The moving component includes a high-precision linear guide and a translation platform. The image acquisition device is arranged on the translation platform and is driven by the high-precision linear guide to perform displacement.

8. The visual scanning and point sampling device according to claim 7, wherein The moving component further includes a rotating platform. The rotating platform is arranged on the translation platform, and the image acquisition device is arranged on the rotating platform, enabling the high-resolution industrial camera to perform translation and rotation.

9. The visual scanning and point sampling device according to claim 1, characterized in that, The moving component is a rotating platform, and the image acquisition device is arranged on the rotating platform, enabling the high-resolution industrial camera to rotate.

10. The visual scanning and point sampling device according to claim 1, wherein, The central control component includes an image processing unit and a motion control unit. The image processing unit is used for receiving and processing the image data from the high-resolution industrial camera, and the motion control unit is used for controlling the motion of the moving component according to the pose and position information provided by the positioning device.

Images