Visual inspection method, device and system

Abstract

This application provides a visual inspection method, apparatus, and system. The method includes: upon receiving a photoelectric signal, controlling a visual processing image sensor via a motion platform to move from a first position at a first speed along the movement direction of a conveyor belt, starting from the time the photoelectric signal is received and delayed by a first time, while controlling the visual processing image sensor to acquire an image; and performing visual inspection on the object under test based on the image acquired by the visual processing image sensor. This method can reduce the workload of the visual processing image sensor and lower its performance requirements.

Description

Technical Field

[0001] This application relates to the field of robot visual perception, and in particular to a visual inspection method, device and system. Background Technology

[0002] In the industrial manufacturing sector, there are many needs that rely on visual inspection, and the objects being inspected are typically on conveyor belts. To improve inspection efficiency, conveyor belts generally move at high speeds, and because the size of the objects being inspected is not fixed, high frame rate image sensors are usually used for inspection to ensure that clear images of the objects are captured for visual inspection.

[0003] However, in the above-mentioned visual detection scheme, the target in the acquired image is prone to motion blur, which affects the accuracy of visual detection. Summary of the Invention

[0004] In view of this, this application provides a visual inspection method, apparatus and system.

[0005] According to a first aspect of the embodiments of this application, a visual detection method is provided, comprising:

[0006] Upon receiving a photoelectric signal, the motion platform controls the visual processing image sensor to move from a first position at a first speed along the direction of the conveyor belt, starting from the time the photoelectric signal is received and delayed by a first time. The visual processing image sensor then performs image acquisition. The photoelectric signal is sent by the photoelectric sensor when it detects the object being measured has passed the second position. The first time is determined based on the distance between the third position and the second position, and the speed of the conveyor belt. The third position is a designated position within the field of view of the visual processing image sensor when it is in the first position. The first speed matches the operating speed of the conveyor belt.

[0007] The object under test is visually inspected based on the image acquired by the vision processing image sensor.

[0008] According to a second aspect of the embodiments of this application, a visual inspection device is provided, comprising: a receiving unit, a control unit, and a detection unit; wherein:

[0009] The control unit is configured to, upon receiving a photoelectric signal from the receiving unit, control the visual processing image sensor via a motion platform to move from a first position at a first speed along the direction of movement of the conveyor belt, starting from the time the photoelectric signal is received and delaying for a first time, and control the visual processing image sensor to acquire images; wherein, the photoelectric signal is sent by the photoelectric sensor when it detects that the object being measured has passed the second position, the first time is determined based on the distance between the third position and the second position, and the speed of movement of the conveyor belt, the third position is the position of the visual processing image sensor near the edge of the field of view of the second position when the visual processing image sensor is in the first position, and the first speed is matched with the running speed of the conveyor belt;

[0010] The detection unit is used to perform visual detection on the object under test based on the image acquired by the visual processing image sensor.

[0011] According to a third aspect of the embodiments of this application, an electronic device is provided, including a processor and a memory, the memory storing machine-executable instructions executable by the processor, the processor being configured to execute the machine-executable instructions to implement the method provided in the first aspect.

[0012] According to a fourth aspect of the embodiments of this application, a machine-readable storage medium is provided, wherein machine-executable instructions are stored therein, and when the machine-executable instructions are executed by a processor, the method provided in the first aspect is implemented.

[0013] According to a fifth aspect of the embodiments of this application, a visual inspection system is provided, comprising: a photoelectric sensor, a motion platform, and a visual processing image sensor; wherein:

[0014] The photoelectric sensor is used to send a photoelectric signal to the visual processing image sensor when it detects that the object being measured has passed through the second position.

[0015] The visual processing image sensor is configured to, upon receiving the photoelectric signal, control the motion platform to move from a first position at a first speed along the movement direction of the conveyor belt, starting from the time the photoelectric signal is received and delaying for a first time, and to acquire an image; wherein, the first time is determined based on the distance between the third position and the second position, and the movement speed of the conveyor belt, the third position being the position of the visual processing image sensor near the edge of the field of view of the second position when the visual processing image sensor is in the first position, and the first speed matching the running speed of the conveyor belt;

[0016] The visual processing image sensor is also used to perform visual inspection of the object under test based on the acquired image.

[0017] The visual inspection method of this application deploys a motion platform and controls the movement of a visual processing image sensor. For a moving object, the motion platform controls the visual processing image sensor to move synchronously with the object based on its speed and direction of movement, achieving tracking and optimizing image acquisition for moving objects, thus improving the accuracy of visual inspection. Furthermore, by deploying a photoelectric sensor, the timing for tracking is determined based on the distance between the photoelectric sensor's detection position and a designated position within the visual range of the visual processing image sensor at a first position, as well as the object's speed. This reduces the workload and performance requirements of the visual processing image sensor. Attached Figure Description

[0018] Figure 1 This is a schematic flowchart of a visual inspection method provided in an embodiment of this application;

[0019] Figure 2 This is a schematic diagram illustrating a specific application scenario provided in an embodiment of this application;

[0020] Figure 3A This is a schematic diagram of a two-axis motion platform provided in an embodiment of this application;

[0021] Figure 3B This is a schematic diagram of a three-axis motion platform provided in an embodiment of this application;

[0022] Figure 4 This is a schematic diagram of a visual positioning method provided in an embodiment of this application;

[0023] Figure 5 This is a schematic diagram of the structure of a visual inspection device provided in an embodiment of this application;

[0024] Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application;

[0025] Figure 7 This is a schematic diagram of the structure of a visual inspection system provided in an embodiment of this application;

[0026] Figure 8 This is a schematic diagram of another visual inspection system provided in an embodiment of this application. Detailed Implementation

[0027] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0028] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise.

[0029] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of this application, and to make the above-mentioned objectives, features and advantages of the embodiments of this application more apparent and understandable, the technical solutions in the embodiments of this application will be further described in detail below with reference to the accompanying drawings.

[0030] It should be noted that the sequence number of each step in the embodiments of this application does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0031] Please see Figure 1 This is a flowchart illustrating a visual inspection method provided in an embodiment of this application, as shown below. Figure 1 As shown, the visual inspection method may include the following steps:

[0032] It should be noted that the entity executing the visual inspection scheme provided in this application embodiment can be a visual processing image sensor or a specially deployed device for visual inspection, such as a visual inspection server.

[0033] The following explanation uses a visual processing image sensor as the main body for implementing a visual inspection scheme.

[0034] Step S100: Upon receiving a photoelectric signal, the motion platform controls the vision processing image sensor to move from the first position at a first speed along the direction of the conveyor belt, starting from the time the photoelectric signal is received and delayed by a first time. The photoelectric signal is sent by the photoelectric sensor when it detects that the object being measured has passed the second position. The first time is determined based on the distance between the third position and the second position, as well as the speed of the conveyor belt. The third position is a designated position within the field of view of the vision processing image sensor when it is in the first position. The first speed is matched with the running speed of the conveyor belt.

[0035] In this embodiment of the application, in order to optimize the image acquisition effect of moving targets and thereby improve the accuracy of visual detection of moving targets, the visual processing image sensor can be controlled by the motion platform to move at a depth that matches the moving speed of the moving target and in a direction that is consistent with the moving direction of the moving target, so that the visual processing image sensor is relatively stationary with respect to the moving target (including a relative speed of 0, or a tolerable relative speed).

[0036] Furthermore, to reduce the workload and performance requirements of the visual processing image sensor, a photoelectric sensor can be deployed to detect the object under test. Based on the distance between the designated position (referred to as the third position) within the field of view of the visual processing image sensor and the detection position (referred to as the second position) of the photoelectric sensor when the visual processing image sensor is in a designated position (referred to as the first position in this document), and the speed of the object under test (i.e., the speed of the conveyor belt), the time when the object under test enters the field of view of the visual processing image sensor after being detected by the photoelectric sensor can be determined, so as to better determine the timing of image acquisition by the visual processing image sensor.

[0037] Accordingly, in the embodiments of this application, when the photoelectric sensor detects that the object being measured has passed through the second position, a photoelectric signal can be sent to the visual processing image sensor.

[0038] For example, the photoelectric sensor can send a photoelectric signal to the vision processing image sensor when it detects that the tail end of the object being measured has passed through the second position.

[0039] When the visual image sensor receives a photoelectric signal, the motion platform can control the visual image sensor to move from a first position at a first speed along the direction of the conveyor belt, starting from the time the photoelectric signal is received and then delaying for a first time, and to acquire an image.

[0040] For example, the first time can be determined based on the distance between the third position and the second position.

[0041] For example, the first time can be the time it takes for the object under test to move from the second position to a designated position (i.e., the third position mentioned above) within the field of view of the visual processing image sensor located at the first position. That is, when the object under test enters the designated position within the field of view of the visual processing image sensor, the visual processing image sensor is controlled by the motion platform to move synchronously with the object under test, and image acquisition is performed during the movement.

[0042] For example, during movement, the vision processing image sensor can acquire multiple frames of images at a preset frame rate to improve the accuracy of visual detection.

[0043] For example, taking the conveyor belt speed as fixed as v, the first time can be the ratio of the distance between the third position and the second position to v.

[0044] Step S110: Visually inspect the object under test based on the image acquired by the visual processing image sensor.

[0045] In this embodiment of the application, the object under test can be visually inspected based on the image acquired in the manner described in step S100.

[0046] It can be seen that, in Figure 1 In the illustrated method, a motion platform is deployed to control the movement of the vision processing image sensor. For a moving object, the motion platform controls the vision processing image sensor to move synchronously with the object based on its speed and direction, enabling tracking and optimizing image acquisition for moving objects, thus improving the accuracy of visual detection. Furthermore, by deploying a photoelectric sensor, the timing for tracking is determined based on the distance between the photoelectric sensor's detection position and a designated position within the visual range of the vision processing image sensor at the first position, as well as the object's speed. This reduces the workload and performance requirements of the vision processing image sensor.

[0047] In some embodiments, before the above-described control of the visual processing image sensor via the motion platform to move from a first position at a first speed along the movement direction of the conveyor belt, starting from the time when the photoelectric signal is detected and delayed by a first time, and before the control of the visual processing image sensor to perform image acquisition, may further include:

[0048] Upon receiving the target position information of the object being measured from the visual positioning image sensor, the motion platform controls the position of the visual processing image sensor in the width direction of the conveyor belt to match the target position information. The target position information is used to characterize the position of the object being measured in the width direction of the conveyor belt. The target position information is determined by the visual positioning image sensor based on the image of the object being measured, and the field of view of the visual positioning image sensor covers the width direction of the conveyor belt.

[0049] For example, considering that the object under test may be located at different positions along the width of the conveyor belt, if a vision processing image sensor with a small field of view is used when the conveyor belt is wide, it may not be possible to capture a complete image of the object under test at certain positions. If a vision processing image sensor with a large field of view is used, a high-resolution image sensor is required to capture a clear image, which increases the implementation cost. In addition, for the object under test located at the edge of the width of the conveyor belt, the captured image of the object under test may have imaging distortion, resulting in poor accuracy of visual detection.

[0050] Accordingly, in this embodiment of the application, in order to reduce the cost of the visual processing image sensor and improve the accuracy of visual detection, a visual positioning sensor can also be deployed. The visual positioning sensor determines the position information of the object under test in the width direction of the conveyor belt (hereinafter referred to as the target position information). Based on the target position information, the motion platform controls the position of the visual processing image sensor in the width direction of the conveyor belt to match the target position information. For example, the object under test is placed within the field of view of the visual processing image sensor, and the object under test is placed at the center position within the field of view of the visual image sensor as much as possible. For example, the distance between the center of the object under test and the center position of the field of view of the visual image sensor in the width direction of the conveyor belt is less than a preset distance.

[0051] For example, when the photoelectric sensor detects that the object being measured has passed through the second position, the photoelectric sensor can send a photoelectric signal to the visual positioning image sensor.

[0052] When a visual positioning image sensor receives a photoelectric sensor, it can use the time of receiving the photoelectric signal as the starting time, delay for a second time, and then perform image acquisition. Based on the acquired image, it can identify the target position information of the object being measured.

[0053] For example, the second time can be determined based on the distance between the second position and a specified position (referred to herein as the fourth position) within the field of view of the visual positioning image sensor, as well as the speed of the conveyor belt.

[0054] For example, the second time can be the time when the object being measured moves from the second position to a designated position (i.e., the fourth position mentioned above) within the field of view of the visual positioning image sensor. That is, when the object being measured enters the designated position of the visual positioning image sensor, the visual positioning image sensor performs image acquisition and locates the object being measured based on the acquired image to determine the target position information of the object being measured.

[0055] For example, taking the conveyor belt speed as fixed as v, the second time can be the ratio of the distance between the fourth position and the second position to v.

[0056] Once the visual positioning image sensor has determined the target position information of the object being measured, it can send the target position information of the object to the visual processing image sensor.

[0057] The vision processing image sensor can match the position of the vision processing image sensor in the width direction of the conveyor belt with the target position information by controlling the motion platform, based on the target position information of the object being measured.

[0058] In this embodiment, the motion platform can move in both the width direction of the conveyor belt and the direction of movement of the conveyor belt.

[0059] In one example, the target location information mentioned above is determined based on the position of the object being measured in the image coordinate system of the visual positioning image sensor and a preset position transformation relationship;

[0060] The preset position conversion relationship includes the mapping relationship between the position in the image coordinate system of the visual positioning image sensor and the position in the width direction of the conveyor belt.

[0061] For example, in order to determine the target position information of the object being measured, the mapping relationship between the position of the object being measured in the image coordinate system of the visual positioning image sensor and its position in the width direction of the conveyor belt can be predetermined (which can be called the preset position transformation relationship).

[0062] For example, taking the direction of the conveyor belt movement as the x-axis of the image coordinate system and the width direction of the conveyor belt as the y-axis of the image coordinate system, the above position transformation relationship can include the mapping relationship between the y-coordinate value of the center point of the object being measured in the image coordinate system and the distance between the center point of the object being measured and a specified edge of the conveyor belt (such as the left edge when facing the direction of the conveyor belt movement).

[0063] For example, with Figure 4 Taking the scenario shown as an example, assuming the width of the conveyor belt in the width direction (or Y direction) is L (mm), the field of view of the visual positioning image sensor in the Y direction matches the width of the conveyor belt, and the width of the image of the visual positioning image sensor in the Y direction is H (pixels), then the single pixel accuracy f = L / H. For the measured object with the y coordinate value (pixel coordinate) of the center point being h, the distance from its center point to the specified edge of the conveyor belt is s = h*L / H.

[0064] It should be noted that the field of view of the visual positioning image sensor in the Y direction can also exceed the width of the conveyor belt. For example, if the specified boundary of the field of view of the visual positioning image sensor in the Y direction (such as the left boundary when facing the direction of the conveyor belt movement) exceeds the width of the conveyor belt by h0 pixels, and the width of the area in the field of view of the visual positioning image sensor in the Y direction that matches the width of the conveyor belt is H (pixels), then for the object being measured with the y coordinate value (pixel coordinate) of the center point being h, the distance from the center point to the specified edge of the conveyor belt is s = (h - h0) * L / H.

[0065] Accordingly, upon receiving a photoelectric signal, the visual positioning image sensor can delay image acquisition for a second time, and locate the object under test based on the acquired image, determining the object's position in the image coordinate system of the visual positioning image sensor. Based on this position and a preset position transformation relationship, the position of the object under test in the width direction of the conveyor belt is then determined. In one example, the visual positioning image sensor is a 3D stereoscopic image sensor.

[0066] Before the aforementioned control of the visual processing image sensor via a motion platform to move from a first position at a first speed along the movement direction of the conveyor belt, starting from the time the photoelectric signal is detected and delayed by a first time, and before the control of the visual processing image sensor to perform image acquisition, may further include:

[0067] Upon receiving the target height information of the object being measured from the visual positioning image sensor, the motion platform controls the height of the visual processing image sensor to match the target height information based on the target height information.

[0068] For example, considering that in real-world scenarios, the height of different objects may vary greatly, and the height of the object may also affect the image acquisition effect of the visual processing image sensor, or even cause the inability to acquire images (e.g., if the object is too tall and collides with the visual processing image sensor).

[0069] Therefore, in order to ensure the image acquisition effect of the vision processing image sensor, the vision positioning image sensor can also determine the height information of the object being measured, so as to set the height of the vision processing image sensor to an appropriate height based on the height information.

[0070] Accordingly, the aforementioned visual positioning image sensor can be a 3D stereo image sensor. When using this visual positioning image sensor to locate the object being measured, the height information of the object being measured (which can be called target height information) can also be determined.

[0071] When the visual positioning image sensor acquires the target height information of the object being measured, it can also send the target height information to the visual processing image sensor. The visual processing image sensor then uses the motion platform to control the height of the visual processing image sensor to match the target height information.

[0072] For example, the height of a vision processing image sensor can be set according to the height of the object being measured and the focal length requirements for image acquisition, in order to optimize the image quality of the object acquired by the vision processing image sensor.

[0073] In this embodiment, the motion platform can move in three directions: the width direction of the conveyor belt, the direction of the conveyor belt movement, and the direction perpendicular to the plane of the conveyor belt.

[0074] To enable those skilled in the art to better understand the technical solutions provided in the embodiments of this application, the technical solutions provided in the embodiments of this application are described below in conjunction with specific application scenarios.

[0075] In this embodiment, visual inspection of workpieces conveyed by a conveyor belt is taken as an example.

[0076] Please see Figure 2 This is a schematic diagram illustrating a specific application scenario provided in an embodiment of this application, such as... Figure 2 As shown, to achieve visual inspection of workpieces, this application scenario can include photoelectric sensors, visual positioning image sensors, visual processing image sensors, and a motion platform. The photoelectric sensors, visual positioning image sensors, and visual processing image sensors are deployed sequentially along the conveyor belt's movement direction. The visual processing image sensors are mounted on the motion platform, and their position can be adjusted by controlling the movement of the platform.

[0077] The functions of each component are explained below.

[0078] Photoelectric sensor: The photoelectric sensor can be connected to the vision positioning image sensor and the vision processing image sensor respectively. When the photoelectric sensor detects the arrival of the workpiece, it can send photoelectric signals to the vision positioning image sensor and the vision processing image sensor respectively.

[0079] Visual positioning image sensor: The field of view of the visual positioning image sensor can cover the width of the conveyor belt. Upon receiving a photoelectric signal, image acquisition can begin after a predetermined delay t1 (i.e., the second time mentioned above), and the workpiece is positioned based on the acquired image. The position information of the workpiece (i.e., the target position information mentioned above) is then output to the visual processing image sensor.

[0080] For example, t1 = s1 / v.

[0081] Where s1 is the distance between the edge of the field of view of the visual positioning image sensor (the edge on the side closer to the photoelectric sensor, i.e., taking the fourth position above as the edge of the field of view of the visual positioning image sensor as an example) and the detection position of the photoelectric sensor (i.e., the second position above), and v is the speed of the conveyor belt.

[0082] Vision processing image sensor: The field of view of the vision processing image sensor can be smaller than that of the vision positioning image sensor, and its field of view does not need to cover the width of the conveyor belt. Upon receiving a photoelectric signal, the position of the vision processing image sensor in the width of the conveyor belt can be adjusted by a motion platform according to the target position information of the workpiece, so that the field of view of the vision processing image sensor can cover the position of the workpiece. In addition, the motion platform can control the vision processing image sensor to start from a specified starting position (i.e., the first position mentioned above), take the time of receiving the photoelectric signal as the starting time, delay for time t2 (i.e., the first time mentioned above), perform image acquisition, and move along the y-direction (i.e., the direction of conveyor belt movement) at a speed v equal to that of the conveyor belt.

[0083] For example, t2 = s2 / v.

[0084] Wherein, s2 is the distance between the field of view edge of the visual processing image sensor (the edge on the side closer to the photoelectric sensor, i.e., taking the third position mentioned above as the field of view edge of the visual positioning image sensor as an example) and the detection position of the photoelectric sensor (i.e., the second position mentioned above) when the visual processing image sensor is in a specified starting position.

[0085] For example, for any workpiece, the vision processing image sensor can stop image acquisition and return to the specified starting position when the movement time reaches t3 or the vision processing is completed.

[0086] For example, the aforementioned t3 is less than or equal to the ratio of the maximum distance the motion platform moves in the y direction to its speed v.

[0087] The instruction manual requires that, in order to ensure the vision processing image sensor can return to its original position in a timely manner, the shortest distance between the two workpieces is:

[0088]

[0089] Where s3 is the maximum movable distance of the motion platform in the y direction, s4 is the maximum movable distance of the motion platform in the x direction, and v1 is the speed at which the motion platform returns to its original position.

[0090] Furthermore, t2≤s4 / v2, where v2 is the speed of the motion platform in the x direction, to ensure that when the photoelectric sensor detects the workpiece, the vision processing image sensor has enough time to move in the x direction to a position that matches the target position information.

[0091] Motion platform: The movement distance of the motion platform in the x and y directions can be determined based on the required field of view of the conveyor belt. Control of the motion platform can be achieved using a vision processing image sensor.

[0092] It should be noted that, in order to reduce installation difficulty and cost, the motion platform can be selected in a relatively smaller size while still meeting the requirements.

[0093] For example, please see Figure 3A For a two-axis motion platform, its schematic diagram can be as follows: Figure 3A As shown.

[0094] For example, a two-axis motion platform moves in both the x and y directions. It can be composed of a motor, a trapezoidal lead screw, and a linear guide. The motor output shaft makes circular motion, and the lead screw and lead screw nut convert the circular motion into linear motion to achieve adjustment in the x and y directions.

[0095] For example, if the workpiece has different depth requirements in the height direction, the above-mentioned visual positioning image sensor can be a 3D stereo image sensor, which can output the height information of the workpiece (i.e. the above-mentioned target height information) in addition to the target position information of the workpiece; in this case, the motion platform can be a 3-axis motion platform to realize the motion in the xyz three directions.

[0096] Please see Figure 3B For a three-axis motion platform, its schematic diagram can be as follows: Figure 3B As shown.

[0097] For example, the three-axis motion platform adds movement in the z-axis direction and consists of a motor, a trapezoidal lead screw, a linear guide, gears and racks. The motor drives the gears and racks to transmit power in the y and z directions, while the motor drives the lead screw and lead screw nut in the x direction, thus realizing position adjustment in three directions.

[0098] The method provided in this application has been described above. The apparatus provided in this application is described below:

[0099] Please see Figure 5 This is a schematic diagram of the structure of a visual inspection device provided in an embodiment of this application, as shown below. Figure 5 As shown, the visual inspection device may include: a receiving unit 510, a control unit 520, and a detection unit 530; wherein:

[0100] The control unit 520 is configured to, when the receiving unit 510 receives a photoelectric signal, control the visual processing image sensor via a motion platform to move from a first position at a first speed along the movement direction of the conveyor belt, starting from the time the photoelectric signal is received and delaying for a first time, and control the visual processing image sensor to perform image acquisition; wherein, the photoelectric signal is sent by the photoelectric sensor when it detects that the object being measured has passed the second position, the first time is determined based on the distance between the third position and the second position, and the movement speed of the conveyor belt, the third position is the position of the visual processing image sensor near the edge of the field of view of the second position when the visual processing image sensor is in the first position, and the first speed is matched with the running speed of the conveyor belt;

[0101] The detection unit 530 is used to perform visual detection on the object under test based on the image acquired by the visual processing image sensor.

[0102] In some embodiments, before the control unit 520 controls the visual processing image sensor to move from a first position at a first speed along the movement direction of the conveyor belt, starting from the time the photoelectric signal is detected and delayed by a first time, and before the visual processing image sensor performs image acquisition, the control unit 520 further includes:

[0103] When the receiving unit 510 receives the target position information of the object being measured sent by the visual positioning image sensor, it controls the position of the visual processing image sensor in the width direction of the conveyor belt to match the target position information based on the target position information. The target position information is used to characterize the position of the object being measured in the width direction of the conveyor belt. The target position information is determined by the visual positioning image sensor based on the image of the object being measured that it has acquired. The field of view of the visual positioning image sensor covers the width direction of the conveyor belt.

[0104] In some embodiments, the target location information is determined based on the position of the object being measured in the image coordinate system of the visual positioning image sensor and a preset position transformation relationship;

[0105] The preset position conversion relationship includes the mapping relationship between the position of the visual positioning image sensor in the image coordinate system and the position in the width direction of the conveyor belt.

[0106] In some embodiments, the visual positioning image sensor is a 3D stereo image sensor;

[0107] The control unit 520, via a motion platform, controls the visual processing image sensor to move from a first position at a first speed along the direction of the conveyor belt, starting from the time the photoelectric signal is detected, with a first delay, and before controlling the visual processing image sensor to perform image acquisition, further includes:

[0108] Upon receiving the target height information of the object being measured sent by the visual positioning image sensor, the motion platform controls the height of the visually processed image to match the target height information based on the target height information.

[0109] This application provides an electronic device including a processor and a memory, wherein the memory stores machine-executable instructions that can be executed by the processor, and the processor executes the machine-executable instructions to implement the visual detection method described above.

[0110] Please see Figure 6 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of this application. The electronic device may include a processor 601 and a memory 602 storing machine-executable instructions. The processor 601 and the memory 602 can communicate via a system bus 603. Furthermore, by reading and executing the machine-executable instructions corresponding to the visual detection logic in the memory 602, the processor 601 can execute the visual detection method described above.

[0111] The memory 602 mentioned in this document can be any electronic, magnetic, optical, or other physical storage device that can contain or store information such as executable instructions, data, etc. For example, machine-readable storage media can be: RAM (Random Access Memory), volatile memory, non-volatile memory, flash memory, storage drives (such as hard disk drives), solid-state drives, any type of storage disk (such as optical discs, DVDs, etc.), or similar storage media, or combinations thereof.

[0112] In some embodiments, a machine-readable storage medium, such as Figure 6 The memory 602 in the device stores machine-executable instructions, which, when executed by a processor, implement the visual inspection method described above. For example, the storage medium may be ROM, RAM, CD-ROM, magnetic tape, floppy disk, or optical data storage device.

[0113] Please see Figure 7 This is a schematic diagram of the structure of a visual inspection system provided in an embodiment of this application, as shown below. Figure 7 As shown, the visual inspection system may include: a photoelectric sensor 710, a motion platform 720, and a visual processing image sensor 730; wherein:

[0114] The photoelectric sensor 710 is used to send a photoelectric signal to the visual processing image sensor when it detects that the object being measured has passed through the second position.

[0115] The visual processing image sensor 730, upon receiving the photoelectric signal, is controlled by the motion platform 720 to move from a first position at a first speed along the movement direction of the conveyor belt, starting from the time the photoelectric signal is received and delayed by a first time, and to acquire an image; wherein, the first time is determined based on the distance between the third position and the second position, and the movement speed of the conveyor belt, the third position being the position near the edge of the field of view of the visual processing image sensor when it is in the first position, and the first speed matching the running speed of the conveyor belt;

[0116] The visual processing image sensor 730 is also used to perform visual inspection of the object under test based on the acquired image.

[0117] In some embodiments, such as Figure 8 As shown, the visual inspection system may further include: a visual positioning image sensor 740; the field of view of the visual positioning image sensor covers the width direction of the conveyor belt;

[0118] The photoelectric sensor 710 is also used to send a photoelectric signal to the visual positioning image sensor when it detects that the object being measured has passed through the second position.

[0119] The visual positioning image sensor 740 is used to, upon receiving the photoelectric signal, perform image acquisition starting from the time of receiving the photoelectric signal and delaying for a second time, and identify the target position information of the object under test based on the acquired image; wherein, the target position information is used to characterize the position of the object under test in the width direction of the conveyor belt; the second time is determined based on the distance between the fourth position and the second position, and the movement speed of the conveyor belt, wherein the fourth position is a designated position within the field of view of the visual positioning image sensor;

[0120] The visual positioning image sensor 740 is also used to send the target position to the visual processing image sensor;

[0121] The visual processing image sensor 730 is also used to control the position of the visual processing image sensor in the width direction of the conveyor belt to match the target position information through the motion platform 720, based on the target position information.

[0122] In some embodiments, the target location information is determined based on the position of the object being measured in the image coordinate system of the visual positioning image sensor and a preset position transformation relationship;

[0123] The preset position conversion relationship includes the mapping relationship between the position of the visual positioning image sensor in the image coordinate system and the position in the width direction of the conveyor belt.

[0124] In some embodiments, the visual positioning image sensor is a 3D stereo image sensor;

[0125] The visual positioning image sensor 740 is also used to identify the target height information of the object being measured based on the acquired image, and send the height information to the visual processing image sensor;

[0126] The visual processing image sensor 730 is also used to control the height of the visual processing image to match the target height information through the motion platform, based on the target height information.

[0127] It should be noted that, in this document, relational terms such as "objective" and "target" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0128] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A visual inspection method, characterized in that, include: Upon receiving a photoelectric signal, the motion platform controls the visual processing image sensor to move from a first position at a first speed along the direction of the conveyor belt, starting from the time the photoelectric signal is received and delayed by a first time. The visual processing image sensor then performs image acquisition. The photoelectric signal is sent by the photoelectric sensor when it detects the object being measured has passed the second position. The first time is determined based on the distance between the third position and the second position, and the speed of the conveyor belt. The first position is the starting point of the visual processing image sensor's movement, the second position is the detection position of the photoelectric sensor, and the third position is a designated position within the field of view of the visual processing image sensor when it is at the first position. The first speed is matched to the running speed of the conveyor belt. The object under test is visually inspected based on the image acquired by the vision processing image sensor.

2. The method according to claim 1, characterized in that, Before controlling the visual processing image sensor via the motion platform to move from a first position at a first speed along the direction of movement of the conveyor belt, starting from the time the photoelectric signal is detected and delayed by a first time, and before controlling the visual processing image sensor to perform image acquisition, the method further includes: Upon receiving target position information of the object being measured from a visual positioning image sensor, the motion platform controls the position of the visual processing image sensor in the width direction of the conveyor belt to match the target position information based on the target position information. The target position information characterizes the position of the object being measured in the width direction of the conveyor belt, and is determined by the visual positioning image sensor based on the acquired image of the object being measured. The field of view of the visual positioning image sensor covers the width direction of the conveyor belt.

3. The method according to claim 2, characterized in that, The target location information is determined based on the position of the object being measured in the image coordinate system of the visual positioning image sensor and a preset position transformation relationship; The preset position conversion relationship includes the mapping relationship between the position of the visual positioning image sensor in the image coordinate system and the position in the width direction of the conveyor belt.

4. The method according to claim 2, characterized in that, The visual positioning image sensor is a 3D stereo image sensor; Before controlling the visual processing image sensor via the motion platform to move from a first position at a first speed along the direction of movement of the conveyor belt, starting from the time the photoelectric signal is detected and delayed by a first time, and before controlling the visual processing image sensor to perform image acquisition, the method further includes: Upon receiving the target height information of the object being measured sent by the visual positioning image sensor, the motion platform controls the height of the visual processing image sensor to match the target height information based on the target height information.

5. A visual inspection device, characterized in that, include: The unit comprises a receiving unit, a control unit, and a detection unit; wherein: The control unit is configured to, upon receiving a photoelectric signal from the receiving unit, control the visual processing image sensor via a motion platform to move from a first position at a first speed along the direction of movement of the conveyor belt, starting from the time the photoelectric signal is received and delaying for a first time, and control the visual processing image sensor to acquire images; wherein, the photoelectric signal is sent by the photoelectric sensor when it detects that the object being measured has passed through a second position, the first position is the starting position of the movement of the visual processing image sensor, the second position is the detection position of the photoelectric sensor, the first time is determined based on the distance between a third position and the second position, and the speed of movement of the conveyor belt, the third position is the position of the visual processing image sensor near the edge of the field of view of the second position when the visual processing image sensor is in the first position, and the first speed is matched with the running speed of the conveyor belt; The detection unit is used to perform visual detection on the object under test based on the image acquired by the visual processing image sensor.

6. The apparatus according to claim 5, characterized in that, The control unit, via a motion platform, controls the vision processing image sensor to move from a first position at a first speed along the direction of the conveyor belt, starting from the time the photoelectric signal is detected, with a first delay, and before controlling the vision processing image sensor to perform image acquisition, further includes: When the receiving unit receives the target position information of the object being measured sent by the visual positioning image sensor, it controls the position of the visual processing image sensor in the width direction of the conveyor belt to match the target position information based on the target position information. The target position information is used to characterize the position of the object being measured in the width direction of the conveyor belt. The target position information is determined by the visual positioning image sensor based on the image of the object being measured that it has acquired. The field of view of the visual positioning image sensor covers the width direction of the conveyor belt.

7. The apparatus according to claim 6, characterized in that, The target location information is determined based on the position of the object being measured in the image coordinate system of the visual positioning image sensor and a preset position transformation relationship; The preset position conversion relationship includes the mapping relationship between the position of the visual positioning image sensor in the image coordinate system and the position in the width direction of the conveyor belt.

8. The apparatus according to claim 6, characterized in that, The visual positioning image sensor is a 3D stereo image sensor; The control unit, via a motion platform, controls the vision processing image sensor to move from a first position at a first speed along the direction of the conveyor belt, starting from the time the photoelectric signal is detected, with a first delay, and before controlling the vision processing image sensor to perform image acquisition, further includes: Upon receiving the target height information of the object being measured sent by the visual positioning image sensor, the motion platform controls the height of the visually processed image to match the target height information based on the target height information.

9. A visual inspection system, characterized in that, include: Photoelectric sensors, motion platforms, and vision processing image sensors; among which: The photoelectric sensor is used to send a photoelectric signal to the visual processing image sensor when it detects that the object being measured has passed through the second position. The visual processing image sensor is configured to, upon receiving the photoelectric signal, control the motion platform to move from a first position at a first speed along the movement direction of the conveyor belt, starting from the time the photoelectric signal is received and delaying for a first time, and to acquire an image; wherein, the first time is determined based on the distance between the third position and the second position, and the movement speed of the conveyor belt, the first position is the starting position of the movement of the visual processing image sensor, the second position is the detection position of the photoelectric sensor, the third position is the position of the visual processing image sensor near the edge of the field of view of the second position when the visual processing image sensor is in the first position, and the first speed is matched with the running speed of the conveyor belt; The visual processing image sensor is also used to perform visual inspection of the object under test based on the acquired image.

10. The visual inspection system according to claim 9, characterized in that, Also includes: A visual positioning image sensor; the field of view of the visual positioning image sensor covers the width direction of the conveyor belt; The photoelectric sensor is also used to send a photoelectric signal to the visual positioning image sensor when it detects that the object being measured has passed through the second position; The visual positioning image sensor is used to, upon receiving the photoelectric signal, perform image acquisition starting from the time of receiving the photoelectric signal and delaying for a second time, and identify the target position information of the object under test based on the acquired image; wherein, the target position information is used to characterize the position of the object under test in the width direction of the conveyor belt; the second time is determined based on the distance between the fourth position and the second position, and the movement speed of the conveyor belt, wherein the fourth position is a designated position within the field of view of the visual positioning image sensor; The visual positioning image sensor is also used to send the target position to the visual processing image sensor; The visual processing image sensor is also used to control the position of the visual processing image sensor in the width direction of the conveyor belt to match the target position information through the motion platform, based on the target position information.

11. The visual inspection system according to claim 10, characterized in that, The target location information is determined based on the position of the object being measured in the image coordinate system of the visual positioning image sensor and a preset position transformation relationship; The preset position conversion relationship includes the mapping relationship between the position of the visual positioning image sensor in the image coordinate system and the position in the width direction of the conveyor belt.

12. The visual inspection system according to claim 10, characterized in that, The visual positioning image sensor is a 3D stereo image sensor; The visual positioning image sensor is also used to identify the target height information of the object being measured based on the acquired image, and send the height information to the visual processing image sensor; The visual processing image sensor is also used to control the height of the visual processing image to match the target height information through the motion platform, based on the target height information.

Images