Method, device and system for determining the swing angle of ship unloader grab bucket

Abstract

The present invention provides a method, device, and system for determining the swing angle of a ship unloader's grab bucket. A camera is provided at each end of the ship unloader's trolley track, and the field of view of each camera covers the movement range of the grab bucket during the ship unloader's operation. The determination method comprises: obtaining the ship unloader's current position on the trolley track; acquiring video captured by each camera in real time during the ship unloader's operation; determining the grab bucket's swing angle in each frame of the video captured by each camera; and determining the grab bucket's current swing angle based on the two grab bucket swing angles in corresponding frames of the video captured by the two cameras and the ship unloader's current position on the trolley track. The present invention can more accurately determine the swing angle of the ship unloader's grab bucket.

Description

Technical Field

[0001] The present invention relates to the field of mechanical engineering technology, and in particular to a method for determining the swing angle of a ship unloader bucket, a device for determining the swing angle of a ship unloader bucket, a swing angle detection system for a ship unloader bucket, a control system of a ship unloader, an edge computing device, and a computer-readable medium. Background Art

[0002] A ship unloader (GSU) can be used to remove cargo (e.g., coal) from a ship at shore and place it in a transport device.

[0003] During ship unloader operation, the grab bucket's swing angle must be precisely positioned. During GSU operation, the unloader's trolley moves along its track, driving the grab bucket. The grab bucket is controlled by the tension of the unloader's wire rope. The grab bucket will swing to varying degrees during the lifting and trolley movement process. Improper control of this swing can impact operational efficiency at best, or even lead to dangerous situations like collisions. Accurately detecting the grab bucket's real-time position and implementing closed-loop anti-sway measures is crucial for ship unloader automation.

[0004] However, currently, the positioning of the swing angle of the grab bucket of the ship unloader is usually achieved by relying on the actual visual observation of the ship unloader driver and the driver's experience, which may cause inaccurate positioning. Summary of the Invention

[0005] The present invention provides a method for determining the swing angle of a ship unloader bucket, a device for determining the swing angle of a ship unloader bucket, a swing angle detection system for a ship unloader bucket, a control system for a ship unloader, an edge computing device, and a computer-readable medium, which can more accurately position the swing angle of the ship unloader bucket.

[0006] In a first aspect, an embodiment of the present invention provides a method for determining the swing angle of a grab bucket of a ship unloader, wherein a camera device is provided at each end of a trolley travel track of the ship unloader, and the field of view of each camera device covers the movement range of the grab bucket of the ship unloader during operation. The determination method comprises:

[0007] Obtaining the current position of the ship unloader on the trolley travel track;

[0008] acquiring the video captured by each camera device in real time during the operation of the ship unloader;

[0009] Determining a grab bucket swing angle in each frame of the video captured by each camera device;

[0010] The current swing angle of the grab bucket is determined according to the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices and the current position of the ship unloader on the trolley travel track.

[0011] In a second aspect, an embodiment of the present invention provides a device for determining the swing angle of a grab bucket of a ship unloader, wherein a camera device is provided at each end of a trolley travel track of the ship unloader, and the field of view of each camera device covers the movement range of the grab bucket of the ship unloader during operation; the determining device comprises:

[0012] The first acquisition module is used to: acquire the current position of the ship unloader on the vehicle travel track;

[0013] The second acquisition module is used to: acquire the video captured by each camera device in real time during the operation of the ship unloader;

[0014] The first calculation module is used to determine the grab bucket swing angle in each frame of the video captured by each camera device;

[0015] The second calculation module is used to determine the current swing angle of the grab bucket based on the two grab bucket swing angles of the corresponding frame images in the video captured by the two cameras and the current position of the ship unloader on the trolley travel track.

[0016] In a third aspect, an embodiment of the present invention provides a system for detecting a swing angle of a ship unloader grab bucket, comprising: an edge computing device and two camera devices connected to the edge computing device, wherein:

[0017] The two camera devices are arranged at both ends of the trolley travel track, and the field of view of each camera device covers the movement range of the grab bucket of the ship unloader during operation; each camera device is used to: collect video within the field of view during the operation of the ship unloader, and send the video to the edge computing device; the edge computing device is the swing angle determination device provided by the second aspect.

[0018] In a fourth aspect, an embodiment of the present invention provides a control system for a ship unloader, comprising the ship unloader grab bucket swing angle detection system, anti-shake system, and automatic control system provided in the third aspect, wherein the anti-shake system is connected to the swing angle detection system and the automatic control system, wherein:

[0019] The automatic control system is used to: control the trolley to move on the trolley track during the operation of the ship unloader, so as to drive the grab bucket to move;

[0020] The swing angle detection system is used to: detect the current swing angle of the grab bucket during movement in real time, and send the current swing angle to the anti-shake system;

[0021] The anti-shake system is used to: obtain motion information of the trolley, determine the additional speed of the trolley according to the motion information of the trolley and the current swing angle, and send the additional speed to the automatic control system;

[0022] The automatic control system is used to adjust the movement of the trolley according to the additional speed so that the current swing angle of the grab bucket is controlled within a preset range.

[0023] In a fifth aspect, an embodiment of the present invention provides an edge computing device, the device comprising: at least one memory and at least one processor;

[0024] The at least one memory is configured to store a machine-readable program;

[0025] The at least one processor is used to call the machine-readable program to execute the method provided by the first aspect.

[0026] In a sixth aspect, an embodiment of the present invention provides a computer-readable medium having computer instructions stored thereon. When the computer instructions are executed by a processor, the processor executes the method provided in the first aspect.

[0027] The method, device, and system for determining the swing angle of a ship unloader's grab bucket, provided by embodiments of the present invention, are implemented based on the installation of a camera at each end of the ship unloader's trolley track. After acquiring the video captured by the two cameras, the system first determines the ship unloader's current position on the trolley track. The system then determines the two grab bucket swing angles in two corresponding frames of the video captured by the two cameras. Based on the two grab bucket swing angles and the ship unloader's current position on the trolley track, the system then determines the grab bucket's current swing angle. This process considers not only the grab bucket's swing angle from the perspectives of the two cameras but also the ship unloader's position on the trolley track. Due to the different positions of the ship unloader, the clarity of the two cameras, the perspective deviation, and other factors vary. These factors are comprehensively considered to determine the real-time swing angle of the grab bucket. This approach avoids excessive swing angle deviation caused by certain factors and improves the accuracy of swing angle calculation. Furthermore, the method provided by embodiments of the present invention relies on minimal hardware, resulting in relatively low hardware and mechanical modification costs. The embodiment of the present invention applies machine vision technology to a ship unloader, successfully solving the problem of low accuracy in detecting the grab bucket swing angle of the ship unloader. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0029] Figure 1 1 is a flow chart of a method for determining the swing angle of a ship unloader grab bucket provided by one embodiment of the present invention;

[0030] Figure 2 1 is a flow chart of step S4 in a method for determining a swing angle of a ship unloader grab bucket provided by one embodiment of the present invention;

[0031] Figure 3 This is a structural block diagram of a device for determining the swing angle of a ship unloader grab bucket provided by one embodiment of the present invention;

[0032] Figure 4 This is a structural block diagram of a swing angle detection system for a ship unloader grab bucket provided by one embodiment of the present invention;

[0033] Figure 5 This is a structural block diagram of a swing angle detection system for a ship unloader grab bucket provided by one embodiment of the present invention;

[0034] Figure 6 This is a schematic structural diagram of a control system for a ship unloader provided by one embodiment of the present invention;

[0035] Description of reference numerals:

[0036] Steps S1 to S4

[0037] Steps S41 to S44

[0038] 10 Swing angle determination device

[0039] 11 First acquisition module

[0040] 12 Second Acquisition Module

[0041] 13 First computing module

[0042] 14 Second computing module

[0043] 100 Swing Angle Detection System

[0044] 110 Camera

[0045] 120 Edge Computing Devices

[0046] 130 Wireless Client

[0047] 140 Wireless Access Points

[0048] 200 Image Stabilization System

[0049] 300 Automatic Control System

[0050] 400 Ship Unloader Control System DETAILED DESCRIPTION

[0051] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0052] In a first aspect, an embodiment of the present invention provides a method for determining the swing angle of a ship unloader grab bucket. The execution subject of the method may be a computer device, for example, an edge computing device installed in an electrical room.

[0053] It is understandable that a ship unloader generally includes a trolley track, a trolley track, a trolley that moves on the trolley track, a grab bucket connected to the trolley via a wire rope, a control system for controlling the trolley, and the like. Under normal circumstances, the trolley track and the trolley track do not intersect in three-dimensional space but have a certain angle, for example, an angle of 90°. The trolley track is located on the ground at the shore, and the entire ship unloader can move on the trolley track, so that the position of the ship unloader can be adjusted according to the position of the ship at the shore. The trolley track is mounted on the support of the ship unloader and is located in the air. In this way, the automatic control system controls the movement of the trolley on the trolley track, and the trolley can drive the grab bucket to move. For example, the grab bucket can be driven to fall above the hull, grab the cargo in the ship and lift it up, and then smoothly run to the top of the unloading area, and the cargo in the grab bucket can be shaken off into the device in the unloading area.

[0054] In order to facilitate observation of the movement of the grab bucket during the entire process, a camera device may be provided at each end of the trolley travel track, and the field of view of each camera device covers the movement range of the grab bucket during operation of the ship unloader.

[0055] It is understood that the two ends of the trolley track refer to the head and tail of the trolley track, i.e., the two ends. In practice, the camera devices can be specifically set up in an open space near the ends of the trolley track. The field of view of each camera device covers the full range of motion of the grab bucket during operation, avoiding the situation where the video captured by a camera device at a certain time does not include the grab bucket.

[0056] The purpose of installing a camera at each end of the trolley track is to ensure that video of the ship unloader, including the grab bucket, can be captured regardless of its position on the track. For example, when the ship unloader approaches the head of the trolley track, the camera located at the head is too close to the grab bucket. The image clarity within the camera's field of view is higher, but the grab bucket's swing angle deviation is larger. The camera located at the rear, however, is farther from the grab bucket, reducing the clarity of the captured video and hindering image feature extraction. However, the grab bucket's swing angle deviation is smaller. In this case, the video captured by one camera can be selected as the primary video, while the video captured by the other camera can be used as the auxiliary video. The grab bucket's swing angle can be calculated using both the primary and auxiliary videos.

[0057] For example, in actual demand, the accuracy of the grab bucket's swing angle is very high. When the ship unloader approaches the head of the trolley track, the video captured by the rear camera, where the grab bucket's swing angle deviation is smaller, can be used as the primary video, and the video captured by the front camera can be used as the auxiliary video. Similarly, if the ship unloader approaches the tail of the trolley track, the video captured by the front camera can be used as the primary video to calculate the grab bucket's swing angle.

[0058] That is to say, two camera devices are set here. According to the position of the ship unloader in the trolley's travel track, the video collected by one camera device can be selected as the main video, and the video collected by the other camera device can be selected as the auxiliary video. The swing angle of the grab bucket is calculated together by the main video and the auxiliary video. The specific selection of which camera device to collect the video as the main video and which camera device to collect the video as the auxiliary video depends on the actual needs of the specific scenario.

[0059] See also Figure 1 The method for determining the swing angle of the grab bucket of a ship unloader provided by an embodiment of the present invention includes the following steps S1 to S4:

[0060] S1. Obtain the current position of the ship unloader on the vehicle travel track;

[0061] As you can understand, when a ship unloader unloads cargo from a ship, it moves along the trolley track based on the ship's position, aligning the unloader with the ship's position to facilitate cargo unloading. For a given ship, the unloader's position along the trolley track is typically fixed. However, if the ship is too large, the unloader can be moved during the unloading process to ensure it's positioned appropriately for cargo unloading.

[0062] S2. acquiring the video captured by each camera device in real time during the operation of the ship unloader;

[0063] For example, during the operation of the ship unloader, each camera device will send the video it collects to the edge computing device in real time, so that the edge computing device will obtain a video stream formed by the frame images transmitted by each camera device.

[0064] S3, determining the grab bucket swing angle in each frame of the video captured by each camera device;

[0065] In a certain scenario, the trolley and grab bucket are connected by a wire rope. The grab bucket's swing angle is the angle between the line on which the wire rope is located and the line on which the wire rope is vertical. It can also be directly understood as the angle between the line on which the wire rope is located and the vertical direction.

[0066] It's understandable that the bucket's swing angle must be determined for each frame of video sent by each camera. That is, one bucket swing angle can be obtained for each frame. In videos sent by two cameras, two frames corresponding to the same time point are considered corresponding frames. That is, for two cameras, two bucket swing angles can be obtained from the corresponding two frames.

[0067] In specific implementation, the process of determining the grab bucket swing angle in each frame of the video captured by each camera device in S3 may specifically include:

[0068] Edge detection is used to detect the area where the wire rope connected to the grab is located in each frame image, and the area where the wire rope is located is segmented. Feature extraction is performed in the segmented area, and the angle between the extracted wire rope and the vertical direction is used as the grab swing angle in the frame image.

[0069] That is to say, for each frame of image, edge detection technology is used to detect the area where the wire rope is located, and then the area where the wire rope is located is segmented. Feature extraction is performed on the segmented area, and the straight line where the wire rope is located in the area can be obtained. Then, the angle between the straight line where the wire rope is located and the vertical direction can be calculated, and the angle is used as the grab bucket swing angle in the frame image.

[0070] In reality, wire ropes are not always straight. For example, when unloading cargo by shaking the grab bucket, the tail end of the wire rope, the end closest to the grab bucket, may be curved. In this case, directly using edge detection to determine the grab bucket's swing angle would inaccurately extract the straight line on which the wire rope lies, resulting in potential errors in the calculated swing angle. Therefore, before edge detection is used to detect the location of the wire rope, nonlinear distortion correction is performed on each image frame to ensure that the wire rope connected to the grab bucket appears straight in each frame.

[0071] That is to say, before edge detection, nonlinear distortion calibration is performed on each frame of the image. Nonlinear distortion calibration can correct the curved part to make it a straight line, and the part that is converted from a curve to a straight line is smoothly connected with other straight line parts. This can avoid the swing angle deviation caused by the curved end of the wire rope.

[0072] Furthermore, after nonlinear distortion calibration is performed on each frame of image, the frame of image may be converted into an image in the HSV space before edge detection is performed.

[0073] It is understandable that RGB is the color space we are most exposed to. An image is represented by three channels: red (R), green (G), and blue (B). Different combinations of these three colors can form almost all other colors. The RGB color space is the most basic, most commonly used, and hardware-oriented color space in image processing, and it is also relatively easy to understand. Images acquired in natural environments are easily affected by natural lighting, occlusion, and shadows, that is, they are relatively sensitive to brightness. The three components of the RGB color space are closely related to brightness, that is, as long as the brightness changes, the three components will change accordingly. The human eye has different sensitivities to these three color components. Among monochrome colors, the human eye is least sensitive to red and most sensitive to blue. Therefore, the RGB color space is a color space with poor uniformity. If color similarity is directly measured using Euclidean distance, the result will deviate significantly from human vision. Therefore, the RGB color space is suitable for display systems, but not for image processing. Therefore, in the embodiment of the present invention, the image is converted into an image in the HSV space.

[0074] Understandably, the HSV color space is closer to people's perception of color than RGB. It intuitively expresses color hue, vividness, and brightness, making it easier to compare colors. The HSV color space represents color images in three parts: Hue (hue), Saturation (saturation, color purity), and Value (lightness).

[0075] It can be seen that in the embodiment of the present invention, converting the image in the RGB color space into the image in the HSV color space is more conducive to the subsequent edge detection process and is easier to extract feature information of the image.

[0076] S4. Determine the current swing angle of the grab bucket according to the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices and the current position of the ship unloader on the vehicle travel track.

[0077] In other words, the calculation of the grab bucket's swing angle depends not only on the two grab bucket angles in the two corresponding frames but also on the ship unloader's current position on the trolley track. When the ship unloader is at different positions on the trolley track, the distances between the two cameras and the grab bucket vary, resulting in differences in the clarity of the corresponding frames captured by the two cameras and deviations due to viewing angles. Therefore, the calculation of the final grab bucket swing angle depends not only on the two grab bucket angles in the corresponding frames but also on the ship unloader's current position on the trolley track. This significantly improves the accuracy of the final calculated grab bucket swing angle.

[0078] In the specific implementation, see Figure 2 The step of determining the current swing angle of the grab bucket according to the two grab bucket swing angles of corresponding frame images in the videos captured by the two cameras and the current position of the ship unloader on the vehicle travel track in S4 may specifically include S41 to S44:

[0079] S41, calculating the position deviation between the ship unloader and each camera device according to the current position of the ship unloader on the trolley travel track;

[0080] It is understandable that by calculating the deviations between the current position of the ship unloader and the positions of the two camera devices, two position deviations can be obtained. When the position of the ship unloader is fixed, the values ​​of the two position deviations are constant.

[0081] S42, determining whether the two position deviations are equal;

[0082] It is understandable that if the two position deviations are equal, it means that the ship unloader is located in the middle of the trolley track. At this time, the clarity and viewing angle deviation of the videos captured by the two cameras are roughly the same. Therefore, the weight values ​​corresponding to the two cameras can be set to be equal. For example, the weight value corresponding to each camera is 0.5.

[0083] However, if the two position deviations are not equal, multiple factors need to be considered when setting the weight values ​​of the two cameras, such as whether the current position of the unloader is close to the head or position, the size of the two position deviations corresponding to the two cameras, etc. For details, please refer to S43 below.

[0084] S43. If the two position deviations are not equal, determining a first camera device and a second camera device among the two camera devices based on whether the current position is within the preset position range and the magnitude relationship between the two position deviations, wherein the weight corresponding to the first camera device is higher than the weight corresponding to the second camera device;

[0085] It is understandable that if the current position of the ship unloader is within the preset position range, there will be a certain difference in the clarity, viewing angle deviation and other factors of the videos captured by the two cameras, but the difference is not very large. At this time, the weight values ​​corresponding to the two cameras can be set to have a certain difference, but the difference is not very large. For example, the weight value corresponding to one camera is 0.4, and the weight value corresponding to the other camera is 0.6. Then which camera has a weight value of 0.4 and which camera has a weight value of 0.6? At this time, you can consider the actual scene and choose whether you have a higher requirement for clarity or a higher requirement for viewing angle deviation, and make a choice based on actual needs.

[0086] In a specific implementation, determining the first camera device and the second camera device of the two camera devices according to whether the current position is within the preset position range and the magnitude relationship between the two position deviations in S43 may specifically include at least one of the following:

[0087] (1) If the current position is within the preset position range, the camera device with a smaller position deviation is used as the first camera device, and the camera device with a larger position deviation is used as the second camera device; when the current position is outside the preset position range, the weight value corresponding to the first camera device is greater than the weight value corresponding to the first camera device when the current position is within the preset range.

[0088] (2) If the current position is outside the preset position range, the camera device with a larger position deviation is used as the first camera device, and the camera device with a smaller position deviation is used as the second camera device; the weight value corresponding to the first camera device when the current position is outside the preset position range is greater than the weight value corresponding to the first camera device when the current position is within the preset range.

[0089] It is understandable that when the current position is within the preset position range, the clarity of the video captured by the camera device with a smaller position deviation is better, and the difference between the viewing angle deviations of the two camera devices is not large. Therefore, at this time, the camera device with a smaller position deviation can be used as the first camera device, and the camera device with a larger position deviation can be used as the second camera device. The weight of the first camera device is higher than the weight value of the second camera device, that is, the first camera device is the main camera device, and the second camera device is the auxiliary camera device.

[0090] It is understandable that when the current position is outside the preset position range, the camera device with a relatively small position deviation is relatively close to one end of the trolley's travel track. At this time, the viewing angle deviation is relatively large under the viewing angle of the camera device, and the camera device with a relatively large position deviation is relatively far away from the grab bucket. Although the clarity of the captured video is reduced, the viewing angle deviation is not large. At this time, the camera device with a relatively large position deviation can be used as the first camera device, and the other camera device can be used as the second camera device. The weight value of the first camera device is higher than the weight value of the second camera device, that is, the first camera device is the main camera device, and the second camera device is the auxiliary camera device.

[0091] The above describes how to determine which of the two cameras is primary and which is secondary at a given moment. However, the current position of the trolley on the trolley track may change at different times. When the current position is within the preset position range, the actual positional deviation between the two cameras is not much, and the difference in the weight values ​​of the two cameras can be set relatively small. However, when the current position is outside the preset position range, the positional deviation between the two cameras is relatively large, and the difference in the weight values ​​of the two cameras can be set relatively large. For example, when the current position is within the preset position range, the weight value of the first camera is 0.6, and the weight value of the second camera is 0.4. When the current position is outside the preset position range, the weight value of the first camera can be set to 0.7, and the weight value of the second camera can be set to 0.3. That is, the weight value corresponding to the first camera when the current position is outside the preset position range is greater than the weight value corresponding to the first camera when the current position is within the preset range.

[0092] Among them, the preset position range is a preset position range on the trolley track. For example, with the middle position of the trolley track as the center, the same distance is extended to both ends, and the obtained position range is used as the above-mentioned preset position range.

[0093] S44. Calculate the current swing angle of the grab bucket according to the two grab bucket swing angles of the corresponding frame images in the video captured by the two cameras and the weight values ​​corresponding to the two cameras.

[0094] For example, the weight value of the first camera device is 0.65, the weight value of the second camera device is 0.35, the grab bucket swing angle in a frame image of the first camera device is c1, and the grab bucket swing angle in the corresponding frame image of the second camera device is c2, so the final grab bucket swing angle is 0.65*c1+0.35*c2.

[0095] In a specific implementation, before S4, the method provided by the embodiment of the present invention may further include:

[0096] Performing a validity check on the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices; if the two grab bucket swing angles are valid, executing the step of determining the current swing angle of the grab bucket;

[0097] Among them, the validity detection includes judging whether the two grab bucket swing angles are both smaller than the preset swing angle and whether the difference between the two grab bucket swing angles is less than the preset difference; if the two grab bucket swing angles are both smaller than the preset swing angle and the difference between the two grab bucket swing angles is less than the preset difference, then the two grab bucket swing angles are valid.

[0098] It is understandable that during the operation of the ship unloader, the grab bucket's swing angle has a certain floating range. If at a certain moment, the grab bucket's swing angle in a frame of image exceeds this floating range, it indicates that an error may have occurred when calculating the grab bucket's swing angle in this frame of image. In addition, regardless of the ship unloader's position on the trolley's travel track, the difference between the two grab bucket's swing angles in the corresponding frames of video captured by the two cameras also has a certain range. If the difference between the two grab bucket's swing angles in the corresponding two frames of image is too large, it indicates that an error has occurred when calculating the grab bucket's swing angle in at least one of the two frames of image. It can be seen that in these two cases, the two calculated grab bucket swing angles are unusable. If the two grab bucket swing angles are continued to be used to calculate the final swing angle, the calculated final swing angle will result in a large error.

[0099] It is understandable that in actual scenarios, due to the influence of factors such as weather, light, possible aerial obstructions, etc., errors in the calculation of the grab bucket swing angle may occur. In order to avoid the calculation error affecting the calculation of the final swing angle, the embodiment of the present invention performs a validity test on the two grab bucket swing angles. Only after the test, it is found that both grab bucket swing angles are valid, will the two grab bucket swing angles be used in subsequent calculations.

[0100] In practice, if the validity check finds that the calculation is invalid, the calculation of the grab bucket swing angle of the two corresponding frame images can be discarded, and the calculation of the grab bucket swing angle is performed for the next frame image.

[0101] Of course, in order to further improve the accuracy of the grab calculation, in one embodiment of the present invention, before the validity detection of the two grab swing angles of the corresponding frame images in the video captured by the two camera devices is performed, the following steps (1) to (3) may be further included:

[0102] Step (1): calculating the position deviation between the ship unloader and each camera device according to the current position of the ship unloader on the trolley travel track;

[0103] Step (2): obtaining a calibrated swing angle of each camera device under its corresponding position deviation; wherein the calibrated swing angle is the grab bucket swing angle in the image captured by each camera device when the steel wire rope connecting the grab bucket is in a vertical state and the position deviations between the ship unloader and each camera device are different;

[0104] It is understandable that pre-calibration is required. For a ship unloader at a certain position on the trolley track, the positional deviations between the two cameras and the ship unloader are constant. When the ship unloader is in a stable operating state and the grab bucket's wire rope is vertical, the grab bucket's swing angle is calculated in the images captured by each camera and used as the calibrated swing angle for the corresponding positional deviation of that camera. The ship unloader is then moved to another position on the trolley track. At this point, the positional deviations between each camera and the ship unloader change, and calibration is repeated at this positional deviation until the calibrated swing angle is determined for each position of the ship unloader on the trolley track.

[0105] Step (3): Calculate the difference between the grab bucket swing angle in each frame image in the video captured by each camera device and the calibrated swing angle, and use the difference as the grab bucket swing angle of each frame image in the video captured by each camera device after decalibration;

[0106] Correspondingly, the validity detection of the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices includes: performing validity detection on the grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices after decalibration.

[0107] It is understandable that the current position of the ship unloader is first determined, and then the position deviation between the current position and the two cameras is calculated. Then, the calibrated swing angle of each camera under the corresponding position deviation is found, and the grab bucket swing angle in the image in the video captured by the camera device is subtracted from the calibrated swing angle to obtain the uncalibrated grab bucket swing angle. Then, the uncalibrated grab bucket swing angle is used to perform validity detection. This can reduce the error in validity detection caused by the viewing angle deviation and the subsequent calculation error of the final swing angle.

[0108] In specific implementation, after the real-time swing angle of the grab bucket is calculated, the real-time swing angle can be rendered and marked in the video captured by the camera device. Of course, the corresponding calibrated swing angle can also be marked in the video for comparison.

[0109] Of course, after obtaining the final real-time swing angle, the swing angle can also be sent to the anti-shake system of the ship unloader, so that the anti-shake system and the automatic control system can control the movement of the trolley according to the swing angle, thereby realizing closed-loop control of grab anti-shake.

[0110] The method for determining the swing angle of a ship unloader's grab bucket, provided in an embodiment of the present invention, is implemented by installing a camera at each end of the ship unloader's trolley track. After acquiring the video captured by the two cameras, the method first determines the ship unloader's current position on the trolley track. The method then determines the two grab bucket swing angles in two corresponding frames of the video captured by the two cameras. Based on the two grab bucket swing angles and the ship unloader's current position on the trolley track, the current grab bucket swing angle is determined. This process considers not only the grab bucket's swing angle from the perspectives of the two cameras but also the ship unloader's position on the trolley track. Due to the different positions of the ship unloader, the clarity of the two cameras, perspective deviation, and other factors vary. These factors are comprehensively considered to determine the real-time grab bucket swing angle. This approach avoids excessive swing angle deviation caused by certain factors and improves the accuracy of swing angle calculation. Furthermore, the method provided in an embodiment of the present invention relies on minimal hardware, resulting in relatively low hardware and mechanical modification costs. The embodiment of the present invention applies machine vision technology to a ship unloader, successfully solving the problem of low accuracy in detecting the grab bucket swing angle of the ship unloader.

[0111] In a second aspect, an embodiment of the present invention provides a device for determining the swing angle of a grab bucket of a ship unloader. A camera device is provided at each end of the trolley travel track of the ship unloader, and the field of view of each camera device covers the movement range of the grab bucket of the ship unloader during operation. Figure 3 , the determining device 10 includes:

[0112] The first acquisition module 11 is used to: acquire the current position of the ship unloader on the vehicle travel track;

[0113] The second acquisition module 12 is used to: acquire the video captured by each camera device in real time during the operation of the ship unloader;

[0114] The first calculation module 13 is used to determine the grab bucket swing angle in each frame of the video captured by each camera device;

[0115] The second calculation module 14 is used to determine the current swing angle of the grab bucket according to the two grab bucket swing angles of the corresponding frame images in the video captured by the two cameras and the current position of the ship unloader on the trolley travel track.

[0116] Among them, the hardware device of the determination device can be an edge computing device installed in an electrical room.

[0117] In some embodiments, the second computing module specifically includes:

[0118] The first calculation unit is configured to calculate a position deviation between the ship unloader and each camera device according to a current position of the ship unloader on the trolley travel track;

[0119] The first judging unit is configured to judge whether the two position deviations are equal;

[0120] a weight determination unit, configured to: if the two position deviations are not equal, determine, based on whether the current position is within the preset position range and the magnitude relationship between the two position deviations, a first camera device and a second camera device of the two camera devices, wherein the weight corresponding to the first camera device is higher than the weight value corresponding to the second camera device;

[0121] The second calculation unit is used to calculate the current swing angle of the grab bucket according to the two grab bucket swing angles of the corresponding frame images in the video captured by the two cameras and the weight values ​​corresponding to the two cameras respectively.

[0122] Furthermore, the weight determination unit is specifically used to: if the current position is within the preset position range, the camera device with a smaller position deviation is used as the first camera device, and the camera device with a larger position deviation is used as the second camera device; if the current position is outside the preset position range, the camera device with a larger position deviation is used as the first camera device, and the camera device with a smaller position deviation is used as the second camera device; when the current position is outside the preset position range, the weight value corresponding to the first camera device is greater than the weight value corresponding to the first camera device when the current position is within the preset range.

[0123] In some embodiments, the apparatus further comprises:

[0124] The first detection module is used to perform validity detection on the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices before the second calculation unit determines the current swing angle of the grab bucket; if the two grab bucket swing angles are valid, the second calculation unit executes the step of "determining the current swing angle of the grab bucket"; wherein, the validity detection includes judging whether the two grab bucket swing angles are both smaller than the preset swing angle and whether the difference between the two grab bucket swing angles is less than the preset difference; if the two grab bucket swing angles are both smaller than the preset swing angle and the difference between the two grab bucket swing angles is less than the preset difference, then the two grab bucket swing angles are valid.

[0125] Furthermore, the device also includes:

[0126] A first calibration module is configured to calculate, before the first detection module performs validity detection on the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices, the position deviation between the ship unloader and each camera device according to the current position of the ship unloader on the trolley travel track; obtain the calibrated swing angle of each camera device under its corresponding position deviation; wherein the calibrated swing angle is the grab bucket swing angle in the image captured by each camera device when the steel wire rope connecting the grab bucket is in a vertical state and the ship unloader and each camera device are at different position deviations; calculate the difference between the grab bucket swing angle in each frame image in the video captured by each camera device and the calibrated swing angle, and use the difference as the grab bucket swing angle of each frame image in the video captured by each camera device after decalibration;

[0127] Correspondingly, the first detection module is specifically used to: perform validity detection on the grab bucket swing angle after decalibration of the corresponding frame images in the video captured by the two camera devices.

[0128] In some embodiments, the first computing module specifically includes:

[0129] The edge detection unit is used to detect the area where the wire rope connected to the grab is located in each frame of the image by edge detection, segment the area where the wire rope is located, perform feature extraction in the segmented area, and use the extracted angle between the wire rope and the vertical direction as the grab swing angle in the frame of the image.

[0130] Furthermore, the first calculation module specifically includes:

[0131] The image processing unit is used to perform nonlinear distortion calibration on each frame of image before the edge detection unit detects the area where the wire rope is located using edge detection, so that the wire rope connected to the grab bucket in each frame of image becomes a straight line; and convert each frame of image into an image in HSV space.

[0132] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents of the device provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect above, and will not be repeated here.

[0133] In a third aspect, an embodiment of the present invention provides a swing angle detection system for a ship unloader grab bucket.

[0134] See also Figure 4The swing angle detection system 100 may include: an edge computing device 120 and two camera devices 110 connected to the edge computing unit, wherein: the two camera devices are arranged at both ends of the trolley travel track, and the field of view of each camera device covers the movement range of the grab bucket of the ship unloader during operation; each camera device is used to: collect video within the field of view during the operation of the ship unloader, and send the video to the edge computing device; the edge computing device 120 is the swing angle determination device 10 provided by the second aspect.

[0135] As you can see, two cameras are installed at the ship unloader's work site, and the edge computing device is used to calculate the real-time swing angle of the grab bucket based on the videos captured by the two cameras. The edge computing device can be installed in the electrical room, allowing staff to observe the real-time swing angle from there.

[0136] In a specific scenario, while a ship unloader is operating, two cameras capture video and send it to an edge computing device. The edge computing device then performs the following steps: It obtains the current position of the ship unloader on the trolley track; it captures the video captured by each camera in real time while the ship unloader is operating; it determines the grab bucket's swing angle for each frame of video captured by each camera; and it determines the current grab bucket's swing angle based on the two grab bucket's swing angles in the corresponding frames of video captured by the two cameras and the ship unloader's current position on the trolley track. This method allows the final real-time swing angle to be calculated and annotated in the video, allowing staff in the electrical room to see the specific grab bucket swing angle.

[0137] In the specific implementation, see Figure 5 The swing angle detection system 100 may also include: two wireless clients 130 and a wireless access point 140; the two wireless clients are connected to the two camera devices in a one-to-one correspondence, and the wireless access point is connected to the edge computing device, and the communication connection between the two camera devices and the edge computing device is realized through the wireless connection between the two wireless clients and the wireless access point.

[0138] In other words, each camera sends video to a wireless access point via its corresponding wireless client. The wireless access point then transmits the video from both cameras to the edge computing device, enabling wireless communication between the cameras and the edge computing device. Data between the wireless client and the wireless access point can be transmitted using the IEEE 802.11ac network protocol, ensuring real-time video data and network stability.

[0139] Of course, data can also be transmitted between the camera device and the edge computing device using a wired connection.

[0140] It can be seen that in the detection system provided by the embodiment of the present invention,

[0141] The detection system provided by the embodiment of the present invention can determine the grab bucket's swing angle while the camera device is collecting video. Not only is the grab bucket's accuracy high, but the response speed is also fast. The detection system's determination of the grab bucket's swing angle is independent of whether the grab bucket has an initial swing angle. Therefore, even when the grab bucket has an initial swing angle, the grab bucket's swing angle can be accurately determined, facilitating the closed-loop control of the subsequent anti-sway system and avoiding the closed-loop failure that occurs in the prior art when the grab bucket has an initial swing angle. Moreover, the system provided by the embodiment of the present invention only requires two cameras, an edge computing device, and related transmission units. The structure of the entire system is very simple. The simple structure will improve the stability of the system, and it is also relatively convenient to construct and modify, with low subsequent maintenance costs. In addition, since the camera device can be set up in the open space next to both ends of the trolley's travel track, it will not be affected by the vibration of the trolley.

[0142] It is understandable that the explanation, specific implementation, beneficial effects, examples and other contents of the swing angle detection system provided by the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect above, and will not be repeated here.

[0143] In a fourth aspect, an embodiment of the present invention provides a control system for a ship unloader.

[0144] See also Figure 6 The control system 400 of the ship unloader may include the swing angle detection system 100, the anti-shake system 200 and the automatic control system 300 of the ship unloader grab provided in the third aspect, wherein the anti-shake system is connected to the swing angle detection system and the automatic control system, wherein:

[0145] The automatic control system is used to: control the trolley to move on the trolley track during the operation of the ship unloader, so as to drive the grab bucket to move;

[0146] The swing angle detection system is used to: detect the current swing angle of the grab bucket during movement in real time, and send the current swing angle to the anti-shake system;

[0147] The anti-shake system is used to: obtain motion information of the trolley, determine the additional speed of the trolley according to the motion information of the trolley and the current swing angle, and send the additional speed to the automatic control system;

[0148] The automatic control system is used to adjust the movement of the trolley according to the additional speed so that the current swing angle of the grab bucket is controlled within a preset range.

[0149] In other words, the ship unloader's control system consists of three subsystems: the grab bucket's swing angle detection system, the anti-shake system, and the automatic control system. The automatic control system controls the grab bucket's movement by controlling the trolley's direction, speed, acceleration, and other parameters according to a preset program. The swing angle detection system determines the grab bucket's real-time swing angle during movement and transmits this real-time angle to the anti-shake system. The anti-shake system generates an additional velocity for the trolley based on the real-time swing angle and transmits it to the automatic control system. The automatic control system then adds this additional velocity to the trolley's current speed, adjusting the trolley's speed and achieving closed-loop control of the grab bucket.

[0150] In a specific implementation, the movement information of the trolley may include the movement direction of the trolley, the movement speed of the trolley and the current position of the trolley on the trolley travel track;

[0151] Correspondingly, the anti-shake system can be specifically used for: if the current position of the trolley on the trolley travel track is in a stable motion range, then the additional speed is generated according to the motion direction of the trolley and the motion speed of the trolley, and the additional speed can make the current swing angle of the grab bucket within the first range after the automatic control system adjusts the motion of the trolley, and the grab bucket can move smoothly when the current swing angle is within the first range; if the current position of the trolley on the trolley travel track is in the unloading range, then the additional speed is generated according to the motion direction of the trolley and the motion speed of the trolley, and the additional speed can make the current swing angle of the grab bucket within the second range after the automatic control system adjusts the motion of the trolley, and the grab bucket can swing to shake off the cargo in the grab bucket when the current swing angle is within the first range.

[0152] In a specific scenario, the grab bucket's movement occurs in multiple stages. First, a trolley controls the grab bucket to drop vertically downward onto the top of the ship's hull to grab the cargo. After grabbing the cargo, the grab bucket is lifted to a certain height and then smoothly moves to the unloading area for unloading. During this stable operation phase, the grab bucket's swing angle needs to be as small as possible to maintain smooth movement and prevent the cargo from falling. Once the grab bucket reaches the unloading area, it needs to swing at a certain angle to shake out the cargo. This swing angle must be controlled to avoid being too large or too small.

[0153] For the above scenario, the anti-shake system needs to consider the direction and speed of the vehicle's movement when generating additional velocity. For example, during a stable motion phase, if the vehicle is pulling the grab bucket to the left, and the bucket has a rightward swing angle, the vehicle's speed can be reduced. This causes the bucket to instantly move leftward at its original speed due to inertia, reducing the rightward swing angle and approaching vertical. In this case, the additional velocity is directed to the right, so the automatic control system adds this rightward additional velocity to the original leftward velocity, reducing the vehicle's leftward speed. For another example, if the vehicle is moving to the right, and the grab bucket's rightward swing angle is too large, reducing the swing angle is necessary. Therefore, the anti-shake system generates an additional velocity to the right, adding this rightward additional velocity to the vehicle's original rightward velocity. This increases the vehicle's rightward velocity, reducing the grab bucket's rightward swing angle and achieving closed-loop control of the swing angle.

[0154] It is understandable that during the stable operation stage, through the closed-loop control of the anti-shake system and the automatic control system, the swing angle of the grab bucket can be controlled within the first range. At this time, the swing angle of the grab bucket is very small and will not cause the cargo in the grab bucket to fall.

[0155] Similarly, for the above scenario, the generation of additional velocity needs to take into account the direction and speed of the trolley's movement. For example, during unloading, if the trolley drives the grab bucket, the bucket has a small swing angle, but this angle is insufficient to shake off the cargo. In this case, the swing angle needs to be increased. Therefore, the anti-shake system generates additional velocity. The automatic control system adds this additional velocity to the trolley's original speed, increasing the grab bucket's swing angle and further shaking off the cargo.

[0156] It can be seen that the anti-shake system and automatic control system here can not only control the swing angle of the grab bucket within a very small range, but also control the swing angle of the grab bucket within a relatively large range, so that different tasks can be completed at different stages.

[0157] In practice, the edge computing device needs to know the current position of the ship unloader on the trolley track when calculating the real-time swing angle. Since the automatic control system stores the ship unloader's real-time operating information, such as its position on the trolley track, the edge computing device is connected to the automatic control system to obtain the ship unloader's current position on the trolley track from the automatic control system.

[0158] Furthermore, since the anti-shake system needs to know the car's current operating information when generating additional speed, the edge computing device can obtain the car's motion information from the automatic control system and send it to the anti-shake system. Of course, since the anti-shake system and the automatic control system are directly connected, the anti-shake system can also directly obtain the car's motion information from the automatic control system.

[0159] It is understandable that the explanation of the relevant contents, specific implementation methods, beneficial effects, examples, etc. in the system provided by the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0160] In a fifth aspect, an embodiment of the present invention provides an edge computing device, which includes: at least one memory and at least one processor; the at least one memory is used to store a machine-readable program; and the at least one processor is used to call the machine-readable program to execute the method provided in the first aspect.

[0161] It is understandable that the explanation, specific implementation, beneficial effects, examples, etc. of the relevant contents in the device provided by the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0162] In a sixth aspect, an embodiment of the present invention provides a computer-readable medium having computer instructions stored thereon. When the computer instructions are executed by a processor, the processor executes the method provided in the first aspect.

[0163] Specifically, a system or device equipped with a storage medium can be provided, on which software program codes that implement the functions of any of the above-mentioned embodiments are stored, and a computer (or CPU or MPU) of the system or device can be enabled to read and execute the program codes stored in the storage medium.

[0164] In this case, the program code itself read from the storage medium can realize the function of any one of the above-mentioned embodiments, and thus the program code and the storage medium storing the program code constitute part of the present invention.

[0165] Examples of storage media for providing program code include floppy disks, hard disks, magneto-optical disks, optical disks (such as CD-ROM, CD-R, CD-RW, DVD-ROM, DVD-RAM, DVD-RW, DVD+RW), magnetic tapes, non-volatile memory cards, and ROMs. Alternatively, the program code can be downloaded from a server computer via a communication network.

[0166] In addition, it should be clear that the functions of any of the above embodiments can be achieved not only by executing the program code read by the computer, but also by enabling the operating system operating on the computer to complete part or all of the actual operations based on the instructions of the program code.

[0167] In addition, it can be understood that the program code read from the storage medium is written into a memory provided in an expansion board inserted into the computer or into a memory provided in an expansion module connected to the computer, and then based on the instructions of the program code, a CPU installed on the expansion board or expansion module is enabled to perform part or all of the actual operations, thereby realizing the functions of any of the above embodiments.

[0168] It is understandable that the explanation, specific implementation methods, beneficial effects, examples, etc. of the relevant contents in the computer-readable medium provided in the embodiment of the present invention can be found in the corresponding parts of the method provided in the first aspect, and will not be repeated here.

[0169] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences from other embodiments. In particular, the device embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

[0170] Those skilled in the art will appreciate that in one or more of the above examples, the functions described in the present invention may be implemented using hardware, software, widgets, or any combination thereof. When implemented using software, these functions may be stored in a computer-readable medium or transmitted as one or more instructions or codes on a computer-readable medium.

[0171] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made on the basis of the technical solution of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for determining the swing angle of a ship unloader grab bucket, characterized in that: A camera device (110) is provided at each end of the trolley travel track of the ship unloader, and the field of view of each camera device (110) covers the movement range of the grab bucket during the operation of the ship unloader; the determination method includes: Obtaining the current position of the ship unloader on the trolley travel track; acquiring in real time the video captured by each camera device (110) during the operation of the ship unloader; Determining the grab bucket swing angle in each frame of the video captured by each camera device (110); Determining the current swing angle of the grab bucket based on two grab bucket swing angles of corresponding frame images in the video captured by two camera devices (110) and the current position of the ship unloader on the trolley travel track; wherein, determining the current swing angle of the grab bucket based on two grab bucket swing angles of corresponding frame images in the video captured by two camera devices (110) and the current position of the ship unloader on the trolley travel track comprises: Calculating a positional deviation between the ship unloader and each camera device (110) based on the current position of the ship unloader on the trolley travel track; Determining whether the two position deviations are equal; If the two position deviations are not equal, determining a first camera device and a second camera device (110) of the two camera devices (110) based on whether the current position is within the preset position range and the magnitude relationship between the two position deviations, wherein the weight corresponding to the first camera device is higher than the weight value corresponding to the second camera device; The current swing angle of the grab bucket is calculated based on the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices (110) and the weight values ​​corresponding to the two camera devices (110).

2. The determination method according to claim 1, characterized in that The determining of the first camera device and the second camera device of the two camera devices (110) based on whether the current position is within the preset position range and the magnitude relationship between the two position deviations includes at least one of the following: If the current position is within a preset position range, the camera device (110) with the smaller position deviation is used as the first camera device, and the camera device with the larger position deviation is used as the second camera device; If the current position is outside the preset position range, the camera device (110) with the larger position deviation is used as the first camera device, and the camera device (110) with the smaller position deviation is used as the second camera device; The weight value corresponding to the first camera device when the current position is outside the preset position range is greater than the weight value corresponding to the first camera device when the current position is within the preset range.

3. The determination method according to claim 1, characterized in that Before determining the current swing angle of the grab bucket, the method further includes: Performing validity detection on two grab bucket swing angles of corresponding frame images in the video captured by two camera devices (110); if the two grab bucket swing angles are valid, executing the step of determining the current swing angle of the grab bucket; Among them, the validity detection includes judging whether the two grab bucket swing angles are both smaller than the preset swing angle and whether the difference between the two grab bucket swing angles is less than the preset difference; if the two grab bucket swing angles are both smaller than the preset swing angle and the difference between the two grab bucket swing angles is less than the preset difference, then the two grab bucket swing angles are valid.

4. The determination method according to claim 3, characterized in that: Before performing validity detection on the two grab bucket swing angles of corresponding frame images in the videos captured by the two camera devices (110), the method further comprises: Calculating a positional deviation between the ship unloader and each camera device (110) based on the current position of the ship unloader on the trolley travel track; Obtaining a calibrated swing angle of each camera device (110) under respective corresponding position deviations; wherein the calibrated swing angle is the grab bucket swing angle in an image captured by each camera device (110) when a steel wire rope connecting the grab bucket is in a vertical state and the ship unloader and each camera device (110) are at different position deviations; Calculating the difference between the grab bucket swing angle in each frame image in the video captured by each camera device (110) and the calibrated swing angle, and using the difference as the grab bucket swing angle after decalibration for each frame image in the video captured by each camera device (110); Correspondingly, the validity detection of the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices (110) includes: the validity detection of the grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices (110) after decalibration.

5. The determination method according to claim 1, characterized in that: The determining of the grab bucket swing angle in each frame of image in the video captured by each camera device (110) comprises: Edge detection is used to detect the area where the wire rope connected to the grab is located in each frame image, and the area where the wire rope is located is segmented. Feature extraction is performed in the segmented area, and the angle between the extracted wire rope and the vertical direction is used as the grab swing angle in the frame image.

6. The determination method according to claim 5, characterized in that: The step of determining the grab bucket swing angle in each frame of the video captured by each camera device (110) further includes: Before detecting the area where the steel wire rope is located by edge detection, nonlinear distortion calibration is performed on each frame of image so that the steel wire rope connected to the grab bucket becomes a straight line in each frame of image; Convert each frame image into an image in HSV space.

7. A device (10) for determining the swing angle of a ship unloader grab bucket, characterized in that: A camera device (110) is provided at each end of the trolley travel track of the ship unloader, and the field of view of each camera device (110) covers the movement range of the grab bucket during the operation of the ship unloader; the determining device (10) includes: A first acquisition module (11) is used to: acquire the current position of the ship unloader on the trolley travel track; A second acquisition module (12) is used to acquire the video captured by each camera device (110) in real time during the operation of the ship unloader; A first calculation module (13) is used to determine a grab bucket swing angle in each frame of image in a video captured by each camera device (110); A second calculation module (14) is used to determine the current swing angle of the grab bucket based on the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices (110) and the current position of the ship unloader on the vehicle travel track; Wherein, the second calculation module (14) is further used for: Calculating a positional deviation between the ship unloader and each camera device (110) based on the current position of the ship unloader on the trolley travel track; Determining whether the two position deviations are equal; If the two position deviations are not equal, determining a first camera device and a second camera device (110) of the two camera devices (110) based on whether the current position is within the preset position range and the magnitude relationship between the two position deviations, wherein the weight corresponding to the first camera device is higher than the weight value corresponding to the second camera device; The current swing angle of the grab bucket is calculated based on the two grab bucket swing angles of the corresponding frame images in the video captured by the two camera devices (110) and the weight values ​​corresponding to the two camera devices (110).

8. A ship unloader grab bucket swing angle detection system (100), characterized in that: include: An edge computing device (120) and two camera devices (110) connected to the edge computing unit, wherein: The two camera devices (110) are arranged at both ends of the trolley travel track, and the field of view of each camera device (110) covers the movement range of the grab bucket of the ship unloader during operation; each camera device (110) is used to: collect video within the field of view during the operation of the ship unloader, and send the video to the edge computing device (120); the edge computing device (120) is the swing angle determination device (10) according to claim 7.

9. The detection system according to claim 8, characterized in that: Also includes: Two wireless clients (130) and a wireless access point (140); the two wireless clients (130) and the two camera devices (110) are connected in a one-to-one correspondence, and the wireless access point (140) and the edge computing device (120) are connected; and a communication connection between the two camera devices (110) and the edge computing device (120) is achieved through the wireless connection between the two wireless clients (130) and the wireless access point (140).

10. A control system (400) for a ship unloader, characterized in that: The invention comprises a swing angle detection system (100), an anti-shake system (200) and an automatic control system (300) of a ship unloader grab according to any one of claims 8 and 9, wherein the anti-shake system (200) is connected to the swing angle detection system (100) and the automatic control system (300), wherein: The automatic control system (300) is used to: control the trolley to move on the trolley track during the operation of the ship unloader, so as to drive the grab bucket to move; The swing angle detection system (100) is used to: detect the current swing angle of the grab bucket during movement in real time, and send the current swing angle to the anti-shake system (200); The anti-shake system (200) is used to: obtain motion information of the trolley, determine the additional speed of the trolley according to the motion information of the trolley and the current swing angle, and send the additional speed to the automatic control system (300); The automatic control system (300) is used to adjust the movement of the trolley according to the additional speed, so that the current swing angle of the grab bucket is controlled within a preset range.

11. The control system according to claim 10, characterized in that: The movement information of the trolley includes the movement direction of the trolley, the movement speed of the trolley and the current position of the trolley on the trolley track; The anti-shake system (200) is specifically used to: if the current position of the trolley on the trolley travel track is within a stable motion range, then generate the additional speed according to the motion direction of the trolley and the motion speed of the trolley, wherein the additional speed can make the current swing angle of the grab bucket within a first range after the automatic control system (300) adjusts the motion of the trolley, and the grab bucket can move smoothly when the current swing angle is within the first range; If the current position of the trolley on the trolley travel track is within the unloading range, the additional speed is generated according to the movement direction and movement speed of the trolley. The additional speed enables the automatic control system (300) to adjust the movement of the trolley so that the current swing angle of the grab bucket is within the second range. When the current swing angle is within the first range, the grab bucket can swing to shake off the cargo in the grab bucket.

12. An edge computing device (120), characterized in that The apparatus includes: at least one memory and at least one processor; The at least one memory is configured to store a machine-readable program; The at least one processor is configured to call the machine-readable program to execute the method according to any one of claims 1 to 6.

13. A computer-readable medium, characterized in that The computer-readable medium stores computer instructions, which, when executed by a processor, cause the processor to execute the method according to any one of claims 1 to 6.

Images