Centering control method, device, equipment, medium and crane

Abstract

The invention discloses a centering control method, device and equipment, a medium and a crane. The method comprises the following steps: acquiring a to-be-detected image; according to the to-be-detected image, detecting targets in the to-be-detected image are recognized, and the detecting targets comprise an open compartment and a container; the relative position deviation of the open carriage and the container is obtained; under the condition that the relative position deviation is greater than a preset relative position deviation, controlling a lifting appliance of the crane to act according to the relative position deviation, and skipping to obtain the to-be-detected image; and when the relative position deviation is smaller than or equal to the preset relative position deviation, generating a centering completion mark. According to the invention, automatic centering without observation and guidance of personnel can be realized, and the working efficiency is improved at the same time.

Description

Technical Field

[0001] This application relates to the field of cable joint technology, and in particular to a centering control method, device, equipment, medium and crane. Background Technology

[0002] A container reach stacker crane, or simply reach stacker, is a specialized loading and unloading machine used for loading, unloading, stacking, and horizontal transport of containers. When placing containers into open train cars, reach stackers often encounter difficulties in aligning the container precisely with the car due to visibility issues. Ground personnel must guide the operator to adjust the spreader's direction, and the operator must then carefully lower the container into the car. This alignment process frequently requires additional personnel to observe and guide, impacting both operational efficiency and the safety of the observers. Summary of the Invention

[0003] This application aims to provide a centering control method, device, equipment, medium, and crane that can achieve automatic centering without the need for personnel observation and guidance, while improving work efficiency.

[0004] The centering control method according to the first aspect of this application, applied to a crane, includes: Acquire the image to be detected; Based on the image to be detected, identify the detection targets in the image to be detected, the detection targets including open carriages and containers; Obtain the relative positional deviation between the open-top carriage and the container; If the relative position deviation is greater than the preset relative position deviation, the crane's lifting device is controlled to move according to the relative position deviation, and the process jumps to acquiring the image to be detected. If the relative position deviation is less than or equal to the preset relative position deviation, a centering completion flag is generated.

[0005] According to some embodiments of this application, obtaining the image to be detected includes: Acquire a first-view image and a second-view image; the first-view image is acquired by a first camera, which is used to capture the positional relationship between the front edge of the container and the front edge of the open cargo compartment; the second-view image is acquired by a second camera, which is used to capture the positional relationship between the rear edge of the container and the rear edge of the open cargo compartment. The first viewpoint image and the second viewpoint image are subjected to homography perspective transformation and synthesized to obtain the image to be detected.

[0006] According to some embodiments of this application, identifying the detection target in the image to be detected includes: The image to be detected is preprocessed by noise reduction and grayscale conversion; The edge region of the target being detected is determined using the HSV color system; The single-pixel edges of the detected target are extracted using an edge detection algorithm; The coordinates of the edge pixel group of the detected target are obtained by analyzing the Rotts operator. The target to be detected is identified in the image to be detected based on the coordinates of the edge pixel group.

[0007] According to some embodiments of this application, obtaining the relative positional deviation between the open wagon and the container includes: Based on the coordinates of the edge pixel group of the detected target, the edge coordinate functions corresponding to the open carriage and the container are obtained; Based on the edge coordinate functions corresponding to the open-top car body and the container, determine the relative positional deviation pixel value between the edge of the open-top car body and the edge of the container at a preset comparison position; Obtain the conversion formula between the image to be detected and its actual physical size; The relative position deviation between the open-top wagon and the container is determined based on the conversion formula and the relative position deviation pixel value.

[0008] According to some embodiments of this application, the relative position deviation includes a deviation angle, a front edge distance, and a rear edge distance. The deviation angle is the angle between the front edge of the container and the front edge of the open cargo compartment. The front edge distance is the distance between the front edge of the container and the front edge of the open cargo compartment. The rear edge distance is the distance between the rear edge of the container and the rear edge of the open cargo compartment.

[0009] According to some embodiments of this application, when the relative position deviation is greater than a preset relative position deviation, controlling the crane's lifting device movement based on the relative position deviation and then jumping to acquiring the image to be detected includes: If the deviation angle exceeds the preset deviation angle range, control the lifting device to rotate and jump to the acquisition of the image to be detected; If the deviation angle does not exceed the preset deviation angle range, the edge distance difference is obtained, which is obtained by subtracting the back edge distance from the front edge distance. If the edge distance difference exceeds the preset edge distance difference range, control the extension and retraction of the lifting device, and switch to acquiring the image to be detected.

[0010] The centering control device according to a second aspect embodiment of this application includes: The image acquisition module is used to acquire the image to be detected; The identification module is used to identify detection targets in the image to be detected, the detection targets including the open carriage and the container; The deviation acquisition module is used to acquire the relative positional deviation between the open-top carriage and the container; The first centering module is used to control the lifting device movement of the crane according to the relative position deviation when the relative position deviation is greater than the preset relative position deviation, and to jump to the acquisition of the image to be detected; The second centering module is used to generate a centering completion flag when the relative position deviation is less than or equal to the preset relative position deviation.

[0011] A crane according to a third aspect embodiment of this application includes a crane body and a controller, the controller being configured to perform the centering control method as described in the first aspect embodiment above.

[0012] An electronic device according to a fourth aspect of this application includes a processor and a memory, the memory storing a program or instructions executable on the processor, the program or instructions, when executed by the processor, implementing the steps of the centering control method as described in any of the first aspect embodiments above.

[0013] A computer-readable storage medium according to a fifth aspect embodiment of the present application stores computer-executable instructions for performing the centering control method as described in the first aspect embodiment above.

[0014] In this embodiment, by acquiring images and then recognizing them, the relative positional deviation between the open-top truck bed and the container is obtained. This enables automatic detection of whether the open-top truck bed and the container are aligned, and allows for automatic adjustment of the spreader and boom when the relative positional deviation exceeds a preset deviation, thereby completing the alignment and placement of the container with the open-top truck bed. This solution eliminates the need for personnel observation and guidance, removing potential risks for observers during operations and improving operational efficiency.

[0015] Other features and advantages of this application will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing this application. Attached Figure Description

[0016] The above and / or additional aspects and advantages of this application will become apparent and readily understood from the description of the embodiments taken in conjunction with the following drawings, in which: Figure 1This is a flowchart illustrating an embodiment of the centering control method of this application; Figure 2 This is a schematic diagram of the deviation angle, front margin, and back margin of this application; Figure 3 This is a schematic diagram of the structure of an embodiment of the centering control device of this application; Figure 4 This is a schematic diagram of the hardware structure of an embodiment of the electronic device of this application. Detailed Implementation

[0017] The embodiments of this application are described in detail below. Examples of these embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain this application, and should not be construed as limiting this application.

[0018] In the description of this application, the use of terms such as "first," "second," etc., is for the purpose of distinguishing technical features only and should not be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated or the order of the technical features indicated.

[0019] In the description of this application, it should be understood that the orientation descriptions, such as up, down, etc., are based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this application and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this application.

[0020] In the description of this application, it should be noted that, unless otherwise explicitly defined, terms such as "setup," "installation," and "connection" should be interpreted broadly, and those skilled in the art can reasonably determine the specific meaning of the above terms in this application in conjunction with the specific content of the technical solution.

[0021] The technical solution of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described below are some embodiments of this application, not all embodiments.

[0022] Figure 1 This is a flowchart illustrating an embodiment of the centering control method of this application; Figure 2 This is a schematic diagram of the deviation angle, front margin, and back margin of this application; Figure 3 This is a schematic diagram of the structure of an embodiment of the centering control device of this application; Figure 4 This is a schematic diagram of the hardware structure of an embodiment of the electronic device of this application.

[0023] See below. Figure 1The embodiments of this application will be further described below. This application proposes a centering control method applied to a crane. The centering control method includes the following steps: Step 101: Obtain the image to be detected; Step 102: Based on the image to be detected, identify the detection targets in the image to be detected. The detection targets include open-top carriages and containers. Step 103: Obtain the relative positional deviation between the open wagon and the container; Step 104: If the relative position deviation is greater than the preset relative position deviation, control the crane's lifting device movement according to the relative position deviation, and jump to acquire the image to be detected; Step 105: If the relative position deviation is less than or equal to the preset relative position deviation, generate an alignment completion mark.

[0024] In this embodiment, by acquiring images and then recognizing them, the relative positional deviation between the open-top truck bed and the container is obtained. This enables automatic detection of whether the open-top truck bed and the container are aligned, and allows for automatic adjustment of the spreader and boom when the relative positional deviation exceeds a preset deviation, thereby completing the alignment and placement of the container with the open-top truck bed. This solution eliminates the need for personnel observation and guidance, removing potential risks for observers during operations and improving operational efficiency.

[0025] The image to be detected is a top-down view showing the open carriages of a train and the containers to be loaded into them. The crane is used to lift the containers and, after aligning them with the open carriages, loads them into the carriages. The crane can be a container crane, specifically a container front-lifting crane.

[0026] In some implementations, acquiring the image to be detected includes: Acquire first-view and second-view images; the first-view images are acquired by a first camera, which is used to capture the positional relationship between the front edge of the container and the front edge of the open cargo compartment; the second-view images are acquired by a second camera, which is used to capture the positional relationship between the rear edge of the container and the rear edge of the open cargo compartment. Homography perspective transformation is performed on the first-view and second-view images to synthesize the image to be detected.

[0027] In this embodiment, images are acquired using both a first camera and a second camera, with the two cameras positioned at different locations. This allows for the capture of the positional relationship between the container and the front and rear edges of the open cargo compartment from different perspectives. This dual-view setup enables comprehensive acquisition of the alignment information between the container and the open cargo compartment along its length, avoiding inaccurate positional judgments caused by blind spots or perspective errors that may exist in single-view photography. After acquiring the first and second view images, a crucial step is to perform homography perspective transformation on both. Homography transformation projects images from different perspectives onto a unified planar coordinate system, eliminating image distortion caused by differences in camera installation position and shooting angle, ultimately yielding the desired image to be detected.

[0028] In some cases, the first and second cameras are symmetrically positioned with respect to the center of the spreader, so that when taking pictures, they are symmetrically positioned with respect to the center of the container viewed from above.

[0029] For example, the first camera can be installed at one end of the spreader near the front edge of the container, with its lens facing diagonally downwards, to clearly capture the relative distribution of the front edge of the container and the front edge of the open cargo compartment on the same plane; the second camera is symmetrically installed at the other end of the spreader near the rear edge of the container, also shooting at a diagonally downwards angle, to capture the relative position of the rear edge of the container and the rear edge of the open cargo compartment.

[0030] The above-described method involves performing homography perspective transformation on the first-view and second-view images to synthesize the image to be detected. Specifically, this is achieved by pre-calibrating the intrinsic and extrinsic parameters of the two cameras to establish a transformation relationship between their coordinate systems. Then, based on this transformation relationship, the two images are transformed and stitched together to ultimately synthesize a single image that accurately and completely reflects the overall relative position of the container and the open cargo compartment. This synthesis method allows subsequent target recognition and positional deviation calculations to be performed based on complete image data within the same coordinate system, effectively improving the accuracy of centering control.

[0031] In some implementations, identifying the target object in the image to be detected, based on the image to be detected, includes: Preprocessing of the image to be detected, including noise reduction and grayscale conversion; The edge region of the target being detected is determined using the HSV color system; Single-pixel edges of the detected target are extracted using an edge detection algorithm; The coordinates of the edge pixel group of the detected target are obtained by analyzing the Rotts operator. Based on the coordinates of edge pixel groups, the target in the image to be detected is identified.

[0032] In this embodiment, the image to be detected is processed to highlight the features of the target and then identified. First, image preprocessing is performed, including noise reduction and grayscale conversion. Then, image feature analysis and feature extraction are performed. First, color feature analysis is performed on the image, specifically using the HSV color system to determine the boundary regions present in the image. Second, a multi-level edge detection algorithm is used to detect single-pixel edges in the image. Finally, depth analysis is performed on the image, using the Rotters operator to analyze the coordinates of boundary pixels in real time. After determining the edge pixels, open wagons and containers in the image to be detected can be identified.

[0033] The above-mentioned preprocessing of the image to be detected, including denoising and grayscale conversion, can effectively improve the accuracy and efficiency of subsequent image processing. The signal-to-noise ratio of the preprocessed image is significantly improved, laying a good foundation for subsequent edge region determination.

[0034] The method described above, which uses the HSV color system to determine the edge region of the target, employs the HSV color model, which better aligns with human color perception. The H (hue), S (saturation), and V (lightness) components are independent, facilitating color threshold segmentation. Specifically, considering the typical color characteristics of open wagons and containers—such as the common blue, red, and gray of containers and the common yellow and black of open wagons—the range of H, S, and V components in the HSV color space can be determined beforehand through sample image analysis. This allows for subsequent processing, ultimately preliminarily determining the edge region of the target and reducing the computational load and interference in subsequent edge detection algorithms.

[0035] The above-described extraction of single-pixel edges of the target object using an edge detection algorithm is a refinement process based on the edge regions obtained from color segmentation. The Canny edge detection algorithm can be used here, as it offers good noise resistance and edge localization accuracy.

[0036] The above analysis uses the Roters operator to obtain the coordinates of the edge pixel points of the detected target. The Roters operator is a gradient calculation method based on cross-difference. Although the Roters operator has high accuracy in edge localization, it is more sensitive to noise. Therefore, in this embodiment, after the single-pixel edge is extracted by the Canny algorithm, the Roters operator is used to further refine the edge image and extract the coordinates of the edge pixels. These coordinate point groups constitute the edge of the detected target, that is, the discrete pixel set of the edge of the open car and container.

[0037] In some implementations, obtaining the relative positional deviation between the open wagon and the container includes: Based on the coordinates of the edge pixels of the detected target, the edge coordinate functions corresponding to the open carriages and containers are obtained; Based on the edge coordinate functions corresponding to the open car body and the container, determine the relative positional deviation pixel value between the edge of the open car body and the edge of the container at the preset comparison position; Obtain the conversion formula between the image to be detected and its actual physical size; Based on the conversion formula and the pixel value of the relative position deviation, the relative position deviation of the open-top car and the container is determined.

[0038] In this embodiment, edge feature coordinate function fitting is performed. The corresponding edge coordinate function can be fitted by the coordinates of the edge pixel group of the detected target. Then, the relative position deviation pixel value is further determined. Finally, the relative position deviation of the actual open wagon and container is obtained by converting the pixel position deviation in the image with the physical size in reality.

[0039] The above method obtains the edge coordinate functions corresponding to open wagons and containers based on the coordinates of the edge pixel group of the detected target. It can be understood that since the coordinates of the edge pixel group contain the coordinates of multiple pixels, multiple coordinate functions can be obtained after fitting. Further edge feature coordinate function feature filtering can be performed to further determine the edge coordinate functions that conform to the edge features of containers and open wagons.

[0040] For example, when identifying the edge region of a rectangular open wagon or container in an image, the function obtained by fitting the coordinates of its edge pixel group is actually the four sides of the rectangle, namely the top edge, bottom edge, left edge, and right edge of the open wagon or container. For a single edge, its corresponding edge coordinate function may be a straight line equation, such as y = kx + b.

[0041] The above method, which determines the relative positional deviation pixel value between the edge of the open-top wagon and the edge of the container at a preset comparison position based on the edge coordinate functions corresponding to the open-top wagon and the container, can be achieved by taking a preset value for the independent variable based on the already determined edge coordinate functions. That is, at the preset comparison position, the function value of the edge coordinate function corresponding to the open-top wagon is compared with the function value of the edge coordinate function corresponding to the container.

[0042] In some implementations, the conversion relationship between the image to be detected and the actual physical size can be a homography matrix, which can be solved.

[0043] Specifically, the correspondence between the camera's field of view and its physical dimensions can be expressed as the following homogeneous coordinate expression: · (1) Where [u, v, 1] represents pixel coordinates, and is a non-zero scaling factor representing the scaling coefficient between the camera's pixel coordinates and the actual world coordinates; [X, Y, 1] represents the actual world horizontal coordinates; H ] is a 3×3 homography matrix representing the camera calibration parameters, which can be expressed as: (2) Homography matrix of camera calibration parameters [ H One solution method includes the following steps.

[0044] First, control point pairs need to be collected. N sets of corresponding point pairs (X) can be collected. i Y i ,1)<—>(u i v i ,1), where,(X i Y i ,1) is the coordinate point in the actual physical world, (u i v i 1) These are the pixel coordinates in the corresponding virtual world image. N is greater than or equal to 4, meaning at least 4 sets are required. More point pairs are typically used, such as 9 to 25 pairs, and least squares fitting is employed to improve accuracy. At least three of the selected point pairs should contain special calibration markers. These markers are located where the fields of view of the first and second cameras overlap. This ensures that at least three of the selected point pairs are situated where the fields of view of the two cameras overlap, thus guaranteeing that the selected points are more representative. Secondly, based on equations (1) and (2) above, eliminating λ yields two linear equations: u = (h 11 * X + h 12 * Y + h 13 ) / (h 31 * X + h 32 * Y + h 33 (3) v = (h 21 * X + h 22 * Y + h 23 ) / (h 31 * X + h 32 * Y + h 33 (4) We further obtain the following expression: u * (h 31 * X + h 32 * Y + h 33 ) = h 11 * X + h12 * Y + h 13 (5) v * (h 31 * X + h 32 * Y + h 33 ) = h 21 * X + h 22 * Y + h 23 (6) It is understandable that each pair of points yields two linear equations, so stacking the equations for all N pairs of points forms a homogeneous system of linear equations: A * h = 0; (7) Where A is a 2N×9 matrix, and h is a 9-dimensional vector containing the elements of the [H] matrix, specifically, h = [h11, h12, h13, h21, h22, h23, h31, h32, h33]. T The first equation corresponding to the 2i-1th row of matrix A is [Xi, Yi, 1, 0, 0, 0, -Xi*ui, -Yi*ui, -ui]; the second equation corresponding to the 2ith row of matrix A is [0, 0, 0, Xi, Yi, 1, -Xi*vi, -Yi*vi, -vi].

[0045] Finally, we solve for h. The least-squares solution of equation (7) under the constraint of ||h|| = 1 can be obtained using Singular Value Decomposition (SVD). Therefore, we perform SVD on matrix A: A = U * S * V T (8) The solution h is the last column of V, corresponding to the right singular vector of the minimum singular value. Finally, h can be reshaped into a 3×3 homography matrix. H ]. After obtaining the homography matrix [ H After that, for any edge point pixel coordinates (u, v) detected on the image, as long as the point is located on the defined physical world plane, its corresponding physical world coordinates (X, Y) can be calculated.

[0046] In some implementations, the relative positional deviation includes a deviation angle, a front margin, and a rear margin. The deviation angle is the angle between the front edge of the container and the front edge of the open cargo compartment. The front margin is the distance between the front edge of the container and the front edge of the open cargo compartment. The rear margin is the distance between the rear edge of the container and the rear edge of the open cargo compartment.

[0047] In this embodiment, to better represent the alignment of the container and the open cargo compartment, the relative positional deviation includes the deviation angle, the front edge distance, and the rear edge distance. The deviation angle reflects the degree of rotational offset of the container relative to the open cargo compartment, such as... Figure 2 As shown by β, when the front edge is not parallel to the front edge of the open cargo compartment, the angle formed between them is the deviation angle. The larger this angle value, the more severe the lateral twisting of the container. The front and rear distances reflect the distance deviations between the front and rear ends of the container and the corresponding edges of the open cargo compartment, respectively. Figure 2 As shown in x1 and x2 in the image. It can be understood that by converting the virtual pixel coordinates in the image above to the actual physical world coordinates, the distances x1 (front) and x2 (back) between the edge of the container and the edge of the open truck can be obtained. Then, by combining trigonometric functions, the angle β between the edge of the container and the edge of the open truck can be obtained.

[0048] In some implementations, when the relative position deviation is greater than a preset relative position deviation, the crane's lifting device is controlled to move according to the relative position deviation, and the process jumps to acquiring the image to be detected, including: If the deviation angle exceeds the preset deviation angle range, control the spreader to rotate and jump to acquire the image to be detected; If the deviation angle does not exceed the preset deviation angle range, the edge distance difference is obtained by subtracting the back edge distance from the front edge distance. If the edge distance difference exceeds the preset edge distance difference range, control the extension and retraction of the spreader and jump to acquire the image to be detected.

[0049] In this embodiment, precise adjustment of the spreader's movement is achieved by judging and controlling the specific parameters of the relative position deviation in steps. The centering adjustment measurement of the spreader involves first adjusting the included angle, and then adjusting the side distance. That is, first adjusting the deviation angle to make it within the preset deviation angle range, and then adjusting the side distance difference to make it within the preset side distance difference range.

[0050] First, the system prioritizes addressing angular deviation. When the deviation angle exceeds the preset range, the system sends a control command to the spreader's rotation mechanism, driving the spreader to rotate by the corresponding angle to reduce the angle between the container and the open cargo compartment. After the rotation adjustment is complete, the system immediately jumps back to the step of acquiring the image to be detected, re-captures and analyzes the current relative position, forming a closed-loop control to ensure that the angular deviation is corrected to within the allowable range.

[0051] If the deviation angle is already within the preset deviation angle range, the deviation in the edge distance direction is further evaluated. At this point, the edge distance difference is calculated, which is the difference between the front edge distance and the rear edge distance. This edge distance difference reflects the horizontal offset trend of the container relative to the open truck bed. When the edge distance difference exceeds the preset edge distance difference range, it indicates that the container is misaligned. The system will control the extension and retraction mechanism of the spreader to change the front and rear position of the container relative to the open truck bed by adjusting the extension or retraction length of the spreader, thereby reducing the difference between the front and rear edge distances. Similarly, after performing the extension and retraction adjustment, the system jumps back to the step of acquiring the image to be detected, continuously monitoring the adjustment effect until the edge distance difference also meets the preset requirements, ultimately achieving precise alignment of the container and the open truck bed. This hierarchical, priority-based control logic can systematically resolve different types of positional deviations, improving the stability and efficiency of alignment control.

[0052] The above-mentioned preset deviation angle range can be The aforementioned preset edge distance difference range can be ,in, That is, the front margin minus the back margin.

[0053] In some implementations, the centering control method of this application can be applied to scenarios including but not limited to containers and open wagons, containers and flatbed trucks, and containers and fixed workstations. As long as the top view image has edge features, it is an applicable scenario of this application.

[0054] The centering control method provided in this application can be executed by a centering control device 200. This application uses the centering control device 200 executing the centering control method as an example to illustrate the centering control device 200 provided in this application.

[0055] Please see Figure 3 This is a schematic diagram of the structure of a centering control device 200 provided in an embodiment of this application. Figure 3 As shown, the centering control device 200 includes: Image acquisition module 201 is used to acquire the image to be detected; The recognition module 202 is used to identify the detection targets in the image to be detected, including open carriages and containers; Deviation acquisition module 203 is used to acquire the relative positional deviation of open-top wagons and containers; The first centering module 204 is used to control the crane's lifting device movement according to the relative position deviation when the relative position deviation is greater than the preset relative position deviation, and jump to acquire the image to be detected. The second centering module 205 is used to generate a centering completion flag when the relative position deviation is less than or equal to the preset relative position deviation.

[0056] In some implementations, the image acquisition module 201 can be used for: Acquire first-view and second-view images; the first-view images are acquired by a first camera, which is used to capture the positional relationship between the front edge of the container and the front edge of the open cargo compartment; the second-view images are acquired by a second camera, which is used to capture the positional relationship between the rear edge of the container and the rear edge of the open cargo compartment. Homography perspective transformation is performed on the first-view and second-view images to synthesize the image to be detected.

[0057] In some implementations, the identification module 202 can be used to: Preprocessing of the image to be detected, including noise reduction and grayscale conversion; The edge region of the target being detected is determined using the HSV color system; Single-pixel edges of the detected target are extracted using an edge detection algorithm; The coordinates of the edge pixel group of the detected target are obtained by analyzing the Rotts operator. Based on the coordinates of edge pixel groups, the target in the image to be detected is identified.

[0058] In some implementations, the deviation acquisition module 203 can be used for: Based on the coordinates of the edge pixels of the detected target, the edge coordinate functions corresponding to the open carriages and containers are obtained; Based on the edge coordinate functions corresponding to the open car body and the container, determine the relative positional deviation pixel value between the edge of the open car body and the edge of the container at the preset comparison position; Obtain the conversion formula between the image to be detected and its actual physical size; Based on the conversion formula and the pixel value of the relative position deviation, the relative position deviation of the open-top car and the container is determined.

[0059] In some implementations, the relative positional deviation includes a deviation angle, a front margin, and a rear margin. The deviation angle is the angle between the front edge of the container and the front edge of the open cargo compartment. The front margin is the distance between the front edge of the container and the front edge of the open cargo compartment. The rear margin is the distance between the rear edge of the container and the rear edge of the open cargo compartment.

[0060] In some implementations, the first centering module 204 may be used for: If the deviation angle exceeds the preset deviation angle range, control the spreader to rotate and jump to acquire the image to be detected; If the deviation angle does not exceed the preset deviation angle range, the edge distance difference is obtained by subtracting the back edge distance from the front edge distance. If the edge distance difference exceeds the preset edge distance difference range, control the extension and retraction of the spreader and jump to acquire the image to be detected.

[0061] Since the centering control device 200 adopts all the technical solutions of the centering control method of the above embodiments, it has at least all the beneficial effects brought about by the technical solutions of the above embodiments, and will not be described in detail here.

[0062] This application provides a crane, including a crane body and a controller, which is used to execute the centering control method described above. The controller can be a vehicle control controller built into the crane itself, or it can be an external independent controller.

[0063] In some implementations, the crane includes a main controller, a boom operating handle, a first camera, a second camera, an industrial computer, a touch screen, a first hydraulic valve, a second hydraulic valve, a third hydraulic valve, a fourth hydraulic valve, a fifth hydraulic valve, a sixth hydraulic valve, and a centering button.

[0064] In this embodiment, the main controller is the core of the control system. It is used to collect signals from various sensors, communicate with the industrial control computer, implement control strategies, and output control commands to the hydraulic valves, thereby controlling the movement of the spreader and boom. The boom operating handle can be pushed forward and backward to issue the boom pitch command, and pushed left and right to issue the spreader frame extension command. The first camera is used to capture the relative positional relationship between the front bottom edge of the container and the front edge of the open cargo compartment. The second camera is used to capture the relative positional relationship between the rear bottom edge of the container and the rear edge of the open cargo compartment. The industrial control computer is used to process the images captured by the first and second cameras and calculate the angle β and distance between the bottom edge of the container and the edge of the open cargo compartment. The touchscreen is used to display the angle β and distance between the bottom edge of the container and the edge of the open cargo compartment. The system prompts the driver to perform spreader rotation and boom extension / retraction operations; the first and second hydraulic valves control the spreader's clockwise and counterclockwise rotation, the third and fourth hydraulic valves control the retraction and extension of the spreader frame, and the fifth and sixth hydraulic valves control the boom's tilting up and down; the centering button is used to initiate container centering control; the main controller, operating handle, and industrial control computer use CAN communication; the industrial control computer, first camera, second camera, and touch screen use Ethernet communication.

[0065] Figure 4 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application.

[0066] This electronic device may include a processor 301 and a memory 302 storing computer program instructions.

[0067] Specifically, the processor 301 may include a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0068] Memory 302 may include mass storage for data or instructions. For example, and not limitingly, memory 302 may include a hard disk drive (HDD), floppy disk drive, flash memory, optical disk, magneto-optical disk, magnetic tape, or Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 302 may include removable or non-removable (or fixed) media. Where appropriate, memory 302 may be internal or external to the integrated gateway disaster recovery device. In a particular embodiment, memory 302 is non-volatile solid-state memory.

[0069] In some embodiments, memory 302 may include read-only memory (ROM), random access memory (RAM), disk storage media device, optical storage media device, flash memory device, electrical, optical, or other physical / tangible memory storage device. Thus, generally, memory includes one or more tangible (non-transitory) computer-readable storage media (e.g., memory devices) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it is operable to perform the operations described with reference to the method according to one aspect of this disclosure.

[0070] The processor 301 implements any of the centering control methods described in the above embodiments by reading and executing computer program instructions stored in the memory 302.

[0071] In one example, the electronic device may also include a communication interface 303 and a bus 310. For example, Figure 4 As shown, the processor 301, memory 302, and communication interface 303 are connected through bus 310 and complete communication with each other.

[0072] The communication interface 303 is mainly used to realize communication between various modules, devices, units and / or equipment in the embodiments of this application.

[0073] Bus 310 includes hardware, software, or both, that couples components of an online data traffic metering device together. For example, and not limitingly, the bus may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), HyperTransport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an Infinite Bandwidth Interconnect, a Low Pin Count (LPC) bus, a memory bus, a Microchannel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local (VLB) bus, or other suitable buses, or combinations of two or more of these. Where appropriate, bus 310 may include one or more buses. Although specific buses are described and illustrated in embodiments of this application, any suitable bus or interconnect is contemplated herein.

[0074] The electronic device can execute the centering control method in the embodiments of this application, thereby achieving the combination Figure 2 and Figure 3 The described centering control method and apparatus.

[0075] Furthermore, in conjunction with the centering control methods in the above embodiments, this application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when these computer program instructions are executed by a processor, they implement any of the centering control methods in the above embodiments.

[0076] It should be clarified that this application is not limited to the specific configurations and processes described above and shown in the figures. For the sake of brevity, detailed descriptions of known methods are omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of this application is not limited to the specific steps described and shown. Those skilled in the art can make various changes, modifications, and additions, or change the order of steps, after understanding the spirit of this application.

[0077] The functional blocks shown in the above-described block diagram can be implemented as hardware, software, firmware, or a combination thereof. When implemented in hardware, they can be electronic circuits, application-specific integrated circuits (ASICs), appropriate firmware, plug-ins, function cards, etc. When implemented in software, the elements of this application are programs or code segments used to perform the required tasks. Programs or code segments can be stored on a machine-readable medium or transmitted over a transmission medium or communication link via data signals carried on a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, fiber optic media, radio frequency (RF) links, etc. Code segments can be downloaded via computer networks such as the Internet, intranets, etc.

[0078] It should also be noted that the exemplary embodiments mentioned in this application describe methods or systems based on a series of steps or apparatus. However, this application is not limited to the order of the above steps; that is, the steps can be performed in the order mentioned in the embodiments, or in a different order, or several steps can be performed simultaneously.

[0079] The aspects of this disclosure have been described above with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this disclosure. It should be understood that each block in the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that these instructions, executable via the processor of the computer or other programmable data processing apparatus, enable the implementation of the functions / actions specified in one or more blocks of the flowchart illustrations and / or block diagrams. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field-programmable logic circuit. It is also understood that each block in the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can also be implemented by special-purpose hardware performing the specified functions or actions, or can be implemented by a combination of special-purpose hardware and computer instructions.

[0080] The above description is merely a specific implementation of this application. Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, modules, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here. It should be understood that the protection scope of this application is not limited thereto. Any person skilled in the art can easily conceive of various equivalent modifications or substitutions within the technical scope disclosed in this application, and these modifications or substitutions should all be covered within the protection scope of this application.

Claims

1. A method of centering control, characterized by, The application is applied to a crane, comprising: acquiring a to-be-detected image; identifying a detection target in the to-be-detected image according to the to-be-detected image, the detection target comprising an open wagon and a container; acquiring a relative position deviation of the open wagon and the container; in a case where the relative position deviation is greater than a preset relative position deviation, controlling a spreader action of the crane according to the relative position deviation, and jumping to the acquiring a to-be-detected image; in a case where the relative position deviation is less than or equal to the preset relative position deviation, generating a centering completion flag.

2. The centering control method according to claim 1, characterized by, The acquiring a to-be-detected image comprises: acquiring a first-view collected image and a second-view collected image; the first-view collected image is collected by a first camera, the first camera being used to collect a positional relationship of a front edge of the container and a front edge of the open wagon, and the second-view collected image is collected by a second camera, the second camera being used to collect a positional relationship of a rear edge of the container and a rear edge of the open wagon; performing a perspective transformation of homography on the first-view collected image and the second-view collected image to synthesize the to-be-detected image.

3. The centering control method according to claim 2, characterized by, The identifying a detection target in the to-be-detected image according to the to-be-detected image comprises: performing a preprocessing of denoising and grayscale on the to-be-detected image; determining an edge region of the detection target through an HSV color system; extracting a single-pixel edge of the detection target through an edge detection algorithm; obtaining a group of edge pixel point coordinates of the detection target through a Roerts operator analysis; identifying the detection target in the to-be-detected image according to the group of edge pixel point coordinates.

4. The centering control method according to claim 3, characterized by, The acquiring a relative position deviation of the open wagon and the container comprises: obtaining edge coordinate functions corresponding to the open wagon and the container according to the group of edge pixel point coordinates of the detection target; determining a relative position deviation pixel value between edges of the open wagon and the container at a preset comparison position according to the edge coordinate functions corresponding to the open wagon and the container; acquiring a conversion relationship between the to-be-detected image and an actual physical size; determining the relative position deviation of the open wagon and the container according to the conversion relationship and the relative position deviation pixel value.

5. The centering control method according to claim 1 or 4, characterized by, The relative position deviation comprises a deviation angle, a front edge distance and a rear edge distance, the deviation angle being an included angle between the front edge of the container and the front edge of the open wagon, the front edge distance being a distance between the front edge of the container and the front edge of the open wagon, and the rear edge distance being a distance between the rear edge of the container and the rear edge of the open wagon.

6. The centering control method according to claim 5, characterized by In a case where the deviation angle exceeds a preset deviation angle range, the spreader is controlled to rotate, and the acquiring a to-be-detected image is jumped to. ​ In a case where the deviation angle does not exceed the preset deviation angle range, an edge distance difference is obtained, the edge distance difference being obtained by subtracting the rear edge distance from the front edge distance; In a case where the edge distance difference exceeds a preset edge distance difference range, the spreader is controlled to be extended or retracted, and the obtaining of the to-be-detected image is performed.

7. A centering control device characterized by comprising: The method is applied to the centering control method according to any one of claims 1 to 6, and comprises: an image obtaining module, configured to obtain a to-be-detected image; an identification module, configured to identify a detection target in the to-be-detected image according to the to-be-detected image, the detection target comprising the open wagon and the container; a deviation obtaining module, configured to obtain a relative position deviation of the open wagon and the container; a first centering module, configured to, in a case where the relative position deviation is greater than a preset relative position deviation, control a spreader of the crane to act according to the relative position deviation, and perform the obtaining of the to-be-detected image; a second centering module, configured to, in a case where the relative position deviation is less than or equal to the preset relative position deviation, generate a centering completion flag.

8. A crane, characterized in that The crane comprises a crane body and a controller, and the controller is configured to execute the centering control method according to any one of claims 1 to 6.

9. An electronic device, comprising: The device comprises a processor and a memory, and the memory stores programs or instructions executable on the processor, and the programs or instructions are executed by the processor to implement the steps of the centering control method according to any one of claims 1 to 6.

10. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer executable instructions for causing a computer to execute the centering control method according to any one of claims 1 to 6.

Images