Anode scrap carbon block sorting method and device, computer equipment, readable storage medium and program product

Abstract

The invention relates to an anode scrap carbon block sorting method and device, computer equipment, a computer readable storage medium and a computer program product. The method comprises the steps that an anode scrap block image corresponding to an anode scrap carbon block is obtained, and the anode scrap carbon block is located on a conveying device; according to the anode scrap block image, performing target detection on the anode scrap carbon block to obtain a carbon block pixel position coordinate of the anode scrap carbon block in a pixel coordinate system; according to preset hand-eye calibration information, the carbon block pixel position coordinates are converted into first grabbing position coordinates under a robot coordinate system; calibration speed information of the transmission device is determined, and second grabbing position coordinates are generated according to the first grabbing position coordinates and the calibration speed information; and according to the second grabbing position coordinates, a preset grabbing device is controlled to grab and sort the anode scrap carbon blocks. By adopting the method, the sorting accuracy of the anode scrap carbon blocks can be improved.

Description

Technical Field

[0001] This application relates to the field of sorting technology, and in particular to a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for sorting residual carbon blocks. Background Technology

[0002] With the development of sorting technology, vision-based sorting technology has emerged, which enables the automatic picking and sorting of items.

[0003] However, traditional 2D vision algorithms often struggle to accurately capture the position of dynamic objects, which leads to a decrease in the accuracy of item sorting. Summary of the Invention

[0004] Therefore, it is necessary to provide a sorting method, apparatus, computer equipment, computer-readable storage medium, and computer program product for residual carbon blocks that can improve the sorting accuracy of residual carbon blocks, in order to address the above-mentioned technical problems.

[0005] In a first aspect, this application provides a method for sorting residual carbon blocks, including:

[0006] Acquire an image of the residual carbon block corresponding to the residual carbon block, wherein the residual carbon block is located on the transmission device;

[0007] Based on the image of the residual electrode block, target detection is performed on the residual electrode carbon block to obtain the pixel position coordinates of the carbon block in the pixel coordinate system;

[0008] Based on the preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into the first grasping position coordinates in the robot coordinate system;

[0009] Determine the calibration speed information of the transmission device, and generate the second gripping position coordinates based on the first gripping position coordinates and the calibration speed information;

[0010] Based on the second gripping position coordinates, the preset gripping device is controlled to grip and sort the residual carbon blocks.

[0011] In one embodiment, determining the calibration speed information of the transmission device includes:

[0012] Acquire a first calibration code image captured at a first time point and a second calibration code image captured at a second time point, wherein the calibration code is located on the transmission device and the transmission device is in motion;

[0013] Based on the first calibration code image, identify the coordinates of the first pixel position corresponding to the calibration code;

[0014] Based on the second calibration code image, identify the second pixel position coordinates corresponding to the calibration code;

[0015] Based on the first pixel position coordinates and the second pixel position coordinates, the transmission device is dynamically calibrated to obtain calibration speed information.

[0016] In one embodiment, the step of dynamically calibrating the transmission device based on the first pixel position coordinates and the second pixel position coordinates to obtain calibration speed information includes:

[0017] Determine the time difference between the first time point and the second time point;

[0018] Based on the preset hand-eye calibration information, the position coordinates of the first pixel are transformed into the robot coordinate system to obtain the position coordinates of the first code;

[0019] Based on the preset hand-eye calibration information, the second pixel position coordinates are transformed into the robot coordinate system to obtain the second code position coordinates;

[0020] The calibration speed information of the transmission device is generated based on the time difference, the position coordinates of the first code, and the position coordinates of the second code.

[0021] In one embodiment, generating the second grasping position coordinates based on the first grasping position coordinates and the calibration speed information includes:

[0022] The grasping delay is obtained, wherein the grasping delay represents the delay from capturing the image of the residual electrode block to the grasping and sorting by the preset grasping device;

[0023] The transmission displacement of the transmission device is determined based on the calibration speed information and the grasping delay;

[0024] Based on the transmission displacement and the first grasping position coordinates, the second grasping position coordinates are located.

[0025] In one embodiment, controlling a preset gripping device to grip and sort the residual carbon block according to the second gripping position coordinates includes:

[0026] The depth information corresponding to the residual electrode block image is obtained, and a corresponding three-dimensional point cloud is generated based on the depth information and the residual electrode block image. Based on the three-dimensional point cloud, the grasping posture of the preset grasping device is determined.

[0027] Based on the grasping posture and the second grasping position coordinates, the preset grasping device is controlled to grasp and sort the residual carbon block.

[0028] Determining the grasping posture of the preset grasping device based on the three-dimensional point cloud includes:

[0029] Principal component analysis is performed on the three-dimensional point cloud to obtain the principal component analysis results, wherein the principal component analysis results are used to characterize the minimum volume orientation of the bounding box of the three-dimensional point cloud.

[0030] Based on the principal component analysis results, the grasping posture of the preset grasping device is determined.

[0031] Secondly, this application also provides a residual carbon block sorting device, comprising:

[0032] An acquisition module is used to acquire an image of the residual carbon block corresponding to the residual carbon block, wherein the residual carbon block is located on the transmission device;

[0033] The recognition module is used to perform target detection on the residual carbon block based on the residual carbon block image, and obtain the pixel position coordinates of the residual carbon block in the pixel coordinate system;

[0034] The conversion module is used to convert the pixel position coordinates of the carbon block into the first grasping position coordinates in the robot coordinate system according to the preset hand-eye calibration information.

[0035] A generation module is used to determine the calibration speed information of the transmission device and generate a second grasping position coordinate based on the first grasping position coordinate and the calibration speed information.

[0036] The control module is used to control the preset gripping device to grip and sort the residual carbon block according to the second gripping position coordinates.

[0037] Thirdly, this application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0038] A residual carbon block image is acquired, wherein the residual carbon block is located on a transmission device; based on the residual carbon block image, target detection is performed on the residual carbon block to obtain the pixel position coordinates of the carbon block in a pixel coordinate system; based on preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into first grasping position coordinates in a robot coordinate system; the calibration speed information of the transmission device is determined, and a second grasping position coordinate is generated based on the first grasping position coordinate and the calibration speed information; based on the second grasping position coordinate, a preset grasping device is controlled to grasp and sort the residual carbon block.

[0039] Fourthly, this application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, performs the following steps:

[0040] A residual carbon block image is acquired, wherein the residual carbon block is located on a transmission device; based on the residual carbon block image, target detection is performed on the residual carbon block to obtain the pixel position coordinates of the carbon block in a pixel coordinate system; based on preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into first grasping position coordinates in a robot coordinate system; the calibration speed information of the transmission device is determined, and a second grasping position coordinate is generated based on the first grasping position coordinate and the calibration speed information; based on the second grasping position coordinate, a preset grasping device is controlled to grasp and sort the residual carbon block.

[0041] Fifthly, this application also provides a computer program product, including a computer program that, when executed by a processor, performs the following steps:

[0042] A residual carbon block image is acquired, wherein the residual carbon block is located on a transmission device; based on the residual carbon block image, target detection is performed on the residual carbon block to obtain the pixel position coordinates of the carbon block in a pixel coordinate system; based on preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into first grasping position coordinates in a robot coordinate system; the calibration speed information of the transmission device is determined, and a second grasping position coordinate is generated based on the first grasping position coordinate and the calibration speed information; based on the second grasping position coordinate, a preset grasping device is controlled to grasp and sort the residual carbon block.

[0043] The aforementioned method, apparatus, computer equipment, computer-readable storage medium, and computer program product for sorting residual carbon blocks first acquire an image of the residual carbon block, wherein the residual carbon block is located on a transmission device. Then, based on the residual carbon block image, deep learning-based target detection can be performed on the residual carbon block, thereby accurately locating the carbon block's pixel position coordinates in the pixel coordinate system. Based on preset hand-eye calibration information, the carbon block's pixel position coordinates can be converted into the first grasping position coordinates in the robot coordinate system. This achieves precise positioning of the residual carbon block in the robot coordinate system, after which the transmission device can be determined. The calibration speed information is used to generate a second gripping position coordinate based on the first gripping position coordinate and the calibration speed information. This takes into account the operating speed of the transmission device and further optimizes the first gripping position coordinate, making the obtained second gripping position coordinate more accurate. It realizes the accurate positioning of the gripping position of the residual carbon block based on the preset hand-eye calibration information obtained by hand-eye calibration and the calibration speed information obtained by dynamic calibration based on the speed of the transmission device, and obtains the second gripping position coordinate. Therefore, in this application, the preset gripping device is controlled to grip and sort the residual carbon block based on the more accurate second gripping position coordinate, which can improve the sorting accuracy of the residual carbon block. Attached Figure Description

[0044] To more clearly illustrate the technical solutions in the embodiments of this application or related technologies, the drawings used in the description of the embodiments of this application or related technologies will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0045] Figure 1 This is a flowchart illustrating a method for sorting residual carbon blocks in one embodiment of this application.

[0046] Figure 2 This is a schematic diagram of the process for determining the calibration speed information of the transmission device in one embodiment of this application;

[0047] Figure 3 This is a schematic diagram of the process of controlling a preset gripping device to grip and sort residual carbon blocks in one embodiment of this application;

[0048] Figure 4 This is a structural block diagram of a residual carbon block sorting device in one embodiment of this application;

[0049] Figure 5 This is an internal structural diagram of a computer device in one embodiment of this application. Detailed Implementation

[0050] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0051] In one exemplary embodiment, such as Figure 1 As shown, a method for sorting residual carbon blocks is provided, including steps 202 to 210. Wherein:

[0052] Step 202: Obtain the image of the residual carbon block corresponding to the residual carbon block, wherein the residual carbon block is located on the transmission device.

[0053] In this embodiment, the residual carbon blocks are placed on a conveying device for transport, and a preset gripping device can be controlled to grip the residual carbon blocks on the conveying device to a preset position, thereby achieving the sorting of residual carbon blocks.

[0054] As an example, a camera can be provided in this embodiment to capture images of the residual carbon block transmitted on the transmission device, thereby obtaining an image of the residual carbon block, wherein the image of the residual carbon block includes relevant image information of the residual carbon block.

[0055] As an example, the aforementioned transmission information could be a conveyor belt.

[0056] Step 204: Based on the image of the residual electrode block, perform target detection on the residual electrode carbon block to obtain the pixel position coordinates of the carbon block in the pixel coordinate system.

[0057] As an example, step 204 includes: performing target detection on the residual electrode block image to obtain a target detection box, and identifying the outline position coordinates of the target detection box; and locating the pixel position coordinates of the residual electrode block in the pixel coordinate system based on the outline position coordinates.

[0058] As an example, in this embodiment, the first position coordinate of the upper left corner of the target detection box and the second position coordinate of the upper right corner of the target detection box can be identified; then the first position coordinate and the second position coordinate can be averaged to obtain the pixel position coordinate of the carbon block in the pixel coordinate system.

[0059] As an example, the object detection process can be performed using a deep learning model, such as the YOLOv8 network model or other deep learning framework models.

[0060] It should be noted that because the color of the residual carbon blocks is dark, the surface texture features of the residual carbon blocks are usually not obvious. Therefore, it is usually difficult to identify the residual carbon blocks based on traditional two-dimensional images, and the recognition accuracy is not high. However, in this embodiment, the target detection is based on a deep learning model. Even if the surface texture features of the residual carbon blocks are not obvious, the pixel position coordinates of the carbon blocks corresponding to the residual carbon blocks can be accurately identified by recognizing the target detection box in the residual carbon block image, which lays the foundation for accurate sorting of residual carbon blocks in the future.

[0061] Step 206: Based on the preset hand-eye calibration information, convert the pixel position coordinates of the carbon block into the first grasping position coordinates in the robot coordinate system.

[0062] In this embodiment, the preset hand-eye calibration information can be a hand-eye calibration matrix. The preset hand-eye calibration information can be obtained by performing hand-eye calibration. The preset hand-eye calibration information represents the mapping relationship between the robot coordinate system where the preset grasping device is located and the pixel coordinate system corresponding to the camera.

[0063] As an example, step 206 includes: mapping the pixel position coordinates of the carbon block to the robot coordinate system according to the hand-eye calibration matrix to obtain the first grasping position coordinates; for example, in this embodiment, the product between the pixel position coordinates of the carbon block and the hand-eye calibration matrix can be calculated to obtain the first grasping position coordinates.

[0064] Step 208: Determine the calibration speed information of the transmission device, and generate the second gripping position coordinates based on the first gripping position coordinates and the calibration speed information.

[0065] Among them, the calibration speed information of the transmission device can be the speed information obtained by performing dynamic speed calibration on the transmission device.

[0066] As an example, step 208 includes: determining the transmission displacement of the transmission device based on the calibration speed information of the transmission device; and adjusting the first grasping position coordinates according to the transmission position to obtain the second grasping position coordinates.

[0067] As an example, based on the first grasping position coordinates and the calibration speed information, the second grasping position coordinates are generated, including:

[0068] The grasping delay is obtained, wherein the grasping delay represents the delay from capturing the image of the residual electrode block to the grasping and sorting by the preset grasping device; the transmission displacement of the transmission device is determined based on the calibration speed information and the grasping delay; and the second grasping position coordinates are located based on the transmission displacement and the first grasping position coordinates.

[0069] In this embodiment, from the camera capturing the image of the residual electrode block to the preset gripping device gripping the residual electrode block at the target position, there is usually a certain gripping delay. Therefore, in order to accurately locate the actual gripping position of the preset gripping device, the operating speed of the device needs to be considered.

[0070] Specifically, the grasping delay can be obtained first, where the grasping delay represents the delay from capturing the image of the residual electrode block to the grasping and sorting by the preset grasping device; the product between the calibration speed information and the grasping delay is calculated to obtain the transmission displacement of the transmission device; according to the transmission position, the coordinate values ​​of the first grasping position coordinates in the transmission direction of the transmission device are adjusted to obtain the second grasping position coordinates.

[0071] As an example, the formula for calculating the coordinates of the second grab position is as follows:

[0072]

[0073] in, The coordinates of the second grab position. For hand-eye calibration matrix, These are the pixel coordinates of the carbon block. The preset transmission device's calibration speed, To capture delays.

[0074] Step 210: Based on the second gripping position coordinates, control the preset gripping device to grip and sort the residual carbon blocks.

[0075] As an example, step 210 includes: controlling a preset gripping device to grip and sort the residual carbon blocks at the second gripping position coordinates.

[0076] As an example, the pre-defined gripping device could be a robotic arm.

[0077] In the above-mentioned method for sorting residual carbon blocks, the residual carbon block image is first acquired, where the residual carbon block is located on the transmission device. Then, based on the residual carbon block image, deep learning-based target detection can be performed on the residual carbon block, thereby accurately locating the pixel position coordinates of the residual carbon block in the pixel coordinate system. Based on preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into the first grasping position coordinates in the robot coordinate system. This achieves precise positioning of the residual carbon block in the robot coordinate system. Afterwards, the calibration speed information of the transmission device can be determined, and based on the first grasping... The second gripping position coordinates are generated by taking into account the operating speed of the transmission device and further optimizing the first gripping position coordinates, making the obtained second gripping position coordinates more accurate. This achieves accurate positioning of the gripping position of the residual carbon block based on the preset hand-eye calibration information obtained from hand-eye calibration and the calibration speed information obtained from the dynamic calibration of the transmission device speed, thus obtaining the second gripping position coordinates. Therefore, in this embodiment, the preset gripping device is controlled to grip and sort the residual carbon block based on the more accurate second gripping position coordinates, which can improve the sorting accuracy of the residual carbon block.

[0078] In one exemplary embodiment, such as Figure 2 As shown, the calibration speed information of the transmission device is determined, including:

[0079] Step 302: Acquire a first calibration code image captured at a first time point and a second calibration code image captured at a second time point, wherein the calibration code is located on the transmission device and the transmission device is in motion.

[0080] In this embodiment, a calibration code can be placed on the transmission device. The calibration code can be placed on the transmission device in the form of a calibration plate, or it can be directly set on the body of the transmission device; no limitation is made here.

[0081] As an example, step 302 includes: on the calibration code displacement transmission device, and after the transmission device is in motion, controlling the camera to capture a first calibration code image at a first time point, and capturing a second calibration code image at a second time point, wherein both the first and second calibration code images include image information of the calibration code, and the second time point is later than the first time point.

[0082] Step 304: Identify the coordinates of the first pixel position corresponding to the calibration code based on the first calibration code image.

[0083] As an example, step 304 includes: performing target detection on the first calibration code image to obtain a first calibration code detection box; performing pixel position coordinate recognition on the first calibration code detection box to obtain first pixel position coordinates; wherein, the first pixel position coordinates can be the center position coordinates or the boundary position coordinates of the first calibration code detection box.

[0084] Step 306: Identify the coordinates of the second pixel position corresponding to the calibration code based on the second calibration code image.

[0085] As an example, step 306 includes: performing target detection on the second calibration code image to obtain a second calibration code detection box; performing pixel position coordinate recognition on the second calibration code detection box to obtain second pixel position coordinates; wherein, the second pixel position coordinates can be the center position coordinates or the boundary position coordinates of the second calibration code detection box.

[0086] Step 308: Based on the position coordinates of the first pixel and the second pixel, perform dynamic speed calibration on the transmission device to obtain calibration speed information.

[0087] As an example, step 308 includes: performing dynamic speed calibration on the transmission device based on the coordinate difference between the first pixel position coordinates and the second pixel position coordinates in the robot coordinate system to obtain calibration speed information.

[0088] As an example, based on the coordinates of the first pixel position and the second pixel position, the transmission device is dynamically calibrated to obtain calibration speed information, including:

[0089] Determine the time difference between the first and second time points; based on preset hand-eye calibration information, transform the coordinates of the first pixel position to the robot coordinate system to obtain the coordinates of the first code position; based on preset hand-eye calibration information, transform the coordinates of the second pixel position to the robot coordinate system to obtain the coordinates of the second code position; based on the time difference, the coordinates of the first code position, and the coordinates of the second code position, generate the calibration speed information of the transmission device.

[0090] Specifically, the time difference between the first time point and the second time point is calculated; the first pixel position coordinates are mapped to the robot coordinate system according to the hand-eye calibration matrix to obtain the first code position coordinates; the second pixel position coordinates are mapped to the robot coordinate system according to the hand-eye calibration matrix to obtain the second code position coordinates; and the calibration speed information of the transmission device is calculated based on the absolute value of the time difference, the first code position coordinates, and the second code position coordinates.

[0091] As an example, the formula for calculating the calibration speed information of the transmission device is as follows:

[0092]

[0093] in, For the second time point, As the first point in time, The coordinates of the second code position. The coordinates of the first code position.

[0094] In this embodiment, a first calibration code image captured at a first time point and a second calibration code image captured at a second time point can be acquired first, wherein the calibration code is located on the transmission device and the transmission device is in motion. Then, the first pixel position coordinates corresponding to the calibration code can be identified based on the first calibration code image, and the second pixel position coordinates corresponding to the calibration code can be identified based on the second calibration code image. In this way, based on the first pixel position coordinates and the second pixel position coordinates, the movement speed of the transmission device can be calculated, realizing real-time dynamic speed calibration of the transmission device, obtaining calibration speed information, ensuring the real-time and accuracy of the calibration speed information, and laying the foundation for accurately determining the second grasping position coordinates.

[0095] In one exemplary embodiment, such as Figure 3 As shown, based on the second gripping position coordinates, the preset gripping device is controlled to grip and sort the residual carbon blocks, including:

[0096] Step 402: Obtain the depth information corresponding to the residual electrode block image, generate the corresponding three-dimensional point cloud based on the depth information and the residual electrode block image, and determine the grasping posture of the preset grasping device based on the three-dimensional point cloud.

[0097] It should be noted that when the preset gripping device grips the residual carbon block, the gripping accuracy is not only related to the gripping position, but also usually related to the gripping posture of the preset gripping device. The preset gripping device can improve the gripping success rate by gripping the residual carbon block with a more suitable gripping posture.

[0098] In this embodiment, the camera can be a depth camera, which can directly obtain the depth information of the residual carbon block.

[0099] As an example, step 402 includes: acquiring depth information corresponding to the image of the residual electrode block, and performing three-dimensional reconstruction based on the depth information and the image of the residual electrode block to obtain a three-dimensional point cloud corresponding to the residual electrode carbon block; and matching the corresponding grasping posture for the preset grasping device based on the three-dimensional point cloud.

[0100] As an example, based on the 3D point cloud, the grasping posture of the preset grasping device is determined, including:

[0101] Principal component analysis is performed on the 3D point cloud to obtain the principal component analysis results. The principal component analysis results are used to characterize the minimum volume orientation of the bounding box of the 3D point cloud. Based on the principal component analysis results, the grasping posture of the preset grasping device is determined.

[0102] In this embodiment, the principal component analysis results can be the eigenvalues ​​and eigenvectors corresponding to the covariance matrix. The eigenvalues ​​represent the variance of the 3D point cloud in the direction of the eigenvectors, and the eigenvectors represent the main direction of the point cloud distribution.

[0103] Specifically, the position coordinates of each point in the 3D point cloud are averaged to obtain the centroid position coordinates of the 3D point cloud; based on the position coordinates of each point and the centroid position coordinates in the 3D point cloud, the covariance matrix corresponding to the 3D point cloud is calculated, and the eigenvalues ​​and eigenvectors of the covariance matrix are determined; using the eigenvalues ​​and eigenvectors as input data, the grasping posture of the preset grasping device is adjusted; wherein, the covariance matrix is ​​used to describe the distribution of the 3D point cloud in each dimension and the relationship between the dimensions.

[0104] As an example, the formula for calculating the covariance matrix is ​​as follows:

[0105]

[0106] in, Let covariance matrix be the variance matrix. For the third point cloud The location coordinates of each point. Let these be the coordinates of the centroid position. This represents the number of data points in the 3D point cloud.

[0107] Step 404: Based on the gripping posture and the coordinates of the second gripping position, control the preset gripping device to grip and sort the residual carbon blocks.

[0108] As an example, step 404 includes: controlling a preset gripping device to grip and sort the residual carbon blocks at the second gripping position coordinates in the gripping posture described above.

[0109] In this embodiment, after obtaining the second gripping position coordinates, the depth information corresponding to the residual electrode block image is also obtained. Based on the depth information and the residual electrode block image, a corresponding three-dimensional point cloud is generated. Based on the three-dimensional point cloud, the gripping posture of the preset gripping device is determined. Then, based on the gripping posture and the second gripping position coordinates, the preset gripping device is controlled to grip and sort the residual electrode blocks. In this way, the second gripping position coordinates are obtained with higher accuracy, and the influence of the gripping posture on the gripping and sorting is also taken into account. In this embodiment, the preset gripping device can be controlled to grip and sort the residual electrode blocks with a more suitable gripping posture, which helps to improve the accuracy of gripping and sorting the residual electrode blocks.

[0110] It should be understood that although the steps in the flowcharts of the embodiments described above are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the embodiments described above may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages in other steps. It is understood that the steps in different embodiments can be freely combined as needed, and all non-contradictory solutions formed by such combinations are within the scope of protection of this application.

[0111] Based on the same inventive concept, this application also provides a residual carbon block sorting device for implementing the above-mentioned residual carbon block sorting method. The solution provided by this device is similar to the solution described in the above method. Therefore, the specific limitations of one or more residual carbon block sorting device embodiments provided below can be found in the limitations of the residual carbon block sorting method above, and will not be repeated here.

[0112] In one exemplary embodiment, such as Figure 4 As shown, a residual carbon block sorting device is provided, including: an acquisition module 502, an identification module 504, a conversion module 506, a generation module 508, and a control module 510, wherein:

[0113] The acquisition module 502 is used to acquire an image of the residual carbon block corresponding to the residual carbon block, wherein the residual carbon block is located on the transmission device;

[0114] The identification module 504 is used to perform target detection on the residual carbon block based on the residual carbon block image, and obtain the carbon block pixel position coordinates in the pixel coordinate system.

[0115] The conversion module 506 is used to convert the pixel position coordinates of the carbon block into the first grasping position coordinates in the robot coordinate system according to the preset hand-eye calibration information.

[0116] The generation module 508 is used to determine the calibration speed information of the transmission device and generate the second gripping position coordinates based on the first gripping position coordinates and the calibration speed information.

[0117] The control module 510 is used to control the preset gripping device to grip and sort the residual carbon block according to the second gripping position coordinates.

[0118] In one embodiment, the generation module is further configured to:

[0119] A first calibration code image captured at a first time point and a second calibration code image captured at a second time point are acquired, wherein the calibration code is located on the transmission device and the transmission device is in motion; based on the first calibration code image, the first pixel position coordinates corresponding to the calibration code are identified; based on the second calibration code image, the second pixel position coordinates corresponding to the calibration code are identified; based on the first pixel position coordinates and the second pixel position coordinates, the transmission device is dynamically calibrated to obtain calibration speed information.

[0120] In one embodiment, the generation module is further configured to:

[0121] Determine the time difference between the first time point and the second time point; based on preset hand-eye calibration information, transform the first pixel position coordinates to the robot coordinate system to obtain the first code position coordinates; based on the preset hand-eye calibration information, transform the second pixel position coordinates to the robot coordinate system to obtain the second code position coordinates; based on the time difference, the first code position coordinates, and the second code position coordinates, generate the calibration speed information of the transmission device.

[0122] In one embodiment, the generation module is further configured to:

[0123] The grasping delay is obtained, wherein the grasping delay represents the delay from capturing the image of the residual electrode block to the grasping and sorting by the preset grasping device; the transmission displacement of the transmission device is determined according to the calibration speed information and the grasping delay; and the second grasping position coordinates are located according to the transmission displacement and the first grasping position coordinates.

[0124] In one embodiment, the control module is further configured to:

[0125] The depth information corresponding to the image of the residual electrode block is obtained, and a corresponding three-dimensional point cloud is generated based on the depth information and the image of the residual electrode block. Based on the three-dimensional point cloud, the grasping posture of the preset grasping device is determined. Based on the grasping posture and the second grasping position coordinates, the preset grasping device is controlled to grasp and sort the residual electrode carbon block.

[0126] In one embodiment, the control module is further configured to:

[0127] Principal component analysis is performed on the three-dimensional point cloud to obtain the principal component analysis results, wherein the principal component analysis results are used to characterize the minimum volume orientation of the bounding box of the three-dimensional point cloud; based on the principal component analysis results, the grasping posture of the preset grasping device is determined.

[0128] Each module in the aforementioned residual carbon block sorting device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the operations corresponding to each module.

[0129] In one exemplary embodiment, a computer device is provided, which may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor, memory, input / output interface, communication interface, display unit, and input device. The processor, memory, and input / output interface are connected via a system bus, and the communication interface, display unit, and input device are also connected to the system bus via the input / output interface. The processor provides computing and control capabilities. The memory includes a non-volatile storage medium and internal memory. The non-volatile storage medium stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage medium. The input / output interface is used for exchanging information between the processor and external devices. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, mobile cellular networks, Near Field Communication (NFC), or other technologies. When the computer program is executed by the processor, it implements a method for sorting residual carbon blocks. Those skilled in the art will understand that... Figure 5 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0130] In one exemplary embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0131] A residual carbon block image is acquired, wherein the residual carbon block is located on a transmission device; based on the residual carbon block image, target detection is performed on the residual carbon block to obtain the pixel position coordinates of the carbon block in a pixel coordinate system; based on preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into first grasping position coordinates in a robot coordinate system; the calibration speed information of the transmission device is determined, and a second grasping position coordinate is generated based on the first grasping position coordinate and the calibration speed information; based on the second grasping position coordinate, a preset grasping device is controlled to grasp and sort the residual carbon block.

[0132] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0133] A first calibration code image captured at a first time point and a second calibration code image captured at a second time point are acquired, wherein the calibration code is located on the transmission device and the transmission device is in motion; based on the first calibration code image, the first pixel position coordinates corresponding to the calibration code are identified; based on the second calibration code image, the second pixel position coordinates corresponding to the calibration code are identified; based on the first pixel position coordinates and the second pixel position coordinates, the transmission device is dynamically calibrated to obtain calibration speed information.

[0134] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0135] Determine the time difference between the first time point and the second time point; based on preset hand-eye calibration information, transform the first pixel position coordinates to the robot coordinate system to obtain the first code position coordinates; based on the preset hand-eye calibration information, transform the second pixel position coordinates to the robot coordinate system to obtain the second code position coordinates; based on the time difference, the first code position coordinates, and the second code position coordinates, generate the calibration speed information of the transmission device.

[0136] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0137] The grasping delay is obtained, wherein the grasping delay represents the delay from capturing the image of the residual electrode block to the grasping and sorting by the preset grasping device; the transmission displacement of the transmission device is determined according to the calibration speed information and the grasping delay; and the second grasping position coordinates are located according to the transmission displacement and the first grasping position coordinates.

[0138] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0139] The depth information corresponding to the image of the residual electrode block is obtained, and a corresponding three-dimensional point cloud is generated based on the depth information and the image of the residual electrode block. Based on the three-dimensional point cloud, the grasping posture of the preset grasping device is determined. Based on the grasping posture and the second grasping position coordinates, the preset grasping device is controlled to grasp and sort the residual electrode carbon block.

[0140] In one embodiment, the processor, when executing a computer program, also performs the following steps:

[0141] Principal component analysis is performed on the three-dimensional point cloud to obtain the principal component analysis results, wherein the principal component analysis results are used to characterize the minimum volume orientation of the bounding box of the three-dimensional point cloud; based on the principal component analysis results, the grasping posture of the preset grasping device is determined.

[0142] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0143] A residual carbon block image is acquired, wherein the residual carbon block is located on a transmission device; based on the residual carbon block image, target detection is performed on the residual carbon block to obtain the pixel position coordinates of the carbon block in a pixel coordinate system; based on preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into first grasping position coordinates in a robot coordinate system; the calibration speed information of the transmission device is determined, and a second grasping position coordinate is generated based on the first grasping position coordinate and the calibration speed information; based on the second grasping position coordinate, a preset grasping device is controlled to grasp and sort the residual carbon block.

[0144] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0145] A first calibration code image captured at a first time point and a second calibration code image captured at a second time point are acquired, wherein the calibration code is located on the transmission device and the transmission device is in motion; based on the first calibration code image, the first pixel position coordinates corresponding to the calibration code are identified; based on the second calibration code image, the second pixel position coordinates corresponding to the calibration code are identified; based on the first pixel position coordinates and the second pixel position coordinates, the transmission device is dynamically calibrated to obtain calibration speed information.

[0146] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0147] Determine the time difference between the first time point and the second time point; based on preset hand-eye calibration information, transform the first pixel position coordinates to the robot coordinate system to obtain the first code position coordinates; based on the preset hand-eye calibration information, transform the second pixel position coordinates to the robot coordinate system to obtain the second code position coordinates; based on the time difference, the first code position coordinates, and the second code position coordinates, generate the calibration speed information of the transmission device.

[0148] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0149] The grasping delay is obtained, wherein the grasping delay represents the delay from capturing the image of the residual electrode block to the grasping and sorting by the preset grasping device; the transmission displacement of the transmission device is determined according to the calibration speed information and the grasping delay; and the second grasping position coordinates are located according to the transmission displacement and the first grasping position coordinates.

[0150] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0151] The depth information corresponding to the image of the residual electrode block is obtained, and a corresponding three-dimensional point cloud is generated based on the depth information and the image of the residual electrode block. Based on the three-dimensional point cloud, the grasping posture of the preset grasping device is determined. Based on the grasping posture and the second grasping position coordinates, the preset grasping device is controlled to grasp and sort the residual electrode carbon block.

[0152] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0153] Principal component analysis is performed on the three-dimensional point cloud to obtain the principal component analysis results, wherein the principal component analysis results are used to characterize the minimum volume orientation of the bounding box of the three-dimensional point cloud; based on the principal component analysis results, the grasping posture of the preset grasping device is determined.

[0154] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, performs the following steps:

[0155] A residual carbon block image is acquired, wherein the residual carbon block is located on a transmission device; based on the residual carbon block image, target detection is performed on the residual carbon block to obtain the pixel position coordinates of the carbon block in a pixel coordinate system; based on preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into first grasping position coordinates in a robot coordinate system; the calibration speed information of the transmission device is determined, and a second grasping position coordinate is generated based on the first grasping position coordinate and the calibration speed information; based on the second grasping position coordinate, a preset grasping device is controlled to grasp and sort the residual carbon block.

[0156] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0157] A first calibration code image captured at a first time point and a second calibration code image captured at a second time point are acquired, wherein the calibration code is located on the transmission device and the transmission device is in motion; based on the first calibration code image, the first pixel position coordinates corresponding to the calibration code are identified; based on the second calibration code image, the second pixel position coordinates corresponding to the calibration code are identified; based on the first pixel position coordinates and the second pixel position coordinates, the transmission device is dynamically calibrated to obtain calibration speed information.

[0158] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0159] Determine the time difference between the first time point and the second time point; based on preset hand-eye calibration information, transform the first pixel position coordinates to the robot coordinate system to obtain the first code position coordinates; based on the preset hand-eye calibration information, transform the second pixel position coordinates to the robot coordinate system to obtain the second code position coordinates; based on the time difference, the first code position coordinates, and the second code position coordinates, generate the calibration speed information of the transmission device.

[0160] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0161] The grasping delay is obtained, wherein the grasping delay represents the delay from capturing the image of the residual electrode block to the grasping and sorting by the preset grasping device; the transmission displacement of the transmission device is determined according to the calibration speed information and the grasping delay; and the second grasping position coordinates are located according to the transmission displacement and the first grasping position coordinates.

[0162] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0163] The depth information corresponding to the image of the residual electrode block is obtained, and a corresponding three-dimensional point cloud is generated based on the depth information and the image of the residual electrode block. Based on the three-dimensional point cloud, the grasping posture of the preset grasping device is determined. Based on the grasping posture and the second grasping position coordinates, the preset grasping device is controlled to grasp and sort the residual electrode carbon block.

[0164] In one embodiment, when the computer program is executed by a processor, it also performs the following steps:

[0165] Principal component analysis is performed on the three-dimensional point cloud to obtain the principal component analysis results, wherein the principal component analysis results are used to characterize the minimum volume orientation of the bounding box of the three-dimensional point cloud; based on the principal component analysis results, the grasping posture of the preset grasping device is determined.

[0166] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium, and when executed, it can include the processes of the embodiments of the above methods. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, artificial intelligence (AI) processors, etc., and are not limited to these.

[0167] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this application.

[0168] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for sorting residual carbon blocks, characterized in that, The method includes: Acquire an image of the residual carbon block corresponding to the residual carbon block, wherein the residual carbon block is located on the transmission device; Based on the image of the residual electrode block, target detection is performed on the residual electrode carbon block to obtain the pixel position coordinates of the carbon block in the pixel coordinate system; Based on the preset hand-eye calibration information, the pixel position coordinates of the carbon block are converted into the first grasping position coordinates in the robot coordinate system; Determine the calibration speed information of the transmission device, and generate the second gripping position coordinates based on the first gripping position coordinates and the calibration speed information; Based on the second gripping position coordinates, the preset gripping device is controlled to grip and sort the residual carbon blocks.

2. The method according to claim 1, characterized in that, Determining the calibration speed information of the transmission device includes: Acquire a first calibration code image captured at a first time point and a second calibration code image captured at a second time point, wherein the calibration code is located on the transmission device and the transmission device is in motion; Based on the first calibration code image, identify the coordinates of the first pixel position corresponding to the calibration code; Based on the second calibration code image, identify the second pixel position coordinates corresponding to the calibration code; Based on the first pixel position coordinates and the second pixel position coordinates, the transmission device is dynamically calibrated to obtain calibration speed information.

3. The method according to claim 2, characterized in that, The step of performing dynamic speed calibration on the transmission device based on the first pixel position coordinates and the second pixel position coordinates to obtain calibration speed information includes: Determine the time difference between the first time point and the second time point; Based on the preset hand-eye calibration information, the position coordinates of the first pixel are transformed into the robot coordinate system to obtain the position coordinates of the first code; Based on the preset hand-eye calibration information, the second pixel position coordinates are transformed into the robot coordinate system to obtain the second code position coordinates; The calibration speed information of the transmission device is generated based on the time difference, the position coordinates of the first code, and the position coordinates of the second code.

4. The method according to claim 1, characterized in that, The step of generating the second grasping position coordinates based on the first grasping position coordinates and the calibration speed information includes: The grasping delay is obtained, wherein the grasping delay represents the delay from capturing the image of the residual electrode block to the grasping and sorting by the preset grasping device; The transmission displacement of the transmission device is determined based on the calibration speed information and the grasping delay; Based on the transmission displacement and the first grasping position coordinates, the second grasping position coordinates are located.

5. The method according to claim 1, characterized in that, The step of controlling a preset gripping device to grip and sort the residual carbon block according to the second gripping position coordinates includes: The depth information corresponding to the residual electrode block image is obtained, and a corresponding three-dimensional point cloud is generated based on the depth information and the residual electrode block image. Based on the three-dimensional point cloud, the grasping posture of the preset grasping device is determined. Based on the grasping posture and the second grasping position coordinates, the preset grasping device is controlled to grasp and sort the residual carbon block.

6. The method according to claim 5, characterized in that, Determining the grasping posture of the preset grasping device based on the three-dimensional point cloud includes: Principal component analysis is performed on the three-dimensional point cloud to obtain the principal component analysis results, wherein the principal component analysis results are used to characterize the minimum volume orientation of the bounding box of the three-dimensional point cloud. Based on the principal component analysis results, the grasping posture of the preset grasping device is determined.

7. A sorting device for residual carbon blocks, characterized in that, The device includes: An acquisition module is used to acquire an image of the residual carbon block corresponding to the residual carbon block, wherein the residual carbon block is located on the transmission device; The recognition module is used to perform target detection on the residual carbon block based on the residual carbon block image, and obtain the pixel position coordinates of the residual carbon block in the pixel coordinate system; The conversion module is used to convert the pixel position coordinates of the carbon block into the first grasping position coordinates in the robot coordinate system according to the preset hand-eye calibration information. A generation module is used to determine the calibration speed information of the transmission device and generate a second grasping position coordinate based on the first grasping position coordinate and the calibration speed information. The control module is used to control the preset gripping device to grip and sort the residual carbon block according to the second gripping position coordinates.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images