Emptying method, device and server

Abstract

The application provides a kind of empty material processing method, device and server, it is related to data processing technology, the method comprises: extracting the inner contour point cloud of the pressing position on the steel plate.The pose of the scrap point cloud of the steel plate scrap outside the pressing position and the pose of the empty material detection area point cloud in the pressing position are obtained according to the inner contour point cloud.If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the scrap point cloud is less than a preset threshold, it is determined that there is a workpiece in the pressing position, and there is no empty material.The method of the application can determine whether there is a workpiece in the pressing position according to the thickness difference between the pose of the empty material detection area point cloud and the pose of the scrap point cloud, avoiding continuing to suck the workpiece in the empty material condition, thereby reducing the invalid suction operation, and solving the technical problem of low efficiency of sucking the workpiece.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of data processing, in particular to a blank processing method, device and server. BACKGROUND

[0002] At present, in the pipeline, the workpiece made in the steel plate needs to be sucked.

[0003] In the prior art, the workpiece sequentially arranged in the steel plate is directly sucked.

[0004] However, in the prior art, since the workpiece sequentially arranged in the steel plate is directly sucked, if there is no workpiece at the suction position, the steel plate will be directly sucked, so that the suction operation is invalid, resulting in low efficiency of sucking the workpiece. SUMMARY

[0005] The present application provides a blank processing method, device and server to solve the technical problem of low efficiency of sucking the workpiece.

[0006] In a first aspect, the present application provides a blank processing method, comprising:

[0007] extracting an inner contour point cloud of a pressing position on a steel plate; wherein the pressing position is a position on the steel plate for separating and making a workpiece;

[0008] According to the inner contour point cloud, the pose of the waste point cloud of the waste material around the pressing position and the pose of the empty material detection area point cloud inside the pressing position are obtained;

[0009] If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud is less than a preset threshold, it is determined that the workpiece exists in the pressing position and there is no empty material.

[0010] Further, the inner contour point cloud is obtained according to the inner contour point cloud, the pose of the waste point cloud of the waste material around the pressing position and the pose of the empty material detection area point cloud inside the pressing position, comprising:

[0011] performing three-dimensional template matching on the inner contour point cloud to obtain a target workpiece template point cloud corresponding to the inner contour point cloud;

[0012] mapping to obtain a workpiece two-dimensional image corresponding to the target workpiece template point cloud;

[0013] According to the preset inflation rule information, the workpiece two-dimensional image is inflated to obtain the pose of the waste point cloud of the waste material around the pressing position; wherein the preset inflation rule information is used to indicate that the workpiece two-dimensional image is inflated according to a preset inflation coefficient;

[0014] According to the preset reduction rule information, the workpiece two-dimensional image is reduced to obtain the pose of the empty material detection area point cloud in the pressing position; wherein, the preset reduction rule information is used to indicate that the workpiece two-dimensional image is reduced according to the preset corrosion coefficient.

[0015] Further, the inner contour point cloud is matched with a three-dimensional template to obtain a target workpiece template point cloud corresponding to the inner contour point cloud, including:

[0016] According to the preset mapping relationship between the inner contour point cloud and the workpiece contour template point cloud, the target workpiece contour template point cloud corresponding to the inner contour point cloud is determined;

[0017] According to the preset mapping relationship between the workpiece contour template point cloud and the workpiece template point cloud, the target workpiece template point cloud corresponding to the target workpiece contour template point cloud is determined.

[0018] Further, the workpiece two-dimensional image is dilated according to the preset dilatation rule information to obtain the pose of the waste material point cloud of the peripheral steel plate waste material of the pressing position, including:

[0019] The workpiece two-dimensional image is dilated to obtain a dilated image of the workpiece two-dimensional image;

[0020] According to the workpiece two-dimensional image and the dilated image, the pose of the waste material point cloud of the peripheral steel plate waste material of the pressing position is obtained.

[0021] Further, the workpiece two-dimensional image is dilated to obtain a dilated image of the workpiece two-dimensional image, including:

[0022] According to the first dilatation coefficient and the second dilatation coefficient in the preset dilatation rule information, the workpiece two-dimensional image is dilated respectively to obtain a first dilated image corresponding to the first dilatation coefficient and a second dilated image corresponding to the second dilatation coefficient;

[0023] According to the workpiece two-dimensional image and the dilated image, the pose of the waste material point cloud of the peripheral steel plate waste material of the pressing position is obtained, including:

[0024] The first dilated image and the workpiece two-dimensional image are overlapped with the center as the reference, and a first non-overlapping area image between the first dilated image and the workpiece two-dimensional image is determined;

[0025] The second dilated image and the workpiece two-dimensional image are overlapped with the center as the reference, and a second non-overlapping area image between the second dilated image and the workpiece two-dimensional image is determined;

[0026] overlap the first non-overlapping area image and the second non-overlapping area image based on the center, and obtain a third non-overlapping area image between the first non-overlapping area image and the second non-overlapping area image;

[0027] The method further comprises:

[0028] Further, the method further comprises:

[0029] Further, the method further comprises:

[0030] The method further comprises:

[0031] Further, the method further comprises:

[0032] Further, the method further comprises:

[0033] Further, the method further comprises:

[0034] Further, the method further comprises:

[0035] Further, the method further comprises:

[0036] The second aspect of the present application provides an empty material processing device, comprising:

[0037] The extraction unit is configured to extract an inner contour point cloud of a pressing position on a steel plate, wherein the pressing position is a position on the steel plate for separating a workpiece;

[0038] The acquisition unit is configured to acquire a pose of a waste material point cloud of a waste material outside the pressing position and a pose of an empty material detection area point cloud inside the pressing position according to the inner contour point cloud;

[0039] The first determination unit is configured to determine that the pressing position has the workpiece and is not empty if it is determined that a thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is less than a preset threshold.

[0040] Further, the acquisition unit comprises:

[0041] The matching module is configured to perform three-dimensional template matching on the inner contour point cloud to obtain a target workpiece template point cloud corresponding to the inner contour point cloud.

[0042] The mapping module is configured to map to obtain a workpiece two-dimensional image corresponding to the target workpiece template point cloud.

[0043] The inflation module is configured to perform inflation processing on the workpiece two-dimensional image according to preset inflation rule information to obtain a pose of a waste point cloud of the peripheral steel plate waste of the pressing position; wherein the preset inflation rule information is used to indicate that the workpiece two-dimensional image is processed according to a preset inflation coefficient.

[0044] The reduction module is configured to perform reduction processing on the workpiece two-dimensional image according to preset reduction rule information to obtain a pose of an empty material detection area point cloud inside the pressing position; wherein the preset reduction rule information is used to indicate that the workpiece two-dimensional image is processed according to a preset corrosion coefficient.

[0045] Further, the matching module comprises:

[0046] The first determination submodule is configured to determine a target workpiece contour template point cloud corresponding to the inner contour point cloud according to a preset mapping relationship between the inner contour point cloud and the workpiece contour template point cloud.

[0047] The second determination submodule is configured to determine a target workpiece template point cloud corresponding to the target workpiece contour template point cloud according to a preset mapping relationship between the workpiece contour template point cloud and the workpiece template point cloud.

[0048] Further, the inflation module comprises:

[0049] The first determination submodule is configured to perform inflation processing on the workpiece two-dimensional image to obtain an inflation image of the workpiece two-dimensional image.

[0050] The second determination submodule is configured to obtain a pose of a waste point cloud of the peripheral steel plate waste of the pressing position according to the workpiece two-dimensional image and the inflation image.

[0051] Further, the first determination submodule is specifically configured to:

[0052] perform inflation processing on the workpiece two-dimensional image according to a first inflation coefficient and a second inflation coefficient in the preset inflation rule information to obtain a first inflation image corresponding to the first inflation coefficient and a second inflation image corresponding to the second inflation coefficient.

[0053] The second determining submodule comprises:

[0054] The third determining submodule is configured to overlap the first dilated image and the workpiece two-dimensional image based on the center, and determine a first non-overlapping area image between the first dilated image and the workpiece two-dimensional image.

[0055] The fourth determining submodule is configured to overlap the second dilated image and the workpiece two-dimensional image based on the center, and determine a second non-overlapping area image between the second dilated image and the workpiece two-dimensional image.

[0056] The fifth determining submodule is configured to overlap the first non-overlapping area image and the second non-overlapping area image based on the center, and obtain a third non-overlapping area image between the first non-overlapping area image and the second non-overlapping area image.

[0057] The sixth determining submodule is configured to map and obtain a waste point cloud corresponding to the third non-overlapping area image, and determine a pose of the waste point cloud.

[0058] Further, the reducing module comprises:

[0059] The seventh determining submodule is configured to perform reducing processing on the workpiece two-dimensional image according to an erosion coefficient in preset reducing rule information, to obtain a reduced image corresponding to the erosion coefficient.

[0060] The eighth determining submodule is configured to map and obtain an empty material detection area point cloud of a pressing position corresponding to the reduced image, and determine a pose of the empty material detection area point cloud.

[0061] Further, the device further comprises:

[0062] The identifying unit is configured to, if it is determined that a thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud is greater than or equal to a preset threshold, perform image recognition on the workpiece two-dimensional image according to a preset neural network model to obtain an identification result; wherein the preset neural network model is obtained by training images containing workpieces and images not containing workpieces.

[0063] The second determining unit is configured to, if it is determined that a color of the identification result is a preset waste color, determine that the pressing position does not contain the workpiece.

[0064] Further, the device further comprises:

[0065] The skipping unit is configured to skip the pressing position not containing the workpiece, and obtain a next inner contour point cloud.

[0066] In a third aspect, the present application provides a server, comprising a memory and a processor, wherein the memory stores a computer program capable of running on the processor, and the processor implements the method of the first aspect when executing the computer program.

[0067] In a fourth aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores computer execution instructions, and the computer execution instructions are used to implement the method of the first aspect when executed by a processor.

[0068] In a fifth aspect, the present application provides a computer program product, comprising a computer program, and the computer program implements the method of the first aspect when executed by a processor.

[0069] The method, device and server provided by the present application extract the inner contour point cloud of the pressing position on the steel plate, wherein the pressing position is the position of the steel plate for separating the workpiece. According to the inner contour point cloud, the pose of the waste point cloud of the waste material outside the pressing position and the pose of the empty material detection area point cloud inside the pressing position are obtained. If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud is less than a preset threshold, it is determined that there is a workpiece in the pressing position and the empty material. In the present scheme, the inner contour point cloud of the pressing position on the steel plate is extracted, wherein the periphery of the pressing position is the waste material of the steel plate, and the inner part of the pressing position contains the empty material detection area. According to the inner contour point cloud, the pose of the waste point cloud of the waste material outside the pressing position and the pose of the empty material detection area point cloud inside the pressing position are determined, and the empty material detection area point cloud is the point cloud corresponding to the empty material detection area. The pose of the empty material detection area point cloud and the pose of the waste point cloud are compared, and if it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud is less than a preset threshold, it is determined that there is a workpiece in the pressing position, and it is further determined that the pressing position is not empty. Therefore, whether there is a workpiece in the pressing position can be determined according to the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud, which avoids continuing to suck the workpiece in the empty material condition, thereby reducing the invalid suction operation and solving the technical problem of low efficiency of sucking the workpiece. BRIEF DESCRIPTION OF DRAWINGS

[0070] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the disclosure.

[0071] Figure 1 A flowchart of a method for processing empty material provided by an embodiment of the present application is shown in the figure;

[0072] Figure 2 A flowchart of another method for processing empty material provided by an embodiment of the present application is shown in the figure;

[0073] Figure 3 A flowchart of another empty material processing method provided by an embodiment of the present application is shown in FIG. 6.

[0074] Figure 4 A flowchart of another empty material processing method provided by an embodiment of the present application is shown in FIG. 6.

[0075] Figure 5 A structural diagram of an empty material processing device provided by an embodiment of the present application is shown in FIG. 7.

[0076] Figure 6 A structural diagram of another empty material processing device provided by an embodiment of the present application is shown in FIG. 8.

[0077] Figure 7 A structural diagram of a server provided by an embodiment of the present application is shown in FIG. 9.

[0078] The specific embodiments of the present disclosure have been shown through the above-described drawings, and will be described in more detail hereinafter. These drawings and descriptions are not intended to limit the scope of the present disclosure concept in any way, but to illustrate the present disclosure concept to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION

[0079] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, the same numbers are used to indicate the same or similar components. The embodiments described in the following exemplary embodiments are not intended to represent all embodiments consistent with the present disclosure.

[0080] In one example, in a pipeline, a workpiece made in a steel plate needs to be sucked. In the prior art, the workpiece sequentially arranged in the steel plate is directly sucked. However, in the prior art, if there is no workpiece at the suction position, the workpiece in the steel plate will be directly sucked, which makes the suction operation invalid and reduces the efficiency of sucking the workpiece.

[0081] The empty material processing method, device and server provided by the present application aim to solve the above technical problems in the prior art.

[0082] The technical solutions of the present application and how the technical solutions of the present application solve the above technical problems will be described in detail below with specific embodiments. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described again in some embodiments. The embodiments of the present application will be described below with reference to the drawings.

[0083] Figure 1 A flowchart of an empty material processing method provided by an embodiment of the present application is shown in FIG. 1, which includes the following steps. Figure 1 ​

[0084] 101. Extracting an inner contour point cloud where the pressing position is located on the steel plate; wherein the pressing position is a position on the steel plate where a workpiece is separated.

[0085] Exemplarily, the execution subject of the embodiment can be a server. First, an inner contour point cloud where the pressing position is located on the steel plate needs to be extracted. The pressing position is a position on the steel plate where a workpiece is separated, the workpiece manufacturing includes stamping / cutting the workpiece on the steel plate, and the workpiece separation includes sucking the manufactured workpiece; the inner contour point cloud where the pressing position is located represents a point cloud determined according to the contour shape of the blank position after the workpiece is separated at the pressing position.

[0086] 102. According to the inner contour point cloud, obtaining the pose of the waste point cloud of the steel plate waste outside the pressing position and the pose of the empty area detection region point cloud inside the pressing position.

[0087] Exemplarily, on the steel plate, the peripheral part of the pressing position, i.e., the peripheral part adjacent to the blank position after the workpiece is separated on the steel plate, is the remaining steel plate waste after the workpiece is separated, and the empty area detection region is a region that needs to be detected whether there is a workpiece, which is located inside the pressing position and is not greater than the blank area of the pressing position. According to the inner contour point cloud, the server can perform three-dimensional template matching and scaling processing on the inner contour point cloud, and then obtain the pose of the waste point cloud of the steel plate waste outside the pressing position and the pose of the empty area detection region point cloud inside the pressing position, wherein the pose of the waste point cloud represents the first thickness of the steel plate, and the pose of the empty area detection region point cloud represents the second thickness of the empty area detection region.

[0088] 103. If it is determined that the thickness difference between the pose of the empty area detection region point cloud and the pose of the waste point cloud is less than a preset threshold, it is determined that there is a workpiece inside the pressing position, and the empty area is not empty.

[0089] Exemplarily, the waste point cloud and the empty area detection region point cloud are located on the plane where the steel plate is located. Taking the plane where the steel plate is located as the bottom surface and the direction perpendicular to the plane where the steel plate is located as the thickness direction, the first thickness of the plate at the steel plate waste can be determined according to the waste point cloud, and the second thickness of the detection region inside the pressing position of the steel plate can be determined according to the empty area detection region point cloud. The server compares the pose of the empty area detection region point cloud with the pose of the waste point cloud. If it is determined that the thickness difference between the pose of the empty area detection region point cloud and the pose of the waste point cloud is less than a preset threshold, i.e., the thickness difference between the first thickness and the second thickness is less than a preset threshold, it is indicated that the empty area detection region is not empty and there is a workpiece with a certain thickness inside the empty area detection region. Therefore, it is determined that there is a workpiece inside the pressing position, and it is further determined that the empty area inside the pressing position is not empty.

[0090] In the embodiment of the present application, the inner contour point cloud where the pressing position on the steel plate is located is extracted; wherein the pressing position is the position of the steel plate where the workpiece is separated and manufactured. According to the inner contour point cloud, the pose of the waste point cloud of the waste material outside the pressing position and the pose of the empty material detection area point cloud inside the pressing position are obtained. If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud is less than a preset threshold, it is determined that there is a workpiece inside the pressing position and the empty material. In the present scheme, the inner contour point cloud where the pressing position on the steel plate is located is extracted, wherein the periphery of the pressing position is the waste material of the steel plate, and the inner part of the pressing position contains the empty material detection area. According to the inner contour point cloud, the pose of the waste point cloud of the waste material outside the pressing position and the pose of the empty material detection area point cloud inside the pressing position are determined, and the empty material detection area point cloud is the point cloud corresponding to the empty material detection area. The pose of the empty material detection area point cloud is compared with the pose of the waste point cloud, and if it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud is less than a preset threshold, it is determined that there is a workpiece inside the pressing position, and it is further determined that the pressing position is not empty. Therefore, whether there is a workpiece inside the pressing position can be determined according to the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud, which avoids continuing to suck the workpiece in the empty material condition, thereby reducing the invalid suction operation and solving the technical problem of low efficiency of sucking the workpiece.

[0091] Figure 2 The flowchart of another empty material processing method provided by the embodiment of the present application is shown in FIG. 2, and the method comprises the following steps. Figure 2

[0092] 201. Extracting the inner contour point cloud where the pressing position on the steel plate is located; wherein the pressing position is the position of the steel plate where the workpiece is separated and manufactured.

[0093] Exemplarily, the present step can refer to step 101 in the embodiment of the present application, and will not be described herein again. Figure 1

[0094] 202. Performing three-dimensional template matching on the inner contour point cloud to obtain the target workpiece template point cloud corresponding to the inner contour point cloud.

[0095] In one example, according to the preset mapping relationship between the inner contour point cloud and the workpiece contour template point cloud, the target workpiece contour template point cloud corresponding to the inner contour point cloud is determined; and according to the preset mapping relationship between the workpiece contour template point cloud and the workpiece template point cloud, the target workpiece template point cloud corresponding to the target workpiece contour template point cloud is determined.

[0096] ​​Exemplarily, the workpieces have multiple types, and the workpieces of each type have different shapes. The workpiece contour template point cloud represents a standard point cloud of a contour of the workpiece, for example, the workpiece contour template point cloud is determined according to the shape of the workpiece, and the standard point cloud of the contour of the workpiece is determined according to the inner contour point cloud, wherein the shape of the workpiece is obtained according to the inner contour point cloud. The workpiece template point cloud represents a standard point cloud located within the contour of the workpiece, that is, a standard point cloud of the workpiece, for example, the workpiece template point cloud is determined according to the point cloud of the contour of the workpiece, and the standard point cloud located within the contour of the workpiece is determined.

[0097] In this step, according to a preset mapping relationship between the inner contour point cloud and the workpiece contour template point cloud, a target workpiece contour template point cloud corresponding to the inner contour point cloud is determined, that is, a target workpiece contour template point cloud corresponding to the shape of the inner contour point cloud is determined. Since each workpiece contour template point cloud has a corresponding workpiece template point cloud pre-stored, according to a preset mapping relationship between the workpiece contour template point cloud and the workpiece template point cloud, a target workpiece template point cloud corresponding to the target workpiece contour template point cloud is determined.

[0098] 203. Obtain a workpiece two-dimensional image corresponding to the target workpiece template point cloud.

[0099] Exemplarily, the server can obtain a workpiece two-dimensional image corresponding to the target workpiece template point cloud.

[0100] 204. Perform dilation processing on the workpiece two-dimensional image according to preset inflation rule information to obtain a pose of the waste point cloud of the steel plate waste material around the pressing position; wherein the preset inflation rule information is used to indicate that the workpiece two-dimensional image is processed by inflation according to a preset inflation coefficient.

[0101] In one example, the workpiece two-dimensional image is processed by inflation to obtain an inflation image of the workpiece two-dimensional image; and the pose of the waste point cloud of the steel plate waste material around the pressing position is obtained according to the workpiece two-dimensional image and the inflation image.

[0102] In one example, the workpiece two-dimensional image is processed by inflation to obtain an inflation image of the workpiece two-dimensional image, including: according to a first inflation coefficient and a second inflation coefficient in the preset inflation rule information, the workpiece two-dimensional image is processed by inflation respectively to obtain a first inflation image corresponding to the first inflation coefficient and a second inflation image corresponding to the second inflation coefficient.

[0103] In one example, “obtaining the pose of the scrap point cloud of the steel plate scrap around the pressing position based on the two-dimensional image of the workpiece and the dilatation image” includes: overlapping the first dilatation image with the two-dimensional image of the workpiece with the center as the reference, and determining the first non-overlapping region image between the first dilatation image and the two-dimensional image of the workpiece; overlapping the second dilatation image with the two-dimensional image of the workpiece with the center as the reference, and determining the second non-overlapping region image between the second dilatation image and the two-dimensional image of the workpiece; overlapping the first non-overlapping region image and the second non-overlapping region image with the center as the reference, and obtaining the third non-overlapping region image between the first non-overlapping region image and the second non-overlapping region image; mapping to obtain the scrap point cloud corresponding to the third non-overlapping region image, and determining the pose of the scrap point cloud.

[0104] For example, Figure 3 A flowchart illustrating another empty material handling method provided in this application embodiment is shown below. Figure 3 As shown, the image includes: steel plate scrap, pressing position, two-dimensional image of the workpiece, inner contour represented by inner contour point cloud, first dilated image, second dilated image, first non-overlapping region image, second non-overlapping region image, and third non-overlapping region image. To ensure the accuracy of the empty material judgment method, it is necessary to determine the scrap point cloud of the steel plate scrap far from the pressing position. Therefore, it is necessary to dilate the two-dimensional image of the workpiece to obtain a dilated image of the two-dimensional image of the workpiece. Specifically, according to the first dilation coefficient and the second dilation coefficient in the preset dilation rule information, the two-dimensional image of the workpiece is dilated to obtain the first dilated image corresponding to the first dilation coefficient and the second dilated image corresponding to the second dilation coefficient.

[0105] Then, the first expanded image is overlapped with the workpiece two-dimensional image based on the center, the area of the first expanded image is greater than the area of the workpiece two-dimensional image, the overlapping area image between the first expanded image and the workpiece two-dimensional image is the workpiece two-dimensional image, and the non-overlapping area image between the first expanded image and the workpiece two-dimensional image is the first area other than the workpiece two-dimensional image. At this time, the first area other than the workpiece two-dimensional image is determined as the first non-overlapping area image between the first expanded image and the workpiece two-dimensional image. The second expanded image is overlapped with the workpiece two-dimensional image based on the center, the overlapping area image between the second expanded image and the workpiece two-dimensional image is the workpiece two-dimensional image, and the non-overlapping area image between the second expanded image and the workpiece two-dimensional image is the second area other than the workpiece two-dimensional image. At this time, the second area other than the workpiece two-dimensional image is determined as the second non-overlapping area image between the second expanded image and the workpiece two-dimensional image. Finally, the first non-overlapping area image and the second non-overlapping area image are overlapped based on the center, the third non-overlapping area image between the first non-overlapping area image and the second non-overlapping area image is obtained, the waste point cloud corresponding to the third non-overlapping area image is mapped and obtained, and the pose of the waste point cloud is determined. The waste point cloud corresponding to the third non-overlapping area image is the waste point cloud of the waste steel plate far away from the pressing position.

[0106] It should be noted that the number of times of the expansion processing of the workpiece two-dimensional image is related to the accuracy of the empty material judgment method. The accuracy of the waste point cloud obtained by the twice expansion processing is relatively high, but is not limited to the twice expansion processing. The workpiece two-dimensional image can be subjected to once expansion processing, and the like. If the workpiece two-dimensional image is subjected to once expansion processing, the workpiece two-dimensional image is subjected to expansion processing according to a third expansion coefficient to obtain a third expanded image corresponding to the third expansion coefficient. The third expanded image is overlapped with the workpiece two-dimensional image based on the center, and the third non-overlapping area image between the third expanded image and the workpiece two-dimensional image is determined.

[0107] 205、According to the preset reduction rule information, the workpiece two-dimensional image is subjected to reduction processing to obtain the pose of the empty material detection area point cloud in the pressing position; wherein the preset reduction rule information is used to indicate that the workpiece two-dimensional image is subjected to reduction processing according to a preset erosion coefficient.

[0108] In one example, according to the erosion coefficient in the preset reduction rule information, the workpiece two-dimensional image is subjected to reduction processing to obtain a reduction image corresponding to the erosion coefficient; the empty material detection area point cloud of the pressing position corresponding to the reduction image is mapped and obtained, and the pose of the empty material detection area point cloud is determined.

[0109] Exemplarily, Figure 4 Another empty material processing method provided by the embodiment of the present application is shown in the flowchart. Figure 4As shown, the method comprises: reducing the image. The preset reduction rule information is used to indicate that the workpiece two-dimensional image is reduced according to a preset corrosion coefficient, and the corrosion coefficient can be set by the user. According to the corrosion coefficient in the preset reduction rule information, the server reduces the workpiece two-dimensional image to obtain a reduced image corresponding to the corrosion coefficient, maps to obtain an empty material detection area point cloud corresponding to the reduced image, the empty material detection area point cloud is a point cloud of an empty material detection area, and a pose of the empty material detection area point cloud is determined.

[0110] 206、If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is less than the preset threshold, it is determined that there is a workpiece in the pressing position and no empty material.

[0111] For example, this step can refer to step 103 in the method 1000, and will not be described again. Figure 1

[0112] 207、If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is greater than or equal to the preset threshold, the server performs image recognition on the workpiece two-dimensional image according to a preset neural network model to obtain a recognition result; wherein the preset neural network model is trained according to images containing workpieces and images not containing workpieces.

[0113] For example, the preset neural network model is trained according to images containing workpieces and images not containing workpieces. Since the images containing workpieces contain workpiece colors and the images not containing workpieces contain only waste material colors, the neural network model can identify whether the workpiece two-dimensional image contains waste material colors, and further determine whether the pressing position is empty. If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is greater than or equal to the preset threshold, it is determined that there is no workpiece in the pressing position and the pressing position is empty. In order to ensure the accuracy of the empty material judgment result, the server can further perform image recognition on the workpiece two-dimensional image according to the preset neural network model to obtain a recognition result.

[0114] 208、If it is determined that the color of the recognition result is a preset waste material color, it is determined that there is no workpiece in the pressing position.

[0115] For example, the server can compare the color of the recognition result with the preset waste material color. If it is determined that the color of the recognition result is the preset waste material color, it is determined that there is no workpiece in the pressing position. If it is determined that the color of the recognition result is a preset workpiece color, it is determined that there is a workpiece in the pressing position.

[0116] 209、Skip the pressing position without workpiece, and obtain the next inner contour point cloud.

[0117] ​Exemplarily, the server can skip the pressing position where the workpiece does not exist, and obtain the next inner contour point cloud, and determine whether the pressing position at the next inner contour point cloud is empty.

[0118] In the embodiment of the application, an inner contour point cloud where a pressing position is located on a steel plate is extracted, wherein the pressing position is a position on the steel plate for separating and manufacturing a workpiece. Three-dimensional template matching is performed on the inner contour point cloud to obtain a target workpiece template point cloud corresponding to the inner contour point cloud. A workpiece two-dimensional image corresponding to the target workpiece template point cloud is mapped and obtained. According to preset inflation rule information, inflation processing is performed on the workpiece two-dimensional image to obtain a pose of a waste material point cloud of waste material outside the pressing position; wherein the preset inflation rule information is used to indicate that inflation processing is performed on the workpiece two-dimensional image according to a preset inflation coefficient. According to preset reduction rule information, reduction processing is performed on the workpiece two-dimensional image to obtain a pose of an empty material detection area point cloud inside the pressing position; wherein the preset reduction rule information is used to indicate that reduction processing is performed on the workpiece two-dimensional image according to a preset erosion coefficient. If it is determined that a thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is less than a preset threshold, it is determined that there is a workpiece in the pressing position and the pressing position is not empty. If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is greater than or equal to the preset threshold, image recognition is performed on the workpiece two-dimensional image according to a preset neural network model to obtain a recognition result; wherein the preset neural network model is obtained by training images containing workpieces and images not containing workpieces. If it is determined that the color of the recognition result is a preset waste material color, it is determined that there is no workpiece in the pressing position. The pressing position where the workpiece does not exist is skipped, and the next inner contour point cloud is obtained. Therefore, whether there is a workpiece in the pressing position can be determined according to the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud, which avoids continuing to suck the workpiece in the empty material case, thereby reducing the invalid suction operation and solving the technical problem of low efficiency of sucking the workpiece.

[0119] Figure 5 A structural schematic diagram of a empty material processing device provided by the embodiment of the application is shown in FIG. 1. Figure 5 As shown in FIG. 1, the device comprises:

[0120] The extraction unit 31 is configured to extract an inner contour point cloud where a pressing position is located on a steel plate; wherein the pressing position is a position on the steel plate for separating and manufacturing a workpiece.

[0121] The acquisition unit 32 is configured to obtain a pose of a waste material point cloud of waste material outside the pressing position and a pose of an empty material detection area point cloud inside the pressing position according to the inner contour point cloud.

[0122] The first determination unit 33 is configured to determine that the workpiece exists in the pressing position and the empty material does not exist if it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is less than a preset threshold.

[0123] The device of the embodiment can execute the technical solutions in the above method, and the specific implementation process and technical principles are the same, which will not be described here.

[0124] Figure 6 Another empty material processing device structure schematic diagram provided by the embodiment of the application is shown in Figure 5 Based on the embodiment shown in Figure 6 The acquisition unit 32 comprises:

[0125] The matching module 321 is configured to perform three-dimensional template matching on the inner contour point cloud to obtain a target workpiece template point cloud corresponding to the inner contour point cloud.

[0126] The mapping module 322 is configured to map a workpiece two-dimensional image corresponding to the target workpiece template point cloud.

[0127] The expansion module 323 is configured to perform expansion processing on the workpiece two-dimensional image according to preset expansion rule information to obtain a pose of waste material point cloud of the peripheral steel plate waste material in the pressing position; wherein the preset expansion rule information is used to indicate that the workpiece two-dimensional image is expanded according to a preset expansion coefficient.

[0128] The reduction module 324 is configured to perform reduction processing on the workpiece two-dimensional image according to preset reduction rule information to obtain a pose of the empty material detection area point cloud in the pressing position; wherein the preset reduction rule information is used to indicate that the workpiece two-dimensional image is reduced according to a preset corrosion coefficient.

[0129] In one example, the matching module 321 comprises:

[0130] The first determination sub-module 3211 is configured to determine a target workpiece contour template point cloud corresponding to the inner contour point cloud according to a preset mapping relationship between the inner contour point cloud and the workpiece contour template point cloud.

[0131] The second determination sub-module 3212 is configured to determine a target workpiece template point cloud corresponding to the target workpiece contour template point cloud according to a preset mapping relationship between the workpiece contour template point cloud and the workpiece template point cloud.

[0132] In one example, the expansion module 323 comprises:

[0133] The first determination sub-module 3231 is configured to perform expansion processing on the workpiece two-dimensional image to obtain an expansion image of the workpiece two-dimensional image.

[0134] The second determining sub-module 3232 is configured to obtain the pose of the scrap point cloud of the peripheral steel plate scrap of the pressing position according to the workpiece two-dimensional image and the expanded image.

[0135] In one example, the first determining sub-module 3231 is specifically configured to:

[0136] The workpiece two-dimensional image is expanded according to the first expansion coefficient and the second expansion coefficient in the preset expansion rule information, to obtain the first expanded image corresponding to the first expansion coefficient and the second expanded image corresponding to the second expansion coefficient.

[0137] The second determining sub-module 3232 includes:

[0138] The third determining sub-module 32321 is configured to overlap the first expanded image and the workpiece two-dimensional image with the center as the reference, and determine the first non-overlapping area image between the first expanded image and the workpiece two-dimensional image.

[0139] The fourth determining sub-module 32322 is configured to overlap the second expanded image and the workpiece two-dimensional image with the center as the reference, and determine the second non-overlapping area image between the second expanded image and the workpiece two-dimensional image.

[0140] The fifth determining sub-module 32323 is configured to overlap the first non-overlapping area image and the second non-overlapping area image with the center as the reference, and obtain the third non-overlapping area image between the first non-overlapping area image and the second non-overlapping area image.

[0141] The sixth determining sub-module 32324 is configured to map and obtain the scrap point cloud corresponding to the third non-overlapping area image, and determine the pose of the scrap point cloud.

[0142] In one example, the reducing module 324 includes:

[0143] The seventh determining sub-module 3241 is configured to reduce the workpiece two-dimensional image according to the corrosion coefficient in the preset reducing rule information, to obtain the reduced image corresponding to the corrosion coefficient.

[0144] The eighth determining sub-module 3242 is configured to map and obtain the empty material detection area point cloud of the pressing position corresponding to the reduced image, and determine the pose of the empty material detection area point cloud.

[0145] In one example, the device further includes:

[0146] The recognition unit 41 is configured to perform image recognition on the workpiece two-dimensional image according to a preset neural network model to obtain a recognition result, if it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is greater than or equal to a preset threshold.

[0147] The second determination unit 42 is configured to determine that there is no workpiece in the material pressing position, if it is determined that the color of the recognition result is a preset waste material color.

[0148] In one example, the device further includes:

[0149] The skipping unit 43 is configured to skip the material pressing position in which there is no workpiece, and acquire a next inner contour point cloud.

[0150] The device of the embodiment can execute the technical solutions in the above method, and the specific implementation process and technical principles are the same, which will not be repeated here.

[0151] Figure 7 A structural diagram of a server provided by an embodiment of the present application is shown in FIG. 1, which includes a memory 51 and a processor 52. Figure 7

[0152] The memory 51 stores a computer program that can run on the processor 52.

[0153] The processor 52 is configured to execute the method provided by the above embodiment.

[0154] The server further includes a receiver 53 and a transmitter 54. The receiver 53 is configured to receive instructions and data sent by an external device, and the transmitter 54 is configured to send instructions and data to the external device.

[0155] An embodiment of the present application further provides a non-transitory computer-readable storage medium, when instructions in the storage medium are executed by a processor of a server, the server can execute the method provided by the above embodiment.

[0156] An embodiment of the present application further provides a computer program product, which includes a computer program stored in a readable storage medium, at least one processor of a server can read the computer program from the readable storage medium, and the at least one processor executes the computer program to make the server execute the scheme provided by any of the above embodiments.

[0157] ​Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the features disclosed herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

[0158] It should be understood that the present disclosure is not limited to the precise structures as herein described and illustrated in the drawings, and that various modifications and changes can be made without departing from its scope. The scope of the present disclosure is limited only by the claims that follow.

Claims

1. A scrap handling method, characterized by, The method comprises the following steps: extracting an inner contour point cloud of a pressing position on a steel plate; wherein the pressing position is a position of the steel plate for separating a workpiece; obtaining a pose of a waste point cloud of the waste material outside the pressing position and a pose of an empty material detection area point cloud inside the pressing position according to the inner contour point cloud; if it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste point cloud is less than a preset threshold, it is determined that the workpiece exists in the pressing position and the material is not empty; the method further comprises the following steps: performing three-dimensional template matching on the inner contour point cloud to obtain a target workpiece template point cloud corresponding to the inner contour point cloud; mapping to obtain a workpiece two-dimensional image corresponding to the target workpiece template point cloud; performing inflation processing on the workpiece two-dimensional image according to preset inflation rule information to obtain the pose of the waste point cloud of the waste material outside the pressing position; wherein the preset inflation rule information is used to indicate that the workpiece two-dimensional image is processed according to a preset inflation coefficient; performing reduction processing on the workpiece two-dimensional image according to preset reduction rule information to obtain the pose of the empty material detection area point cloud inside the pressing position; wherein the preset reduction rule information is used to indicate that the workpiece two-dimensional image is processed according to a preset erosion coefficient.

2. The method of claim 1, wherein, the method further comprises the following steps: determining a target workpiece contour template point cloud corresponding to the inner contour point cloud according to a preset mapping relationship between the inner contour point cloud and the workpiece contour template point cloud; determining a target workpiece template point cloud corresponding to the target workpiece contour template point cloud according to a preset mapping relationship between the workpiece contour template point cloud and the workpiece template point cloud.

3. The method of claim 1, wherein, the method further comprises the following steps: performing inflation processing on the workpiece two-dimensional image to obtain an inflation image of the workpiece two-dimensional image; obtaining the pose of the waste point cloud of the waste material outside the pressing position according to the workpiece two-dimensional image and the inflation image.

4. The method of claim 3, wherein the method further comprises the following steps: performing inflation processing on the workpiece two-dimensional image according to a first inflation coefficient and a second inflation coefficient in the preset inflation rule information to obtain a first inflation image corresponding to the first inflation coefficient and a second inflation image corresponding to the second inflation coefficient; the method further comprises the following steps: overlapping the first inflation image and the workpiece two-dimensional image with the center as the reference, and determining a first non-overlapping area image between the first inflation image and the workpiece two-dimensional image; overlap the second expanded image and the workpiece two-dimensional image based on the center, and determine a second non-coincidence area image between the second expanded image and the workpiece two-dimensional image; overlap the first non-coincidence area image and the second non-coincidence area image based on the center, and obtain a third non-coincidence area image between the first non-coincidence area image and the second non-coincidence area image; map obtain a waste material point cloud corresponding to the third non-coincidence area image, and determine a pose of the waste material point cloud.

5. The method of claim 1, wherein, The method further comprises: According to the corrosion coefficient in the preset reduction rule information, the workpiece two-dimensional image is reduced to obtain a reduced image corresponding to the corrosion coefficient; map obtain a waste material point cloud corresponding to the third non-coincidence area image, and determine a pose of the waste material point cloud.

6. The method according to any one of claims 1 to 5, characterized in that, The method further comprises: If it is determined that the thickness difference between the pose of the empty material detection area point cloud and the pose of the waste material point cloud is greater than or equal to a preset threshold, the workpiece two-dimensional image is subjected to image recognition according to a preset neural network model to obtain a recognition result; wherein the preset neural network model is trained according to images containing workpieces and images not containing workpieces; If it is determined that the color of the recognition result is a preset waste material color, it is determined that there is no workpiece in the pressing position.

7. The method of claim 6, wherein, The method further comprises: Skip the pressing position where the workpiece does not exist, and obtain the next inner contour point cloud.

8. A server, characterized by The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the method of any one of claims 1-7.

9. A computer-readable storage medium, characterized in that, The computer readable storage medium stores computer execution instructions, and the computer execution instructions are executed by the processor to implement the method of any one of claims 1-7.

Images