Material sorting method, material sorting device, material sorting equipment and storage medium

Abstract

The present disclosure relates to the field of material sorting, and specifically to a material sorting method, a material sorting device, a material sorting equipment and a storage medium. The material sorting method is applied to the material sorting equipment, and the method includes: performing fixed-point scanning through a ray scanning device to obtain a ray projection image of the material; performing a first processing on the ray projection image to determine the plane contour information of the material; collecting point cloud data of the material during the transmission process from above the material through a laser radar; matching the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data; determining the target center of gravity position of the material based on the target point cloud data; and sorting the material according to the target center of gravity position through a sorting device. The error that may be caused by a single scanning method can be reduced, and the accuracy of determining the target center of gravity position can be improved, thereby reducing the material processing time and improving the sorting efficiency.

Description

Technical Field

[0001] The present invention relates to the field of material sorting, and in particular to a material sorting method, a material sorting device, a material sorting equipment and a computer-readable storage medium. Background Art

[0002] In the field of material sorting, a typical sorting process is composed of a transmission device, X-ray scanning equipment and an advanced sorting system. In this process, the material is sent into the X-ray scanning area under the action of the transmission device. At this time, the X-ray scanning technology accurately captures the category information and precise location information of the material, and transmits this information to the classification system in real time. After receiving this information, the classification system performs corresponding sorting operations on the material.

[0003] However, there is a technical challenge in this process: since the X-ray source uses a point emission method to scan the material, there is a certain deviation between the material projection profile formed on the X-ray detector and its actual position, and this deviation may affect the accuracy and overall efficiency of sorting. Summary of the invention

[0004] In order to overcome the problems existing in the related art, an exemplary embodiment of the present disclosure provides a material sorting method, which is applied to material sorting equipment. The material sorting equipment includes a ray scanning device, a laser radar, and a sorting device. The method includes: performing fixed-point scanning through the ray scanning device to obtain a ray projection image of the material; performing a first processing on the ray projection image to determine the plane contour information of the material; collecting point cloud data of the material during the transmission process from above the material through the laser radar; matching the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data; determining the target center of gravity position of the material based on the target point cloud data; and sorting the material according to the target center of gravity position through the sorting device.

[0005] In some embodiments, the ray scanning device includes a fixed-point ray source, which matches the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data, including: based on the position of the fixed-point ray source and the height information of each point data in the point cloud data, respectively determining the ray projection point position corresponding to each point data; according to the plane contour information, determining the ray projection range corresponding to the material; based on the matching results of multiple ray projection point positions and ray projection ranges, determining the target point cloud data corresponding to the material in the point cloud data.

[0006] In some embodiments, the target point cloud data includes multiple target point data, and based on the matching results of multiple ray projection point positions and ray projection ranges, the target point cloud data corresponding to the material in the point cloud data is determined, including: matching the ray projection point position with the ray projection range to obtain a matching result; if the matching result indicates that the ray projection point position is within the ray projection range, then determining that the point data corresponding to the ray projection point position is the target point data corresponding to the material.

[0007] In some embodiments, based on the matching results of multiple ray projection point positions and ray projection ranges, the target point cloud data corresponding to the material in the point cloud data is determined, and it also includes: if the matching result indicates that the ray projection point position is outside the ray projection range, it is determined that the point data corresponding to the ray projection point position is not the target point data corresponding to the material.

[0008] In some embodiments, determining the target center of gravity position of the material based on the target point cloud data includes: determining the shape information of the material according to the coordinate position information of each target point data in the target point cloud data; and determining the target center of gravity position of the material based on the shape information.

[0009] In some embodiments, the target center of gravity position of the material is determined based on the shape information, including: determining the three-dimensional contour information of the material based on the height information of each target point data in the target point cloud data; determining the target center of gravity position of the material based on the shape information and the three-dimensional contour information.

[0010] In some embodiments, the sorting device includes multiple sorting mechanisms opposite to the material transmission direction, and the materials are sorted according to the target center of gravity position by the sorting device, including: based on the target center of gravity position, determining the target sorting mechanism and the target execution timing for the target sorting mechanism to perform sorting from multiple sorting mechanisms; according to the target execution timing, sorting the materials by the target sorting mechanism.

[0011] In some embodiments, the method further includes: performing a second processing on the ray projection image to determine the category information of the material; if the category of the material is determined to be a category to be sorted through the category information, executing the step of matching the point cloud data with the plane contour information.

[0012] In the second aspect, the present disclosure also provides a material sorting device, which is applied to material sorting equipment. The material sorting equipment includes a ray scanning device, a laser radar, and a sorting device. The device includes: an acquisition module, which is used to perform fixed-point scanning through the ray scanning device to obtain a ray projection image of the material; a first processing module, which is used to perform a first processing on the ray projection image to determine the plane contour information of the material; a data acquisition module, which is used to collect point cloud data of the material during transmission from above the material through a laser radar; a matching module, which is used to match the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data; a second processing module, which is used to determine the target center of gravity position of the material based on the target point cloud data; and a third processing module, which is used to sort the material according to the target center of gravity position through the sorting device.

[0013] In the third aspect, the present disclosure also provides a material sorting device, including: a transmission device, used to transmit materials; a ray scanning device, used to perform fixed-point scanning on the transmission device to determine the ray projection image of the material; a laser radar, used to collect point cloud data of the material during the transmission process; a processor, respectively connected to the ray scanning device and the laser radar, the processor is used to perform a first processing on the ray projection image to determine the plane contour information of the material; match the point cloud data with the plane contour information, determine the target point cloud data corresponding to the material in the point cloud data, determine the target center of gravity position of the material based on the target point cloud data, and send the target center of gravity position to the sorting device; the sorting device is arranged downstream of the transmission device, and is used to sort the material according to the target center of gravity position.

[0014] In a fourth aspect, the present disclosure further provides a computer-readable storage medium, which stores the following program, and the program is used to execute the material sorting method provided in any of the above aspects.

[0015] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the present disclosure.

[0016] The technical solution provided by the embodiments of the present disclosure may include the following beneficial effects: According to the material sorting method provided by the present disclosure, through the combination of ray scanning and laser radar, the geometric shape and position information of the material can be obtained more accurately, thereby improving the accuracy of sorting. The point cloud data collected by the laser radar can monitor the position and shape changes of the material in real time, which in turn helps to dynamically adjust the sorting strategy to make the sorting process more targeted and widely applicable. In addition, based on the matching results of the point cloud data and the material plane contour information, the target point cloud data of the material is determined, which can reduce the error that may be caused by a single scanning method, and then the target center of gravity position is determined based on the target point cloud data, which can improve the accuracy of determining the target center of gravity position, so that when the material is sorted by the sorting device, the material processing time can be reduced and the sorting efficiency can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The present invention may be better understood by describing exemplary embodiments of the present invention in conjunction with the accompanying drawings, in which:

[0018] Figure 1 It is a structural schematic diagram of a material sorting device shown in an exemplary embodiment of the present disclosure;

[0019] Figure 2 A schematic diagram of a material sorting method according to an exemplary embodiment of the present disclosure;

[0020] Figure 3 A top view of point cloud data shown in an exemplary embodiment of the present disclosure;

[0021] Figure 4 A schematic flow chart of another material sorting method shown in an exemplary embodiment of the present disclosure;

[0022] Figure 5 A schematic diagram of plane profile information shown in an exemplary embodiment of the present disclosure;

[0023] Figure 6 A schematic diagram of the principle of ray projection shown in an exemplary embodiment of the present disclosure;

[0024] Figure 7 A schematic flow chart of another material sorting method according to an exemplary embodiment of the present disclosure;

[0025] Figure 8 This is a schematic flow chart of another material sorting method shown in an exemplary embodiment of the present disclosure;

[0026] Fig. 9 A schematic flow chart of a material sorting method according to another exemplary embodiment of the present disclosure;

[0027] Fig.10 It is a structural schematic diagram of another material sorting equipment shown in an exemplary embodiment of the present disclosure;

[0028] Fig.11 It is a structural schematic diagram of another material sorting equipment shown in an exemplary embodiment of the present disclosure;

[0029] Fig.12 It is a schematic structural diagram of another material sorting equipment shown as an exemplary embodiment of the present disclosure. DETAILED DESCRIPTION

[0030] The specific embodiments of the present invention will be described below. It should be noted that in the specific description of these embodiments, in order to provide a concise description, it is impossible for this specification to provide a detailed description of all the features of the actual embodiments. It should be understood that in the actual implementation of any embodiment, just as in the process of any engineering project or design project, in order to achieve the specific goals of the developer and to meet system-related or business-related restrictions, various specific decisions are often made, and this will also change from one embodiment to another. In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, for ordinary technicians in the field related to the content disclosed by the present invention, some changes such as design, manufacturing or production based on the technical content disclosed in this disclosure are just conventional technical means, and should not be understood as insufficient content of this disclosure.

[0031] Unless otherwise defined, the technical terms or scientific terms used in the present disclosure shall have the usual meanings understood by persons with ordinary skills in the technical field to which the present invention belongs. The words "first", "second" and similar words used in the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. Words such as "one" or "one" and the like do not indicate a quantity limitation, but rather indicate the presence of at least one. Words such as "include" or "comprise" and the like mean that the elements or objects appearing before "include" or "comprise" cover the elements or objects listed after "include" or "comprise" and their equivalents, and do not exclude other elements or objects. Words such as "connect" or "connected" and the like are not limited to physical or mechanical connections, nor are they limited to direct or indirect connections.

[0032] In the field of material sorting, the relevant sorting process includes: the material is sent into the X-ray scanning area under the action of the transmission device. At this time, the X-ray scanning technology accurately captures the category information and precise location information of the material, and transmits this information to the classification system in real time. After receiving this information, the classification system performs corresponding sorting operations on the material.

[0033] However, there is a technical challenge in this process: since the X-ray source uses a point emission method to scan the material, there is a certain deviation between the material projection profile formed on the X-ray detector and its actual position, and this deviation may affect the accuracy and overall efficiency of sorting.

[0034] For example, if the material is ore, Figure 1 When the ore sorting equipment 100 shown is sorting ore, the relevant process can be as follows: in the process of transporting ore by the conveyor belt 110, the ore on the conveyor belt 110 can be scanned by the ray scanning device 120 to determine the category information and position information of the ore, and the category information and position information are sent to the sorting device 130, and then the sorting device 130 can perform targeted sorting operations on the ore so that the ore can fall into the corresponding drop device 140.

[0035] However, when the X-rays emitted by the fixed-point ray source 121 of the ray scanning device 120 scan the ore on the conveyor belt 110 and penetrate the ore at a certain angle, the projection contour corresponding to the ore formed on the ray detector 122 of the ray scanning device 120 cannot fully reflect the true shape and position of the ore. Although the center of gravity can be calculated based on the projection contour and the operation of the sorting device 130 can be guided accordingly, the center of gravity obtained by this method often deviates from the actual center of gravity of the ore. This deviation will directly affect the accuracy of the injection, so that the ore may not move along the predetermined trajectory, thereby reducing the sorting effect.

[0036] To solve the above problems, an exemplary embodiment of the present disclosure provides a material sorting method, which is applied to a material sorting device, wherein the material sorting device may include a ray scanning device, a laser radar, and a sorting device. Figure 2 As shown, the material sorting method may include:

[0037] Step S210, performing fixed-point scanning by a ray scanning device to obtain a ray projection image of the material.

[0038] The ray scanning device is a scanning device that can perform targeted detection on materials without destroying the materials. For example, the ray scanning device can be a device for emitting and receiving X-rays or gamma rays.

[0039] In order to facilitate the subsequent effective sorting of the currently transmitted materials, the ray scanning device uses a fixed-point scanning method to perform fixed-point scanning on the currently transmitted materials. When the ray passes through the material, due to the different internal structures and components of the material, the ray will be absorbed and scattered to varying degrees, and then a ray projection image of the material can be generated.

[0040] In order to understand the relevant property information of the material so that the material can be screened in a targeted manner later, the ray projection information of the material is obtained. The relevant property information may include but is not limited to the plane profile information, category information, density information, composition information, etc. of the material.

[0041] Step S220: performing a first processing on the ray projection image to determine the plane contour information of the material.

[0042] In order to improve the material sorting efficiency, the ray projection image is first processed to determine the contour of the material according to the obtained processing result, thereby obtaining the plane contour information of the material, so as to narrow the range of determining the location of the material.

[0043] The first processing may be edge detection processing, semantic segmentation processing, or other processing that can determine the contour of the material, which may be determined based on actual needs.

[0044] Step S230, collecting point cloud data of the material during the transmission process from above the material through a laser radar.

[0045] Since the plane profile information obtained by the ray scanning device may deviate from the actual position of the material, in order to improve the accuracy of position determination, the laser radar is used to scan from above the material to obtain point cloud data including the target point data corresponding to the material. Since the laser radar is arranged in a linear array, the distribution of the material can be clarified through the obtained point cloud data, so that the actual position of the material can be determined later. In one example, the top view of the point cloud data can be as follows Figure 3 shown.

[0046] Step S240, matching the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data.

[0047] The plane profile information is obtained by fixed-point scanning by a ray scanning device, which belongs to line scanning. Therefore, by scanning the material, the generated transverse ray projection may have deviations, while the accuracy of scanning in the material transmission direction is relatively high. Among them, the plane profile information belongs to two-dimensional information. Through the plane profile information, the key geometric features of the material can be determined.

[0048] Point cloud data is obtained by vertically scanning the material, and the density of the point cloud data can be used to determine the material's attribute information. The attribute information may include but is not limited to shape information, location information, and height information. Point cloud data is three-dimensional data. The spatial characteristics of the material can be determined through point cloud data.

[0049] Therefore, by matching the point cloud data with the plane contour information, the accuracy of the plane contour information in the material transmission direction can be combined to perform targeted screening on the point cloud data to determine which point data can characterize the material, thereby obtaining the target point cloud data corresponding to the material.

[0050] Step S250, determining the target center of gravity position of the material based on the target point cloud data.

[0051] By analyzing the target point cloud data, the actual target shape of the material can be determined, and the target center of gravity position of the material can be determined therefrom. The actual target shape of the material can be determined by calculating the statistical characteristics of the target point cloud data, for example, the statistical characteristics can include a minimum bounding box, a convex hull, a center of mass, etc.

[0052] Step S260, sorting materials according to the target center of gravity position by a sorting device.

[0053] The sorting device can clearly identify the location where the material needs to be sorted, and the center of gravity is a key factor in the balance of an object. Therefore, in order to enable the material to reach the designated drop area according to the preset trajectory, the sorting device is used to sort the material according to the target center of gravity position to reduce damage to the material during transportation and storage, so that the material can be stably transmitted during the sorting process, thereby improving the accuracy and reliability of the sorting.

[0054] According to the material sorting method provided by the present disclosure, through the combination of ray scanning and laser radar, the geometric shape and position information of the material can be obtained more accurately, thereby improving the accuracy of sorting. The point cloud data collected by the laser radar can monitor the position and shape changes of the material in real time, which in turn helps to dynamically adjust the sorting strategy to make the sorting process more targeted and widely applicable. In addition, based on the matching results of the point cloud data and the material plane contour information, the target point cloud data of the material is determined, which can reduce the errors that may be caused by a single scanning method, and then the target center of gravity position is determined based on the target point cloud data, which can improve the accuracy of determining the target center of gravity position, so that when the material is sorted by the sorting device, the material processing time can be reduced and the sorting efficiency can be improved.

[0055] In some embodiments, the radiation scanning device includes a fixed-point radiation source, such as Figure 4 As shown, the above step S240 may include the following steps:

[0056] Step S241 , based on the position of the fixed-point ray source and the height information of each point data in the point cloud data, respectively determine the ray projection point position corresponding to each point data.

[0057] Since the fixed-point ray source is fixed upstream in the material transmission direction and the material is at a certain height, the ray emitted by the fixed-point ray source will pass through the material at a certain angle and fall on the ray detector, and then the position of the ray projection point corresponding to each point data can be determined, which is convenient for clarifying the distribution of the position of each ray projection point. Among them, the position of the ray projection point can be determined based on the similarity principle of triangles or by a ray tracing algorithm.

[0058] Moreover, based on the height information of each point data in the point cloud data, it is also possible to preliminarily screen out which point data may be related to the material, thereby narrowing the determination scope of the target point cloud data.

[0059] Step S242, determining the ray projection range corresponding to the material according to the plane contour information.

[0060] According to the plane profile information, the distribution of the projection of the material as a whole onto the radiation detector can be determined, and then the ray projection range corresponding to the material can be obtained. Figure 5 As shown in FIG. 1 , when the position of the fixed-point radiation source is constant, the material is represented by a sphere. Then, the material is scanned by the radiation emitted by the fixed-point radiation source, and the plane profile information generated by the radiation detector can be as follows: Figure 5 As shown in the ellipse in the figure, the ray projection range corresponding to the material can be clearly determined through the plane contour information.

[0061] Step S243, based on the matching results of the positions of the multiple ray projection points and the ray projection ranges, determine the target point cloud data corresponding to the material in the point cloud data.

[0062] The ray projection point positions of each point data are matched with the ray projection range respectively, and then according to the obtained matching results, it can be determined which ray projection point positions are within the ray projection range or on the range boundary, and which ray projection point positions are outside the ray projection range boundary. For example, if the ray projection point position is within the ray projection range or on the range boundary, then the corresponding point data may be the point data corresponding to the material. If the ray projection point position is outside the ray projection range boundary, then the corresponding point data must not be the point data corresponding to the material. Therefore, through the matching results of multiple ray projection point positions and ray projection ranges, the validity of each point data can be targetedly screened to obtain the target point cloud data corresponding to the material in the point cloud data, thereby improving the reliability of the determination of the target point cloud data.

[0063] In some examples, the target point cloud data includes multiple target point data, and the above step S243 may include the following steps:

[0064] Step a1, matching the ray projection point position with the ray projection range to obtain a matching result;

[0065] Step a2: if the matching result indicates that the ray projection point position is within the ray projection range, it is determined that the point data corresponding to the ray projection point position is the target point data corresponding to the material.

[0066] Specifically, Figure 6 As shown in the figure, taking the position of the fixed-point ray source as O as an example, the projection of the ray emitted by the fixed-point ray source vertically falling on the ray detector is point O1. When the ray penetrates the material, the ray projection range falling on the ray detector is DE. The position of point D represents the nearest projection position boundary when the ray scans the material, and the position of point E represents the farthest projection position boundary when the ray scans the material.

[0067] Therefore, by matching the ray projection point position with the ray projection range, it is possible to determine whether the ray projection point position of which point data falls within the ray projection range DE. Take a point data A scanned by the laser radar as an example, and its corresponding ray projection point position A1. If the ray projection point position A1 is within or on the boundary of the ray projection range DE, it can be determined that the point data A is the laser radar scanning result corresponding to a certain position on the material. Therefore, the point data A can be determined to be the target point data corresponding to the material.

[0068] In some other examples, the above step S243 may also include the following steps:

[0069] Step a3: if the matching result indicates that the position of the ray projection point is outside the ray projection range, it is determined that the point data corresponding to the ray projection point position is not the target point data corresponding to the material.

[0070] If the ray projection point position A1 is outside the ray projection range DE, it can be determined that the point data A is not the laser radar scanning result corresponding to a certain position on the material. Therefore, it can be determined that the point data corresponding to the ray projection point position is not the target point data corresponding to the material.

[0071] By filtering the target point data based on the results of matching the ray projection point position with the ray projection range, the difficulty of identifying the target point cloud data can be reduced, the efficiency of determining the point data can be improved, and thus the efficiency of material sorting can be improved.

[0072] In some embodiments, Figure 7 As shown, the above step S250 may include the following steps:

[0073] Step S251, determining the shape information of the material according to the coordinate position information of each target point data in the target point cloud data.

[0074] According to the coordinate position information of each target point data in the target point cloud data, the actual contour of the material can be fitted in a targeted manner, thereby obtaining shape information that can characterize the material. The fitting methods used include but are not limited to: polygon fitting, surface fitting or feature curve extraction.

[0075] Step S252: Determine the target center of gravity position of the material based on the shape information.

[0076] According to the shape information, the force condition of the material can be determined. According to the target point data, the total number of target point data in the target point cloud data, and the weight of the material, the actual center of gravity position of the material can be estimated in a targeted manner, thereby obtaining the target center of gravity position of the material. Among them, if the weight of the material is known, a targeted estimation can be made directly to improve the accuracy of the determination of the target center of gravity position. If the weight of the material is unknown, the actual center of gravity position of the material can be estimated in a targeted manner based on the default weight, thereby improving the determination efficiency and ensuring that the material sorting process can proceed smoothly.

[0077] In some examples, the above step S252 may include the following steps:

[0078] Step b1, determining the three-dimensional contour information of the material according to the height information of each target point data in the target point cloud data;

[0079] Step b2, determining the target center of gravity position of the material based on the shape information and the three-dimensional contour information.

[0080] Specifically, according to the height information of each target point data in the target point cloud data, the height change of the material can be determined, and then the three-dimensional contour information of the material can be obtained by contour extraction. Among them, the algorithm for contour extraction may include but is not limited to contour extraction, edge detection or surface fitting.

[0081] Based on the obtained three-dimensional contour information, combined with the shape information of the material, the geometric characteristics of the material can be better understood, so as to obtain the target center of gravity position of the material. For example, if the quality or weight of each point data is known, the target center of gravity position can be determined by weighted average. If there is no quality information, the target center of gravity position can be determined directly based on the coordinates of each target point data and the total number of target point data.

[0082] In other examples, the process of determining the target center of gravity position based on the coordinates of each target point data and the total number of target point data can be as follows: sum the coordinates of all target point data respectively, and divide the sum result by the total number of points, and then determine the coordinates of the center of gravity of the material, so that the target center of gravity position of the material can be determined according to the coordinates of the center of gravity of the material. Determining the target center of gravity position in this way can improve the determination efficiency so that the candidate can sort the material in time.

[0083] In some embodiments, the sorting device includes a plurality of sorting mechanisms opposite to the material conveying direction, such as Figure 8 As shown, the above step S260 may include the following steps:

[0084] Step S261, based on the target center of gravity position, determine the target sorting mechanism and the target execution timing for the target sorting mechanism to perform sorting from multiple sorting mechanisms.

[0085] During the material transmission process, there may be multiple materials on the transmission device, and the positions of the materials are relatively random. Therefore, in order to ensure the reliability of sorting and facilitate the sorting device to perform sorting processing on the current material in a timely manner, the location of the material can be determined by the target center of gravity position, and then based on the operation status and position information of each sorting device, the most suitable sorting device can be selected as the target sorting mechanism for sorting the material.

[0086] After determining the target sorting mechanism, in order to ensure that the sorting of materials can be carried out in the best position and state, the target execution timing of the target sorting mechanism to perform sorting is determined based on the size of the materials, the current transmission conditions of the materials and the current position of the target sorting mechanism to maximize the sorting effect and efficiency.

[0087] Step S262, sorting materials through a target sorting mechanism according to the target execution timing.

[0088] When the current environmental conditions meet the target execution timing, the target sorting mechanism sorts the materials so that the sorted materials can enter the corresponding drop device. The sorting device can be a blowing device or a pushing device. If the sorting device is a blowing device, the materials can be sorted by blowing the target center of gravity. If the sorting device is a pushing device, the materials can be sorted by hitting the target center of gravity.

[0089] In some examples, when the materials transmitted by the material sorting equipment need to be sorted into multiple materials, the sorting parameters of the target sorting mechanism can also be adjusted based on the category information of the materials so that the materials can accurately fall into the drop device corresponding to their category information, thereby improving the reliability and efficiency of material sorting. For example, if the sorting device is a blowing device, the sorting parameter can be the injection speed and / or injection pressure of the fluid. If the sorting device is a pushing device, the sorting parameter can be the thrust of the push plate.

[0090] In some embodiments, the present disclosure also provides another material sorting method, such as Fig. 9 As shown, the material sorting method comprises the following steps:

[0091] Step S310, performing fixed-point scanning by a ray scanning device to obtain a ray projection image of the material.

[0092] Step S320: performing a first processing on the ray projection image to determine the plane contour information of the material.

[0093] Step S330: performing a second process on the ray projection image to determine the category information of the material.

[0094] By performing a second processing on the ray projection image, the characteristic information of the material can be clarified. The characteristic information may include but is not limited to: shape, size, texture, etc. Based on the result of the classification detection of the characteristic information, the specific category information of the material is determined.

[0095] The classification detection process may be performed by a classification algorithm, a classifier or other methods. The classification algorithm may be a rule-based algorithm, such as a decision tree, a support vector machine, etc. The classification algorithm may also be an algorithm based on template matching, such as classification by identifying a specific shape. The classification algorithm may also be an algorithm based on deep learning, such as a convolutional neural network (CNN), a recurrent neural network (RNN), etc. The classifier may be trained based on a semi-supervised or unsupervised learning method.

[0096] Step S340, collecting point cloud data of the material during the transmission process from above the material through a laser radar.

[0097] Step S350: If the category of the material is determined to be a to-be-sorted category through the category information, the point cloud data is matched with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data.

[0098] If the category of the material is determined to be the category to be sorted through the category information, it is characterized that the material is the required material. Therefore, the obtained point cloud data is matched with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data, so as to locate the target center of gravity position of the material based on the obtained target point cloud data. For example, taking the material as ore, the category to be sorted is concentrate. If the category of the material is determined to be concentrate through the category information, the point cloud data is matched with the plane contour information to determine the target center of gravity position of the material, and then targeted screening is performed later.

[0099] Step S360, determining the target center of gravity position of the material based on the target point cloud data.

[0100] Step S370, sorting materials according to the target center of gravity position by using a sorting device.

[0101] According to the material sorting method provided by the present disclosure, when the category of the material is determined to be the category to be sorted, the target point cloud data is determined based on the matching result between the point cloud data and the plane contour information of the material, which can effectively reduce the calculation amount of sorting and save resources. In addition, the target center of gravity position of the material is determined based on the target point cloud data, and the material is sorted according to the target center of gravity position by the sorting device, which can effectively improve the accuracy of material sorting, reduce the material processing time, and thus improve the efficiency of material sorting.

[0102] In some embodiments, if the category of the material is determined to be a non-sorting category through category information, the step of matching the point cloud data with the plane contour information and determining the target point cloud data corresponding to the material in the point cloud data will not be performed, thereby saving computing resources, reducing material sorting delays, and improving material sorting efficiency.

[0103] Based on the same inventive concept, Fig.10 As shown, the present disclosure further provides a material sorting device 400, which may include:

[0104] A first transmission device 410, used for transmitting materials;

[0105] A first ray scanning device 420 is disposed upstream of the first transmission device 410, and the first ray scanning device 420 is used to perform a fixed-point scan on the first transmission device 410 to determine a ray projection image of the material;

[0106] The first laser radar 430 is disposed above the first transmission device 410 and is used to collect point cloud data of the material during the transmission process;

[0107] The first processor 440 is connected to the first ray scanning device 420 and the first laser radar 430 respectively. The first processor 440 is used to perform a first processing on the ray projection image to determine the plane contour information of the material; match the point cloud data with the plane contour information, determine the target point cloud data corresponding to the material in the point cloud data, determine the target center of gravity position of the material based on the target point cloud data, and send the target center of gravity position to the first sorting device;

[0108] The first sorting device 450 is disposed downstream of the first transmission device 410 and is used to sort materials according to the target center of gravity position.

[0109] In some examples, such as Fig.10 As shown, the first ray scanning device 420 includes a first fixed-point ray source 421 and a first ray detector 422 .

[0110] In some optional application scenarios, taking the case where the material is ore and the material sorting equipment is an ore sorting equipment as an example, the process of sorting the ore by the ore sorting equipment can be as follows:

[0111] In the process of transporting the ore through the first transport device (such as a conveyor belt), the first fixed-point ray light source of the first ray scanning device performs fixed-point scanning in a line scanning manner to obtain a ray projection image of the ore. The first fixed-point ray light source is located upstream of the first transport device, at a certain height from the conveyor belt, and the rays emitted by the first fixed-point ray light source are X-rays.

[0112] After a period of time, when the ore reaches the location of the first laser radar, the first laser radar performs laser line scanning to obtain point cloud data.

[0113] The first processor can determine the plane contour information of the ore by processing the ray projection image, and then match the point cloud data with the plane contour information to determine the target point cloud data corresponding to the ore in the point cloud data.

[0114] The first processor can determine the shape information of the ore according to the coordinate position information of each target point data in the target point cloud data, and further determine the target center of gravity position of the ore based on the shape information.

[0115] Taking the first sorting device as a blowing device as an example, the ore can be sorted by blowing the target center of gravity position through the blowing device so that the ore can fall into the corresponding dropping device to complete the sorting operation of the ore.

[0116] Based on the same inventive concept, Fig.11 As shown, the present disclosure also provides another material sorting device 500, which may include:

[0117] A second transmission device 510, used for transmitting materials;

[0118] The second sorting device 520 is disposed downstream of the second transmission device 510 and is used to sort the materials according to the target center of gravity position of the materials;

[0119] The second ray scanning device 530 is disposed above the second sorting device 520. The second ray scanning device 530 is used to perform fixed-point scanning on the material thrown out by the second transmission device 520 to determine the ray projection image of the material;

[0120] The second laser radar 540 is disposed downstream of the second ray scanning device 530 and is used to collect point cloud data of the material during the process of horizontal throwing;

[0121] The second processor 550 is connected to the second ray scanning device 530 and the second laser radar 540 respectively. The second processor 550 is used to perform a first processing on the ray projection image to determine the plane contour information of the material; match the point cloud data with the plane contour information, determine the target point cloud data corresponding to the material in the point cloud data, determine the target center of gravity position of the material based on the target point cloud data, and send the target center of gravity position to the second sorting device.

[0122] In some examples, such as Fig.11 As shown, the second ray scanning device 530 includes a second fixed-point ray source 531 and a second ray detector 532 .

[0123] In some optional application scenarios, taking the case where the material is ore and the material sorting equipment is an ore sorting equipment as an example, the process of sorting the ore by the ore sorting equipment can be as follows:

[0124] When the ore is thrown out horizontally by the conveyor belt (second conveyor device), the fixed-point ray light source of the second ray scanning device uses a line scanning method to perform fixed-point scanning on the ore to obtain a ray projection image of the ore. The fixed-point ray light source is located upstream of the second sorting device, at a certain height from the conveyor belt, and the rays emitted by the fixed-point ray light source are X-rays.

[0125] After a period of time, when the position where the ore is thrown out reaches the position of the second laser radar, the second laser radar performs laser line scanning to obtain point cloud data.

[0126] The second processor can determine the plane contour information of the ore by performing the first processing on the ray projection image, and then match the point cloud data with the plane contour information to determine the target point cloud data corresponding to the ore in the point cloud data.

[0127] The second processor can determine the shape information of the ore according to the coordinate position information of each target point data in the target point cloud data, and further determine the target center of gravity position of the ore based on the shape information.

[0128] Taking the second sorting device as the second blowing device as an example, the ore can be sorted by blowing the target center of gravity position through the second sorting device, so that the ore can fall into the corresponding dropping device, completing the sorting operation of the ore.

[0129] Based on the same inventive concept, the present disclosure also provides a material sorting device applied to a material sorting device. The material sorting device includes a ray scanning device, a laser radar, and a sorting device. Fig.12 As shown, the material sorting device 600 may include:

[0130] An acquisition module 610 is used to perform fixed-point scanning through a ray scanning device to acquire a ray projection image of the material;

[0131] A first processing module 620 is used to perform a first processing on the ray projection image to determine the plane contour information of the material;

[0132] The data acquisition module 630 is used to collect point cloud data of the material during the transmission process from above the material through a laser radar;

[0133] A matching module 640 is used to match the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data;

[0134] The second processing module 650 is used to determine the target center of gravity position of the material based on the target point cloud data;

[0135] The third processing module 660 is used to sort the materials according to the target center of gravity position through the sorting device.

[0136] In some embodiments, the ray scanning device includes a fixed-point ray source, and the matching module 640 may include: a first determination unit, used to determine the ray projection point position corresponding to each point data based on the position of the fixed-point ray source and the height information of each point data in the point cloud data; a second determination unit, used to determine the ray projection range corresponding to the material according to the plane contour information; a matching unit, used to determine the target point cloud data corresponding to the material in the point cloud data based on the matching results of multiple ray projection point positions and ray projection ranges.

[0137] In some embodiments, the target point cloud data includes multiple target point data, and the matching unit may include: a first execution unit, used to match the ray projection point position with the ray projection range to obtain a matching result; a second execution unit, used to determine that the point data corresponding to the ray projection point position is the target point data corresponding to the material if the matching result indicates that the ray projection point position is within the ray projection range.

[0138] In some embodiments, the matching unit may further include: a third execution unit, for determining that the point data corresponding to the ray projection point position is not the target point data corresponding to the material if the matching result indicates that the ray projection point position is outside the ray projection range.

[0139] In some embodiments, the second processing module 650 may include: a third determination unit, used to determine the shape information of the material according to the coordinate position information of each target point data in the target point cloud data; and a fourth determination unit, used to determine the target center of gravity position of the material based on the shape information.

[0140] In some embodiments, the fourth determination unit may include: a fourth execution unit, used to determine the three-dimensional contour information of the material based on the height information of each target point data in the target point cloud data; a fifth execution unit, used to determine the target center of gravity position of the material based on the shape information and the three-dimensional contour information.

[0141] In some embodiments, the third processing module 660 may include: a fifth determination unit, used to determine a target sorting mechanism and a target execution timing for the target sorting mechanism to perform sorting from multiple sorting mechanisms based on the target center of gravity position; a control unit, used to sort materials through the target sorting mechanism according to the target execution timing.

[0142] In some embodiments, the device 600 may also include: a fourth processing module, used to perform a second processing on the ray projection image to determine the category information of the material; a fifth processing module, used to execute the step of matching the point cloud data with the plane contour information if the category of the material is determined to be a category to be sorted through the category information.

[0143] Regarding the material sorting device in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0144] Based on the same inventive concept, the present disclosure also provides a computer-readable storage medium, which stores the following program, and the program is used to execute the material sorting method of any of the aforementioned embodiments.

[0145] The present application uses specific words to describe the embodiments of the present application. For example, "one embodiment", "an embodiment", and / or "some embodiments" refer to a certain feature, structure or characteristic related to at least one embodiment of the present application. Therefore, it should be emphasized and noted that "one embodiment" or "an embodiment" or "an alternative embodiment" mentioned twice or multiple times in different positions in this specification does not necessarily refer to the same embodiment. In addition, some features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0146] In the context of this application, unless the context clearly indicates an exception, the words "a", "an", "a kind" and / or "the" do not refer to the singular, but may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list, and the method or device may also include other steps or elements.

[0147] Similarly, it should be noted that in order to simplify the description of the disclosure of this application and thus help understand one or more application embodiments, in the above description of the embodiments of this application, multiple features are sometimes merged into one embodiment, figure or description thereof. However, this disclosure method does not mean that the features required by the object of this application are more than the features claimed for protection in this disclosure. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0148] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is only for example and does not constitute a limitation of the present application. Although not explicitly stated herein, those skilled in the art may make various modifications, improvements and amendments to the present application. Such modifications, improvements and amendments are suggested in the present application, so such modifications, improvements and amendments still belong to the spirit and scope of the embodiments of the present application.

Claims

1. A material sorting method, characterized in that: Applied to material sorting equipment, the material sorting equipment includes a ray scanning device, a laser radar, and a sorting device, the ray scanning device includes a fixed-point ray source, and the method includes: Performing fixed-point scanning by the ray scanning device to obtain a ray projection image of the material; Performing a first processing on the ray projection image to determine the plane contour information of the material; Collecting point cloud data of the material during the transmission process from above the material by using the laser radar; Matching the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data, including: determining the ray projection point position corresponding to each point data based on the position of the fixed-point ray source and the height information of each point data in the point cloud data; determining the ray projection range corresponding to the material according to the plane contour information; determining the target point cloud data corresponding to the material in the point cloud data based on the matching results of multiple ray projection point positions and the ray projection range, the target point data in the target point cloud data being the point data where the ray projection point position is within the ray projection range or on the range boundary; Determining the target center of gravity position of the material based on the target point cloud data includes: determining shape information of the material according to coordinate position information of each target point data in the target point cloud data; determining the target center of gravity position of the material based on the shape information; The material is sorted by the sorting device according to the target center of gravity position.

2. The material sorting method according to claim 1, characterized in that: The target point cloud data includes a plurality of target point data, and the determining the target point cloud data corresponding to the material in the point cloud data based on the matching results of the plurality of ray projection point positions and the ray projection range includes: Matching the ray projection point position with the ray projection range to obtain a matching result; If the matching result indicates that the position of the ray projection point is within the ray projection range, it is determined that the point data corresponding to the position of the ray projection point is the target point data corresponding to the material.

3. The material sorting method according to claim 2, characterized in that: The determining, based on the matching results of the plurality of ray projection point positions and the ray projection range, target point cloud data corresponding to the material in the point cloud data further includes: If the matching result indicates that the position of the ray projection point is outside the ray projection range, it is determined that the point data corresponding to the ray projection point position is not the target point data corresponding to the material.

4. The material sorting method according to claim 1, characterized in that: The step of determining a target center of gravity position of the material based on the shape information includes: Determining the three-dimensional contour information of the material according to the height information of each target point data in the target point cloud data; The target center of gravity position of the material is determined according to the shape information and the three-dimensional contour information.

5. The material sorting method according to claim 1, characterized in that: The sorting device includes a plurality of sorting mechanisms opposite to the material transmission direction, and the sorting of the material according to the target center of gravity position by the sorting device includes: Based on the target center of gravity position, determining a target sorting mechanism from the plurality of sorting mechanisms and a target execution timing for the target sorting mechanism to perform sorting; According to the target execution timing, the material is sorted by the target sorting mechanism.

6. The material sorting method according to claim 1, characterized in that: The method further comprises: Performing a second processing on the ray projection image to determine the category information of the material; If it is determined through the category information that the category of the material is a category to be sorted, a step of matching the point cloud data with the plane contour information is performed.

7. A material sorting device, characterized in that: Applied to material sorting equipment, the material sorting equipment includes a ray scanning device, a laser radar, and a sorting device, the ray scanning device includes a fixed-point ray source, and the device includes: An acquisition module, used for performing fixed-point scanning through the ray scanning device to acquire a ray projection image of the material; A first processing module, used for performing a first processing on the ray projection image to determine the plane contour information of the material; A data acquisition module, used for acquiring point cloud data of the material during the transmission process from above the material through the laser radar; A matching module, used for matching the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data, including: determining the ray projection point position corresponding to each point data based on the position of the fixed-point ray source and the height information of each point data in the point cloud data; determining the ray projection range corresponding to the material according to the plane contour information; determining the target point cloud data corresponding to the material in the point cloud data based on the matching results of multiple ray projection point positions and the ray projection range, the target point data in the target point cloud data being the point data where the ray projection point position is within the ray projection range or on the range boundary; The second processing module is used to determine the target center of gravity position of the material based on the target point cloud data, including: determining the shape information of the material according to the coordinate position information of each target point data in the target point cloud data; determining the target center of gravity position of the material based on the shape information; The third processing module is used to sort the material according to the target center of gravity position through the sorting device.

8. A material sorting device, characterized in that: include: A transmission device for transmitting materials; A ray scanning device, used for performing fixed-point scanning on the transmission device to determine a ray projection image of the material, wherein the ray scanning device comprises a fixed-point ray source; Laser radar, used to collect point cloud data of the material during transportation; A processor is connected to the ray scanning device and the laser radar respectively, and the processor is used to perform a first processing on the ray projection image to determine the plane contour information of the material; match the point cloud data with the plane contour information to determine the target point cloud data corresponding to the material in the point cloud data, including: based on the position of the fixed-point ray source and the height information of each point data in the point cloud data, respectively determine the ray projection point position corresponding to each point data; determine the ray projection range corresponding to the material according to the plane contour information; determine the target point cloud data corresponding to the material in the point cloud data based on the matching results of multiple ray projection point positions and the ray projection range, the target point data in the target point cloud data is the point data whose ray projection point position is within the ray projection range or on the range boundary; determine the target center of gravity position of the material based on the target point cloud data, including: determine the shape information of the material according to the coordinate position information of each target point data in the target point cloud data; determine the target center of gravity position of the material based on the shape information; and send the target center of gravity position to the sorting device; The sorting device is arranged downstream of the transmission device, and is used to sort the material according to the target center of gravity position.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores the following program, which is used to execute the material sorting method according to any one of claims 1 to 6.

Images