Material sorting method

By combining the material image information obtained by the ray device and the color sorting camera, the relative motion state of the ore and the conveyor belt are determined and the sorting strategy is formulated, which solves the wrong sorting problem caused by inaccurate material identification in the prior art, and improves the accuracy and efficiency of sorting.

CN119926836AActive Publication Date: 2025-05-06BEIJING HONEST TECHNOLOGY CO LTD

Patent Information

Application Number
CN202510367367.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-03-26
Publication Date
2025-05-06
Estimated Expiration
2045-03-26

AI Technical Summary

Technical Problem

Due to the relative movement of materials and conveyor belts, the material profile collected in the color sorting camera and ray device is inaccurate, which affects the identification accuracy and leads to incorrect sorting and missed sorting.

Method used

By combining the material image information obtained by the ray device and the color sorting camera, the relative motion state of the material and the conveyor belt is determined, and corresponding sorting strategies are formulated according to different motion states, including determining the sorting time and position.

Benefits of technology

Improve the accuracy and efficiency of material sorting, avoid sorting failure or missed selection caused by material position error, and ensure the accurate operation of the sorting device.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119926836A_ABST
    Figure CN119926836A_ABST
Patent Text Reader

Abstract

The invention relates to the technical field of ore separation, in particular to a material separation method. Comprising the following steps: determining a relative motion state of a material and a conveyor belt according to a ray image, a color selection image and a mapping relation between the ray image and the color selection image of the material respectively acquired by a ray device and a color selection camera; if it is determined that the materials and the conveying belt are in the relative static state, the sorting strategy of the materials is determined according to the ray image, the distance between the color sorting camera and the ray device and the running speed of the conveying belt, and the sorting strategy comprises the sorting time and the sorting position; if it is determined that the materials and the conveying belt are in the relative motion state, a sorting strategy is determined according to motion blur of the materials in the color sorting image; and according to the sorting strategy, sorting operation is carried out on the materials. By means of the material sorting method and device, the material sorting accuracy and sorting efficiency can be effectively improved, and more accurate sorting operation can be achieved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of ore sorting, and in particular to a material sorting method. Background Art

[0002] Coal, spodumene, silica and other ores are widely used in current industrial production. However, for ores such as coal, spodumene and silica, they usually contain a large amount of gangue and impurities after mining, and need to be sorted to improve the quality of the ore, reduce transportation costs, and reduce environmental pollution. Ore sorting equipment is widely used under this demand. Under the premise of resource conservation and environmental protection, the efficient and clean use of ore resources has become a key issue for the survival and development of my country's coal enterprises. For the sorting of ore, the ore is generally transported by a conveying device such as a conveyor belt, and a color sorting camera and a radiation device are set on the conveying path of the ore to realize the identification and detection of the ore, and the sorting operation is performed by the sorting device. However, there are certain technical bottlenecks in the existing ore sorting equipment. Since the detected ore may move relative to the conveying device, the ore contour collected and detected by the color sorting camera and the radiation device is inaccurate, which affects the accuracy of ore identification, resulting in low identification accuracy and incorrect sorting. In addition, since the ore may move relative to the conveying device, causing the ore position to shift too much, the time and position of the sorting device performing the sorting operation determined by the ore contour collected and detected by the color sorting camera and the X-ray device are incorrect, resulting in incorrect sorting and missed sorting, thereby reducing the sorting accuracy. Summary of the invention

[0003] 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, including: determining the relative motion state of the material and the conveyor belt according to the radiographic image, the color sorting image of the material acquired by the radiographic device and the color sorting camera respectively, and the mapping relationship between the radiographic image and the color sorting image; if it is determined that the material and the conveyor belt are in a relatively static state, determining the material sorting strategy according to the radiographic image, the distance between the color sorting camera and the radiographic device, and the running speed of the conveyor belt, wherein the sorting strategy includes the sorting time and the sorting position; if it is determined that the material and the conveyor belt are in a relative motion state, determining the sorting strategy according to the motion blur of the material in the color sorting image; and performing a sorting operation on the material according to the sorting strategy.

[0004] In some embodiments, determining the sorting strategy based on the motion blur of the material in the color sorting image includes: determining the degree of motion blur of the material in the color sorting image; if the degree of motion blur is less than a motion blur threshold, determining the material sorting strategy based on the X-ray image, the distance between the color sorting camera and the sorting mechanism, and the conveyor belt running speed; if the degree of motion blur is greater than or equal to the motion blur threshold, determining the material sorting time based on the motion blur of the material.

[0005] In some embodiments, determining the material sorting time based on the motion blur of the material includes: determining the speed of the material arriving at the radiation device based on the distance between the radiation device and the color sorting camera, the speed of the material when it arrives at the color sorting camera, and the time for the material to move from the radiation device to the color sorting camera; determining the acceleration of the material based on the speed of the material arriving at the color sorting camera, the time for the material to move from the radiation device to the color sorting camera, and the speed of the material arriving at the radiation device; determining the material sorting time based on the acceleration of the material, the speed of the material when it arrives at the color sorting camera, and the speed of the material arriving at the radiation device.

[0006] In some embodiments, determining the material sorting time according to the acceleration of the material, the speed of the material when it reaches the color sorting camera, and the speed of the material until it reaches the radiation device includes: determining the relative movement of the material with the conveyor belt before it reaches the sorting device according to the acceleration of the material, the speed of the material when it reaches the color sorting camera, and the speed of the material until it reaches the radiation device; if the material is relatively stationary with the conveyor belt before it reaches the sorting device, then determining the time required for the material and the conveyor belt to reach relative stillness, and the time required for the material and the conveyor belt to move to the sorting device after reaching relative stillness, as the material sorting time; if the material moves relative to the conveyor belt before it reaches the sorting device, then determining the material sorting time according to the acceleration of the material, the speed of the material when it reaches the color sorting camera, the movement speed of the conveyor belt, and the distance between the color sorting device and the sorting device.

[0007] In some embodiments, determining the material sorting time according to the motion blur of the material also includes: determining the actual movement direction and movement speed of the material according to the motion blur of the material; determining the theoretical movement direction of the material according to the X-ray image, the color sorting image, and the mapping relationship between the X-ray image and the color sorting image; determining the deviation between the actual movement direction of the material and the theoretical movement direction of the material; if the deviation between the actual movement direction of the material and the theoretical movement direction of the material is less than a motion deviation threshold, determining the material sorting strategy according to the X-ray image, the distance between the color sorting camera and the X-ray device, and the conveyor belt running speed; if the deviation between the actual movement direction of the material and the theoretical movement direction of the material is greater than or equal to the motion deviation threshold, skipping the step of performing a sorting operation on the material according to the sorting strategy.

[0008] In some embodiments, determining the theoretical direction of movement of the material according to the radiographic image, the color sorting image, and the mapping relationship between the radiographic image and the color sorting image includes: determining the theoretical contour of the material in the color sorting image according to the radiographic image and the mapping relationship between the color sorting image and the radiographic image; determining the vector direction from the centroid of the theoretical contour of the material in the color sorting image to the centroid of the actual contour of the material in the color sorting image as the theoretical direction of movement of the material according to the theoretical contour of the material in the color sorting image and the actual contour of the material in the color sorting image; or, determining all contour points of the theoretical contour of the material in the color sorting image to all contour points of the actual contour of the material in the color sorting image as the theoretical direction of movement of the material according to the theoretical contour of the material in the color sorting image and the actual contour of the material in the color sorting image.

[0009] In some embodiments, determining the actual movement direction and movement speed of the material based on the motion blur of the material includes: determining the blur direction and blur length of the material based on the motion blur of the material, and determining the blur direction as the actual movement direction of the material; determining the movement speed of the material based on the exposure time of the color sorting camera and the blur length.

[0010] In some embodiments, the relative motion state of the material and the conveyor belt is determined according to the radiographic image, the color sorting image, and the mapping relationship between the radiographic image and the color sorting image of the material respectively acquired by the radiographic device and the color sorting camera, including: determining the theoretical position of the color sorting contour of the material on the radiographic image as the theoretical radiographic contour according to the color sorting image and the mapping relationship between the radiographic image and the color sorting image; and determining the relative motion state of the material and the conveyor belt according to the theoretical radiographic contour and the actual radiographic contour in the radiographic image.

[0011] In some embodiments, determining the relative motion state of the material and the conveyor belt based on the theoretical ray profile and the actual ray profile in the ray image includes: matching the theoretical ray profile with the actual ray profile to determine multiple point pairs; determining the degree of deviation of the material based on the distance of each point pair; if the degree of deviation is less than or equal to the profile deviation threshold, determining that the material and the conveyor belt are in a relatively static state; if the degree of deviation is greater than the profile deviation threshold, determining that the material and the conveyor belt are in a relative motion state.

[0012] In some embodiments, determining the degree of deviation of the material based on the distance of each point pair includes: determining the distance between two points of each point pair based on multiple point pairs; excluding abnormal point pairs based on the distance between two points of each point pair, and determining the average, standard deviation, and maximum value of the Euclidean distances of multiple target point pairs; determining the degree of deviation of the material based on the average, standard deviation, and maximum value of the distances of multiple target point pairs.

[0013] 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.

[0014] Through the present disclosure, it is possible to combine the X-ray images collected by the X-ray device and the color sorting images collected by the color sorting camera and other information for detection and analysis of the relative movement state of the material, so that the sorting device can more accurately predict the actual position of the material falling from the conveyor belt and the sorting time and other information, thereby avoiding sorting failure or misselection caused by material position error, improving the sorting accuracy, and avoiding misoperation of the sorting device, which can effectively improve the accuracy and efficiency of material sorting and achieve more precise sorting operations. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The present invention may be better understood by describing exemplary embodiments of the present invention in conjunction with the accompanying drawings, in which:

[0016] Figure 1 The present invention is a flow chart of a material sorting method according to an exemplary embodiment of the present invention;

[0017] Figure 2 The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention;

[0018] Figure 3 The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention;

[0019] Figure 4 The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention;

[0020] Figure 5The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention;

[0021] Figure 6 The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention;

[0022] Figure 7 The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention;

[0023] Figure 8 The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention;

[0024] Fig. 9 The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention;

[0025] Fig.10 The present invention is a flow chart of a material sorting method according to another exemplary embodiment of the present invention. DETAILED DESCRIPTION

[0026] 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.

[0027] Unless otherwise defined, the technical or scientific terms used in the claims and the specification shall have the usual meaning understood by persons with ordinary skills in the technical field to which the invention belongs. The words "first", "second" and similar words used in the patent application specification and the claims of the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "One" or "one" and other similar words do not indicate a quantitative limitation, but indicate the existence of at least one. "Include" or "comprises" and other similar words mean that the elements or objects appearing before "include" or "comprises" include the elements or objects listed after "include" or "comprises" and their equivalent elements, and do not exclude other elements or objects. "Connected" or "connected" and other similar words are not limited to physical or mechanical connections, nor are they limited to direct or indirect connections.

[0028] Material sorting equipment can be used to identify and sort materials, thereby realizing the classification and collection of materials. Generally, materials are transferred through conveying mechanisms such as conveyor belts, and a radiographic camera and a color sorting camera are set above the conveyor belt to collect radiographic images and color sorting images of the materials respectively. The sorting equipment can determine the category of the material based on the radiographic image and the color sorting image, and determine the position and time when the material falls from the conveyor belt through the information of the radiographic image and the color sorting image, so as to determine the position and time when the sorting device performs the sorting operation. The distance between the radiographic device and the color sorting camera is fixed, and the conveyor belt speed is fixed, so the time difference dt between collecting the radiographic image and collecting the color sorting image can be determined. At any time t0, the radiographic image is collected, and the material contour collected in the radiographic image is the radiographic contour. At t0+dt, the color sorting camera can collect images of the same material, and the material contour in the collected color sorting image is the color sorting contour. Theoretically, if the material remains relatively still with the conveyor belt, the ray profile and the color sorting profile can correspond to each other, so that any point P on the material collected by the ray device at time t0 corresponds to point P' collected by the color sorting camera at time t0+dt, which is the same point on the material. However, the material may move relative to the conveyor belt on the conveyor belt, such as accelerated motion or rotation. This relative motion may cause the contour position of the same material in the ray image and the color sorting image to shift, resulting in the inability to align the ray profile and the color sorting profile of the material, which will cause the sorting device to deviate when determining the sorting position and sorting time of the sorting device according to the ray profile and the color sorting profile of the material, resulting in errors in material sorting, incorrect sorting and missed sorting, which will reduce the sorting accuracy.

[0029] According to the above technical problems, such as Figure 1 As shown, the present disclosure provides a material sorting method, including: step S110 to step S140.

[0030] Step S110, according to the radiographic image, color sorting image, and mapping relationship between the radiographic image and the color sorting image of the material respectively obtained by the radiographic device and the color sorting camera, the relative motion state of the material and the conveyor belt is determined. First, the radiographic image of the material can be taken by the radiographic device, and then the color sorting image of the material can be taken by the color sorting camera, wherein the time interval between each radiographic image and the color sorting image between the radiographic device and the color sorting camera is the same. Among them, the radiographic image includes the radiographic contour of the material, and the color sorting image includes the color sorting contour of the same material. In addition, the color sorting image can also include information such as the color of the material surface. For the material on the conveyor belt, when it remains relatively stationary with the conveyor belt, the radiographic image and the color sorting image are mapped, and the radiographic contour in the radiographic image and the color sorting contour in the color sorting image should be consistent based on the mapping relationship, and any point on the radiographic contour and the corresponding contour point on the color sorting contour are in the same position after mapping, so that the radiographic contour and the color sorting contour have the same size and posture. When the material and the conveyor belt are in a state of relative motion, the material has a certain acceleration after being photographed by the radiation device until being photographed by the color sorting camera, causing its position on the conveyor belt to change; or the material rotates, causing its posture on the conveyor belt to change. If the material and the conveyor belt remain relatively still, the sorting device of the material sorting equipment can directly determine the time and position of sorting the material according to information such as the radiation image of the material when performing the sorting operation, with high accuracy. However, when the material and the conveyor belt are in relative motion, the position of the material will be offset, so that the position and posture of the material may continue to shift during the process of moving from the color sorting camera to the sorting device, resulting in the sorting device of the material sorting equipment being unable to accurately determine the time and position of sorting the material according to information such as the radiation image when performing the sorting operation, resulting in reduced sorting accuracy. Therefore, the relative motion state of the material and the conveyor belt can be determined first according to the radiation image, color sorting image, and the mapping relationship between the radiation image and the color sorting image of the material obtained by the radiation device and the color sorting camera respectively. This enables the state and position of the material to be determined in subsequent steps, so that different sorting strategies can be adopted for materials that move relative to the conveyor belt and materials that remain relatively stationary with the conveyor belt, allowing the material sorting equipment to obtain more accurate sorting time and sorting position information, thereby improving the accuracy and efficiency of material sorting.

[0031] Step S120, if it is determined that the material and the conveyor belt are in a relatively static state, then the material sorting strategy is determined according to the radiographic image, the distance between the color sorting camera and the radiographic device, and the conveyor belt running speed, wherein the sorting strategy includes the sorting time and the sorting position. When the material and the conveyor belt are in a relatively static state, it can be determined that the material and the conveyor belt continue to remain relatively stable and do not move during the process of the material moving from the radiographic device to the color sorting camera, and it can be considered that the material can also continue to maintain a relatively stable state with the conveyor belt during the subsequent process of moving from the color sorting camera to the sorting device. Therefore, the material sorting strategy can be determined according to the material's radiographic image, the first distance between the color sorting camera and the radiographic device, and the conveyor belt running speed. Among them, the material sorting strategy includes the sorting time for the sorting device to perform the sorting operation, and the position where the material will fall from the conveyor belt, that is, the sorting position where the sorting device performs the sorting operation.

[0032] Step S130, if it is determined that the material and the conveyor belt are in a relative motion state, the sorting strategy is determined according to the motion blur of the material in the color sorting image. When the material and the conveyor belt are in a relative motion state, it can be determined that the material generates an acceleration relative to the conveyor belt during the process of moving from the ray device to the color sorting camera, resulting in the material moving speed being different from the conveyor belt transmission speed, or the material rotates during the transmission process. If the material and the conveyor belt are in a relative motion state, it can be determined that the material's posture has changed relative to the conveyor belt during the process of moving from the ray device to the color sorting camera, and the color sorting profile of the material and the ray profile cannot be directly aligned according to the mapping relationship. This relative motion state will cause a certain amount of motion blur in the color sorting image taken by the color sorting camera. The material changes its posture during the process of moving from the ray device to the color sorting camera, resulting in the inability to directly determine the sorting position and sorting time of the material when it falls from the conveyor belt for sorting based on the ray image information and the conveyor belt speed. In addition, since the material may also maintain relative motion with the conveyor belt during the process of moving from the color sorting camera to the sorting device, resulting in continuous changes in the material's posture, it is also impossible to directly determine the sorting position and sorting time of the material when it falls from the conveyor belt for sorting based on the radiographic image information and the conveyor belt speed. Therefore, the material sorting strategy can be determined based on the motion blur of the material in the color sorting image. Motion blur can reflect the direction of relative motion between the material and the conveyor belt, as well as information such as speed. Therefore, the material sorting strategy can be determined based on the motion blur of the material in the color sorting image, so that a more accurate sorting time and sorting position for the material can be obtained, avoiding incorrect sorting and missed sorting.

[0033] Step S140, according to the sorting strategy, the sorting operation is performed on the material. According to the determined sorting strategy, the sorting operation can be performed on the material by the sorting device. Specifically, the sorting device can be a push plate mechanism including multiple push plates or a blowing mechanism including multiple nozzles. For the push plate mechanism, determining the sorting position of the material is to determine one or more push plates to perform the sorting operation. For the blowing mechanism, determining the sorting position of the material is to determine one or more nozzles to perform the sorting operation. According to the determined sorting strategy, the time and position of the material falling from the conveyor belt can be determined more accurately, so that the sorting device of the sorting equipment can respond in time and accurately to achieve accurate sorting. It can effectively avoid sorting errors caused by early or delayed execution of the sorting operation, and effectively avoid invalid sorting caused by the failure of the sorting device to push or blow to the corresponding material due to incorrect sorting position judgment, which can effectively improve the accuracy of material sorting.

[0034] The disclosed embodiment combines the multimodal detection information including the radiographic image collected by the radiographic device and the color sorting image collected by the color sorting camera, and analyzes the relative motion state of the material, so that the sorting device can accurately predict the actual falling trajectory and sorting time of the material, avoid sorting failure or misselection caused by material position error, and improve the sorting accuracy. According to the different relative motion states of the material and the conveyor belt, different sorting strategies can be determined and sorting operations can be performed, which has good adaptability. For materials that are relatively stationary with the conveyor belt, the sorting time and position can be directly determined based on the conveyor belt speed and the distance between the radiographic device and the color sorting camera and the radiographic image information to ensure the stability of the sorting operation. For materials that move relative to the conveyor belt, the displacement, rotation and other information of the material can be inferred by analyzing the motion blur in the color sorting image, and the sorting strategy can be dynamically adjusted to achieve more accurate sorting. In the case of uncertain material motion state, the traditional method is prone to early or delayed sorting due to misjudgment, or the push plate or nozzle fails to accurately act on the target material due to position offset. This method can avoid misoperation of the sorting device by accurately calculating the sorting time and position, thereby improving the sorting efficiency. The present disclosure adopts automated image analysis and motion state calculation, does not require manual adjustment of sorting parameters, reduces human errors, can improve the automation level of material sorting equipment, and makes material sorting more efficient and intelligent.

[0035] In some embodiments, Figure 2 As shown, in step 130, the sorting strategy is determined according to the motion blur of the material in the color sorting image, and steps S131 to S133 may also be included.

[0036] Step S131, determining the degree of motion blur of the material in the color sorting image. When the material passes through the color sorting camera, the material moves relative to the conveyor belt, so different degrees of motion blur may appear in the image captured by the color sorting camera. Edge detection, Fourier analysis and other methods can be used to extract the color sorting contour information that has motion blur in the color sorting image, quantify the motion blur of the material, and determine the degree of motion blur. Motion blur can reflect the speed and direction of the material movement. Specifically, when the material moves relative to the conveyor belt in any direction, the color sorting contour of the material in the color sorting image may produce motion blur in its movement direction when the color sorting camera captures the color sorting image of the material. The actual movement direction and actual movement speed of the material can be determined based on the direction of the motion blur and the length of the motion blur.

[0037] Step S132, if the degree of motion blur is less than the motion blur threshold, the material sorting strategy is determined according to the radiographic image, the distance between the color sorting camera and the sorting mechanism, and the conveyor belt running speed. A motion blur threshold can be preset. For the case where the degree of motion blur is less than the preset motion blur threshold, it can be considered that the relative movement between the material and the conveyor belt is relatively slow or basically in a stable state. The relative movement state of the material and the conveyor belt at the moment of the color sorting camera shooting can be regarded as relatively static. Therefore, the sorting time and sorting position of the material can be determined according to the ray contour in the radiographic image, the distance from the color sorting camera to the sorting device, and the conveyor belt running speed. The ray contour of the material can be clearly obtained from the image collected by the ray device, which can reflect the shape, size and initial position of the material on the conveyor belt. By analyzing these contours using image processing algorithms, the position of the material in the radiographic image and its edge features can be accurately calibrated. Subsequently, since the relative motion state of the material and the conveyor belt at the moment the color sorting camera captures the image is regarded as relatively static, it can be determined that in the process of the material moving from the color sorting camera to the sorting device, its moving speed is consistent with the conveyor belt speed, and its position and posture relative to the conveyor belt do not change. Therefore, based on the fixed distance between the color sorting camera and the sorting device and the running speed of the conveyor belt, the expected transmission time of the material from the location of the color sorting camera to the sorting device can be determined as the sorting time, and the position of the material on the conveyor belt at the moment the color sorting camera captures the image can be determined at the same time, thereby accurately determining the falling position of the material at the end of the conveyor belt as the sorting position.

[0038] Step S133, if the degree of motion blur is greater than or equal to the motion blur threshold, the material sorting time is determined according to the motion blur of the material. For the case where the degree of motion blur is greater than or equal to the preset motion blur threshold, it can be considered that at the moment when the color sorting camera takes the color sorting image, the material and the conveyor belt are still in relative motion, and the relative motion between the material and the conveyor belt is relatively violent, so that the material continues to maintain relative motion with the conveyor belt during the process of moving from the position of the color sorting camera to the sorting device. Therefore, in this case, the speed and posture of the material continue to change during the process of moving from the position of the color sorting camera to the sorting device, and the sorting time and sorting position cannot be determined according to the fixed distance between the color sorting camera and the sorting device and the running speed of the conveyor belt. Since the motion blur in the color sorting image can reflect the movement direction and movement speed of the material at the moment of taking the color sorting image. Therefore, according to the motion blur, the movement speed and acceleration of the material at the moment of taking the color sorting image can be determined, so as to determine a more accurate material sorting time.

[0039] By detecting the degree of motion blur in the color sorting image, the material sorting method provided by this embodiment can accurately distinguish whether the material remains relatively still with the conveyor belt or has a large degree of relative motion, thereby determining different sorting strategies and improving the accuracy and reliability of sorting. By quantitatively analyzing motion blur by edge detection, Fourier analysis and other methods, it is not only possible to determine whether the material has relative motion, but also to further determine its motion direction, speed and acceleration, so as to more accurately determine the sorting time and position of the material in the future. When the degree of motion blur of the material is small, the sorting time and position can be accurately calculated based on the conveyor belt speed and fixed distance to ensure efficient and stable sorting. When the degree of motion blur of the material is large, the sorting time can be calculated based on the motion blur information of the material, rather than relying solely on the conveyor belt speed, thereby avoiding misselection or omission caused by material position offset and improving the sorting success rate. Through accurate prediction based on motion blur, this method can ensure that the sorting operation only acts on the correct material, thereby reducing invalid operations and improving the service life and energy efficiency of the equipment.

[0040] In some embodiments, Figure 3 As shown, step S133 determines the material sorting time according to the motion blur of the material, and also includes steps S1331 to S1333.

[0041] Step S1331, according to the distance between the ray device and the color sorting camera, the speed of the material when it reaches the color sorting camera, and the time when the material moves from the ray device to the color sorting camera, the speed of the material reaching the ray device is determined. Since motion blur occurs in the color sorting image of the material taken by the color sorting camera, it can be determined that the material has relative motion at the time of the color sorting camera shooting. According to the motion blur, the speed of the material when it reaches the color sorting camera can be determined, that is, the speed of the material when the color sorting camera shoots the color sorting image. The time interval for the ray device to collect ray images and the time interval for the color sorting camera to collect color sorting images are both preset fixed values. Therefore, according to the time interval for the ray device to collect ray images and the time interval for the color sorting camera to collect color sorting images, the time interval between taking the ray image of the current material and taking the color sorting image of the current material can be determined, that is, the time when the material moves from the ray device to the color sorting camera. The distance between the ray device and the color sorting camera is a fixed preset value. Therefore, according to the speed when the material reaches the color sorting camera, the distance from the ray device to the color sorting camera, and the time when the material moves from the ray device to the color sorting camera, the speed of the material when it reaches the ray camera can be calculated, that is, the speed of the material when the ray device shoots the material. Specifically, since the method provided in this embodiment is only used to determine the sorting time of the material, and the sorting time is only related to the parameters of the material along the moving direction of the conveyor belt, the speed component of the material along the moving direction of the conveyor belt when it reaches the color sorting camera can be determined according to the following formula based on the distance from the ray device to the color sorting camera, the speed component of the material along the moving direction of the conveyor belt when it reaches the color sorting camera, and the time taken for the material to reach the color sorting camera from the ray device. X :

[0042]

[0043] Among them, S XC is the distance from the ray device to the color sorting camera, t XC V is the time taken for the material to reach the color sorting camera from the X-ray device. C It is the velocity component of the material along the conveyor belt when it reaches the color sorting camera.

[0044] Step S1332, the acceleration of the material is determined according to the speed of the material when it reaches the color sorting camera, the time when the material moves from the radiation device to the color sorting camera, and the speed of the material to the radiation device. The acceleration of the material can be the acceleration of the material when it reaches the color sorting camera, that is, the acceleration of the material when the color sorting camera collects the color sorting image. According to the speed of the material when it reaches the color sorting camera, the speed of the material to the radiation device, and the time when the material moves from the radiation device to the color sorting camera, the acceleration of the material when the color sorting camera collects the color sorting image can be determined, so as to facilitate the subsequent determination of the movement speed of the material and the sorting time according to the acceleration of the material when the color sorting camera collects the color sorting image. Specifically, since the method provided in this embodiment is only used to determine the sorting time of the material, the sorting time is only related to the parameters of the material along the moving direction of the conveyor belt. Therefore, the acceleration of the material in the moving direction of the conveyor belt can be determined according to the speed component of the material along the moving direction of the conveyor belt when it reaches the color sorting camera, the speed component of the material along the moving direction of the conveyor belt when it reaches the radiation device, and the time when the material moves from the radiation device to the color sorting camera. According to the formula: a=(V C -V X ) / t XC , we can determine the acceleration a of the material along the conveyor belt, where V X V is the velocity component of the material along the conveyor belt when it reaches the ray device. C is the velocity component of the material along the conveyor belt when it reaches the color sorting camera, t XC It is the time taken for the material to reach the color sorting camera from the X-ray device.

[0045] Step S1333, determine the material sorting time according to the acceleration of the material, the speed of the material when it reaches the color sorting camera, and the speed of the material to the radiation device. According to the acceleration of the material, the speed of the material when it reaches the radiation device, and the speed of the material when it reaches the color sorting camera, the motion parameters of the material in the process of moving from the color sorting camera to the sorting device can be determined. Since the material has an acceleration along the moving direction of the conveyor belt when it is photographed by the color sorting camera, it can be determined that in the process of moving from the color sorting camera to the end of the conveyor belt until the sorting device performs the sorting operation, the material and the conveyor belt may maintain a relative motion state, and maintain acceleration relative to the conveyor belt throughout the process until it falls. The material may also reach a relative static state with the conveyor belt halfway, so that the speed component of the material in the moving direction of the conveyor belt is consistent with the moving speed of the conveyor belt and then falls. Specifically, according to the acceleration of the material along the moving direction of the conveyor belt, the speed of the material along the moving direction of the conveyor belt when it reaches the color sorting camera, and the speed of the material along the moving direction of the conveyor belt when it reaches the radiation device, the sorting time of the material from the color sorting camera to the end of the conveyor belt until the sorting device performs the sorting operation can be determined.

[0046] Through the material sorting method provided in this embodiment, by calculating the speed of the material when it reaches the radiation device, the initial motion state of the material on the conveyor belt can be more accurately grasped, and the errors caused by shooting angles or lighting conditions in the color sorting image can be effectively compensated, so that the motion parameter calculation of the material is more stable and reliable. By calculating the acceleration of the material, the movement trend of the material on the conveyor belt can be accurately judged, so as to adjust the sorting strategy and ensure the accuracy of the sorting operation. Since the motion state of the material will continue to change after the color sorting camera, relying solely on the color sorting image of the color sorting camera may lead to wrong judgments and trigger wrong sorting operations. By calculating the sorting time, the sorting device only performs the sorting action when the material reaches the appropriate position, reducing invalid push plate or blowing operations, reducing the energy consumption and mechanical loss of the equipment, and improving the long-term stability of the system. This method can effectively reduce the misselection caused by material position deviation and improve the response speed of the sorting system.

[0047] In some embodiments, Figure 4 As shown, step S1333 determines the material sorting time according to the acceleration of the material, the speed of the material when it reaches the color sorting camera, and the speed of the material when it reaches the ray device, and also includes steps S13331 to S13333

[0048] Step S13331, based on the acceleration of the material, the speed of the material when it reaches the color sorting camera, and the speed of the material to the radiation device, determine the relative motion state of the material and the conveyor belt before it reaches the sorting device. Since the material has an acceleration along the direction of the conveyor belt when it is photographed by the color sorting camera, and the movement of the material may have a certain loss, the speed of the material gradually decreases. The material can eventually reach a state of relative stillness with the conveyor belt within a certain time or a certain moving distance range, so that the speed component of the material along the direction of the conveyor belt movement is consistent with the conveyor belt movement speed. However, the distance from the color sorting camera to the sorting device is limited. Therefore, materials in different situations may be in different motion states when they arrive at the sorting device. Specifically, in the process of moving from the color sorting camera to the end of the conveyor belt until the sorting device performs the sorting operation, the material and the conveyor belt may always maintain a relative motion state, and the material remains accelerated relative to the conveyor belt throughout the process until it falls. The material may also be damaged by friction with the conveyor belt surface, which may gradually reduce the speed of the material, so that the material can reach a relative static state with the conveyor belt in the process of moving from the color sorting camera to the end of the conveyor belt until the sorting device performs the sorting operation, so that the speed component of the material in the direction of the conveyor belt movement is consistent with the movement speed of the conveyor belt, and then fall and be sorted by the sorting device. Specifically, it can be determined based on parameter t1 whether the material can reach a relative static state with the conveyor belt before reaching the sorting device. t1=(V B -V C) / a, where V C V is the velocity component of the material along the conveyor belt when it reaches the color sorting camera. B is the moving speed of the conveyor belt, and a is the acceleration of the material along the moving direction of the conveyor belt when it is photographed by the color sorting camera. When t1 ≥ 0, it can be considered that before the material reaches the sorting device, in the moving direction of the conveyor belt, the material and the conveyor belt may reach a relatively static state. Specifically, the material may reach a relatively static state with the conveyor belt before reaching the sorting device; it may also reach a relatively static state with the conveyor belt when the material reaches the sorting device, or after the material reaches the sorting device. In this regard, it can be based on: Among them, S1 is the distance that the material needs to move in the current moving state until it reaches a relative static state with the conveyor belt. C is the speed of the material along the conveyor belt when the color sorting camera captures the color sorting image, and a is the acceleration of the material along the conveyor belt when the color sorting camera collects the color sorting image. CW In the case of V B When S1≥S CW In the case of V B When t1 is less than 0, that is, when the material and the conveyor belt reach a relatively static state, the material has reached the sorting device or exceeded the sorting device. When t1 is less than 0, it can be considered that before the material reaches the sorting device, the velocity component along the direction of movement of the conveyor belt cannot reach the movement speed of the conveyor belt, indicating that the material continues to accelerate relative to the conveyor belt, that is, in the direction of movement of the conveyor belt, the material and the conveyor belt maintain relative motion. According to the relative motion judgment between the material and the conveyor belt before the material reaches the sorting device, the sorting time of the material can be determined in different ways according to different relative motion states. Step S13332, if the material is relatively static with the conveyor belt before reaching the sorting device, the time required for the material and the conveyor belt to reach relative static and the time required for the material and the conveyor belt to move to the sorting device after reaching relative static are determined as the material sorting time. If the material can reach relative stillness before reaching the sorting device, the material sorting time from the color sorting camera to the sorting device can be divided into two parts. One part is the time required for the material to start moving from the color sorting camera to the sorting device until the material reaches the same speed as the conveyor belt in the direction of movement of the conveyor belt, that is, the time required for the material and the conveyor belt to reach a relative stillness. The other part is the time required for the material to move to the sorting device after reaching relative stillness with the conveyor belt. The addition of the above two parts of time is the time required for the material to move from the color sorting camera to the sorting device, that is, the material sorting time. Specifically, it can be calculated according to the formula Determine. Among them, tCW is the material sorting time, V B is the conveyor belt speed, V C S is the speed of the material along the conveyor belt when it is photographed by the color sorting camera. CW is the distance between the color sorting camera and the sorting device, that is, the distance the material moves from the color sorting camera to the sorting device, and a is the acceleration of the material along the conveyor belt when the color sorting camera collects the color sorting image. It is the time required for the material and the conveyor belt to reach a relative static state.

[0049] Step S13333, if the material moves relative to the conveyor belt before reaching the sorting device, the sorting time of the material is determined based on the acceleration of the material, the speed of the material when it reaches the color sorting camera, and the distance between the color sorting device and the sorting device. If the material is still in a state of relative motion with the conveyor belt before reaching the sorting device, the sorting time of the material can be directly determined by the acceleration of the material along the direction of movement of the conveyor belt, the speed component of the material along the direction of movement of the conveyor belt when it reaches the color sorting camera, and the distance the material moves from the color sorting device to the sorting device. Specifically, it can be determined according to the formula Determine, where t CW is the material sorting time, V C is the speed of the material along the conveyor belt when it is photographed by the color sorting camera, S CW is the distance between the color sorting camera and the sorting device, that is, the distance the material travels from the color sorting camera to the sorting device, and a is the acceleration of the material along the direction of movement of the conveyor belt when the color sorting camera collects the color sorting image.

[0050] The material sorting method provided by the present disclosure, wherein, by calculating whether the material can reach a relative static state with the conveyor belt before reaching the sorting device, the movement mode of the material can be more accurately judged, thereby optimizing the calculation of the sorting time. The material may experience a continuous acceleration state or eventually tend to a static state on the conveyor belt. The present method can select different calculation methods according to the actual situation, thereby ensuring that the sorting device can operate at the most appropriate time. If the material still maintains relative motion with the conveyor belt before reaching the sorting device, it may cause the material to deviate from the originally expected falling trajectory, resulting in sorting errors. The present method enables the sorting device to adjust its action in time by accurately calculating the acceleration and motion state of the material, thereby reducing the situation of misselection or omission. In particular, for materials with irregular shapes or easy rolling, the method can better adapt to their complex motion characteristics and improve the sorting accuracy. Since the present method can dynamically adapt to the motion characteristics of different materials, it can still maintain a high sorting accuracy when facing materials of different shapes, masses or surface characteristics, and has better robustness.

[0051] In some embodiments, Figure 5 As shown, step S130, determining the material sorting time according to the motion blur of the material, may also include: steps S134 to S138.

[0052] Step S134, based on the motion blur of the material, determine the actual motion direction and speed of the material. Since the material and the conveyor belt are in relative motion when the color sorting image is captured, the material's motion speed is inconsistent with that of the conveyor belt, and the material's speed is greater than that of the conveyor belt, which will cause motion blur in the color sorting image. Motion blur makes the color sorting contour edge of the color sorting image appear elongated. The actual motion direction of the material when the material and the conveyor belt are in relative motion, as well as the actual speed of the material at the time of color sorting image acquisition, can be determined based on the length and direction of the elongated color sorting contour edge caused by motion blur.

[0053] Step S135, determine the theoretical direction of movement of the material according to the radiographic image, the color sorting image, and the mapping relationship between the radiographic image and the color sorting image. According to the ray profile in the radiographic image, the mapping relationship between the radiographic image and the color sorting image, and the color sorting profile in the color sorting image, the ray profile can be mapped to the color sorting image to determine the theoretical profile of the ray profile in the color sorting image. According to the deviation between the color sorting profile and the theoretical profile, the theoretical direction of movement of the material can be determined, that is, according to the movement speed and direction of the material at the moment when the material is moved from the radiographic device to the color sorting camera and the color sorting camera captures the material, the theoretical direction of movement of the material. Since the material's movement state may continue to change during the process of moving from the radiographic device to the color sorting camera. Specifically, the material may rotate during this process, causing its actual direction of movement to change.

[0054] Step S136, determining the deviation between the actual movement direction of the material and the theoretical movement direction of the material. Based on the determined actual movement direction and theoretical movement direction of the material, the deviation between the two can be determined, and the deviation can be recorded in the form of an angle. The angle formed by the actual movement direction of the material and the theoretical movement direction of the material can be determined as the deviation between the two. A movement deviation threshold can be set, and the deviation between the actual movement direction of the material and the theoretical movement direction of the material can be compared with the movement deviation threshold. Different sorting strategies can be adopted according to the deviation between the actual movement direction of the material and the theoretical movement direction of the material.

[0055] Step S137, if the deviation between the actual movement direction of the material and the theoretical movement direction of the material is less than the movement deviation threshold, then executing step S132, determining the material sorting strategy according to the radiographic image, the distance between the color sorting camera and the radiographic device, and the conveyor belt running speed;

[0056] When the deviation between the actual movement direction of the material and the theoretical movement direction of the material is less than the movement deviation threshold, it can be considered that the overall movement direction of the material remains stable during the process of moving from the X-ray device to the color sorting camera, and the deviation of the movement direction and speed is small. In this case, it can be considered that the movement direction of the material during the process of moving from the color sorting image to the sorting device is consistent with the movement direction of the material during the process of moving from the X-ray device to the color sorting camera. Therefore, the material sorting strategy can be determined based on the X-ray image, the distance from the color sorting camera to the sorting mechanism, and the conveyor belt running speed.

[0057] Step S138, if the deviation between the actual movement direction of the material and the theoretical movement direction of the material is greater than or equal to the movement deviation threshold, then step S140 is skipped, and the material is sorted according to the sorting strategy. When the deviation between the actual movement direction of the material and the theoretical movement direction of the material is greater than or equal to the movement deviation threshold, it can be considered that the deviation of the overall movement direction and movement speed of the material is large during the process of moving from the ray device to the color sorting camera, or the current material collides with other materials, resulting in a large cumulative error in the movement, making it difficult to accurately confirm the movement information of the current material. Therefore, in this case, step S140 can be skipped, and the current material is not sorted, thereby avoiding the situation where large errors lead to incorrect calculation of sorting time and sorting position.

[0058] Through the material sorting method provided in this embodiment, the actual movement direction and speed of the material are determined by analyzing motion blur, rather than relying solely on theoretical calculations, so that the sorting system can adapt to the dynamic changes of the material more accurately. During the transmission process, the material may undergo nonlinear movements such as rotation, jumping, and tilting, resulting in a large deviation between its actual movement direction and the theoretical direction. By setting the motion deviation threshold, the system can identify materials with abnormal motion states and choose whether to perform sorting to avoid misselection. For materials with small deviations, the system can continue to use standard sorting strategies based on radiographic images, color sorting camera positions, and conveyor belt speeds to ensure efficient processing. For materials with large deviations, the system can choose to skip sorting to reduce errors. This flexible sorting strategy improves the reliability of the system, enabling it to adapt to materials of different types, shapes, and motion states, improve the overall sorting accuracy, and at the same time reduce the ineffective actions of the sorting device, reduce mechanical wear and energy consumption, and improve sorting efficiency.

[0059] In some embodiments, Figure 6 As shown, step S134, determining the actual movement direction and movement speed of the material according to the motion blur of the material, may include step S1341 and step S1342.

[0060] Step S1341, according to the motion blur of the material, determine the blur direction and blur length of the material, and determine the blur direction as the actual motion direction of the material. According to the color sorting image captured by the color sorting camera, the characteristics of the motion blur captured in the color sorting image can be determined. Among them, the characteristics of motion blur can include the direction of blur and the length of blur. The contour information of the material in the color sorting image, that is, the color sorting contour, can be determined by the edge detection algorithm. Since the material is motion blurred, the contour of the area where the motion blur occurs generally presents an elongated shape. Therefore, the direction in which the contour of the area where the motion blur occurs is elongated is the motion blur direction of the material. In addition, according to the color sorting image of the collected material, the color sorting image can be Fourier transformed to determine the spectrum of the color sorting image, so as to perform spectrum analysis on the blurred area in the color sorting image. The blur direction usually corresponds to the direction in which the low-frequency component in the spectrum is enhanced, so the blur direction of the material can be determined by the spectrum. The length of the blurred area in the color sorting image can be determined according to the measurement, and the length can be in pixels. Subsequently, according to the resolution of the color sorting camera and the length of the blurred area in the color sorting image, the length of the blurred area in the color sorting image can be converted into the actual distance as the blurred length of the material. At the same time, the blurred direction of the material in the color sorting image can be determined as the actual movement direction of the material. In addition, for the color sorting image, if there is noise or complex background in the color sorting image, the color sorting image can be processed by denoising such as Gaussian filtering and background segmentation methods such as background difference method, which can effectively improve the extraction accuracy of blurred features.

[0061] Step S1342, determining the moving speed of the material according to the exposure time and blur length of the color sorting camera. According to the color sorting image collected by the color sorting camera, the moving blur of the material, and the blur degree thereof is generally related to the moving speed of the material and the exposure time of the color sorting camera. The moving speed of the material can be determined according to the blur length. Among them, the length of the blur area in the color sorting image can be determined according to the measurement, and according to the resolution of the color sorting camera, the length of the blur area in the color sorting image can be converted into an actual distance as the blur length of the material. According to the blur length of the material and the exposure time of the color sorting camera, the moving speed of the material can be determined. According to the following formula: v=m / texp, the moving speed of the material can be determined. Among them, v is the moving speed of the material, that is, the moving speed of the material at the moment of being photographed by the color sorting camera, texp is the exposure time of the color sorting camera, which is a preset fixed parameter, and m is the blur length. In addition, since the moving speed of the material may produce a certain error, the current system can be calibrated through a calibration experiment, such as a block movement experiment with a known speed, to improve the accuracy of the speed estimation.

[0062] According to the material sorting method provided in this embodiment, the accuracy of judging the direction and speed of material movement can be effectively improved. Through the edge detection algorithm, the elongation direction of the material contour in the color sorting image can be identified, and then the blur direction can be determined, which is the actual direction of movement of the material. Using Fourier transform analysis, the motion blur direction can be further confirmed by the spectral characteristics of the image, thereby improving the robustness of direction recognition. Combining denoising and background segmentation algorithms can reduce the influence of noise and complex background on the judgment of the direction of movement and improve the accuracy of direction extraction. By calculating the exposure time of the color sorting camera and the blur length of the material, the actual movement speed of the material can be accurately determined. Since the materials in the assembly line may have different friction characteristics, shapes, and weights, their movement state may change over time. This method can dynamically calculate the motion parameters at each exposure moment of the color sorting camera, so that the system can adjust the sorting strategy in real time, can accurately sort, reduce the misjudgment rate, and greatly improve the accuracy, adaptability and stability of the sorting system.

[0063] In some embodiments, Figure 7 As shown, step S135, according to the radiographic image, the color sorting image and the mapping relationship between the radiographic image and the color sorting image, determines the theoretical movement direction of the material, and may also include step S1351, step S1352, or step S1351, step S1353.

[0064] Step S1351, determine the theoretical contour of the material in the color sorting image according to the radiographic image and the mapping relationship between the color sorting image and the radiographic image. In determining the theoretical direction of movement of the material in the process of moving from the radiographic device to the color sorting device, the color sorting image and the theoretical image need to be judged in the same dimension. Therefore, some methods can be used to map the color sorting contour and the radiographic contour of the material in the same dimension. Specifically, the radiographic contour can be mapped to the color sorting image according to the mapping relationship between the radiographic image and the color sorting image, as well as the radiographic contour of the material in the radiographic image, so as to determine the theoretical position of the radiographic contour of the material in the radiographic image in the color sorting image under the premise that the material maintains the motion state at the moment of collecting the radiographic image, so that the radiographic contour and the color sorting contour can coexist in the color sorting image, so as to facilitate the determination of the theoretical direction of movement of the material according to the relationship between the radiographic contour and the color sorting contour.

[0065] Step S1352, according to the theoretical contour of the material in the color sorting image and the actual contour of the material in the color sorting image, determine the vector direction from the centroid of the theoretical contour of the material in the color sorting image to the centroid of the actual contour of the material in the color sorting image as the theoretical movement direction of the material. After the theoretical contour of the material ray contour is mapped in the color sorting image, in order to determine the theoretical movement direction of the material, the centroid positions of the theoretical contour and the color sorting contour can be calculated respectively. The centroid can be determined by the coordinate average of the contour points of the theoretical contour and the color sorting contour. The X and Y coordinates of all pixels in the theoretical contour can be weighted averaged to obtain the theoretical centroid; the X and Y coordinates of all pixels in the color sorting contour can be weighted averaged to obtain the color sorting centroid. Subsequently, the vector from the theoretical centroid to the color sorting centroid can be determined, and the direction of the vector can be determined as the theoretical movement direction of the material.

[0066] Step S1353, according to the theoretical contour of the material in the color sorting image and the actual contour of the material in the color sorting image, all contour points of the theoretical contour of the material in the color sorting image are determined, and the vector direction to all contour points of the actual contour of the material in the color sorting image is the theoretical movement direction of the material. The system can extract the coordinate set of all contour points in the theoretical contour and the coordinate set of all corresponding contour points in the color sorting contour. Using the mapping relationship between the color sorting image and the ray image, the most likely corresponding point in the color sorting contour can be found for each point in the theoretical contour. In some cases, the correspondence between the theoretical contour point and the color sorting contour point may not be matched one by one, and the corresponding matching can be achieved through the nearest neighbor algorithm or the matching algorithm based on shape similarity. Subsequently, the system can determine a vector direction for each pair of corresponding points, perform statistical analysis on all vector directions, determine the vector mean, and use the direction of this mean vector as the theoretical movement direction of the material in the color sorting image.

[0067] The material sorting method provided by this embodiment can improve the calculation accuracy of the movement direction by unifying the spatial dimensions of the X-ray image and the color sorting image. Since the acquisition time of the X-ray image and the color sorting image is different, the material may have been displaced, rotated, and deformed, so it is necessary to establish a mapping relationship between the two to ensure that the information is comparable in the same dimension. By mapping the X-ray contour to the color sorting image, the coordinate mismatch problem caused by direct comparison of the X-ray image and the color sorting image is avoided, and the accuracy of data fusion is improved. The system can more accurately determine the theoretical movement direction of the material and provide more accurate motion parameters for subsequent sorting strategies. In addition, the reliability of sorting can also be improved to avoid misclassification due to abnormal material movement trajectory. By optimizing the sorting execution strategy, unnecessary sorting errors can be reduced, and sorting efficiency and sorting accuracy can be improved.

[0068] In some embodiments, Figure 8As shown, step S110 determines the relative motion state of the material and the conveyor belt according to the radiographic image, the color sorting image, and the mapping relationship between the radiographic image and the color sorting image of the material respectively obtained by the radiation device and the color sorting camera, and may include: step S111 and step S112.

[0069] Step S111, according to the color sorting image and the mapping relationship between the ray image and the color sorting image, determine the theoretical position of the color sorting contour of the material on the ray image as the theoretical ray contour. In the process of determining the relative motion state of the material and the conveyor belt according to the color sorting image and the ray image, it is necessary to judge the color sorting image and the theoretical image in the same dimension. Therefore, some methods can be used to map the color sorting contour and the ray contour of the material to the same dimension. Specifically, according to the mapping relationship between the ray image and the color sorting image, and the color sorting contour of the material in the color sorting image, the color sorting contour can be mapped to the ray image, so as to determine the theoretical position of the color sorting contour of the material in the ray image under the premise that the material maintains the motion state at the time of color sorting image acquisition, as the theoretical ray contour.

[0070] Step S112, determine the relative motion state of the material and the conveyor belt according to the theoretical ray profile and the actual ray profile in the ray image. The theoretical ray profile can be compared with the actual ray profile, and the relative motion state of the material and the conveyor belt can be determined according to the degree of difference between the theoretical ray profile and the actual ray profile. Since the material may move or rotate in any direction relative to the conveyor belt during the movement process, the deviation between the theoretical ray profile and the actual ray profile may include position deviation and rotation deviation. The relative motion state of the material and the conveyor belt can be determined according to the deviation between the theoretical ray profile and the actual ray profile. If the theoretical ray profile and the actual ray profile basically coincide, it means that there is no significant relative motion between the material and the conveyor belt after the ray image is acquired and during the period from the acquisition of the color sorting image, and it can be considered that the material remains stable. If there is a significant deviation between the theoretical ray profile and the actual ray profile, it means that there is relative motion between the material and the conveyor belt.

[0071] Through the material sorting method provided in this embodiment, the material contours under different imaging mechanisms can be mapped to the same coordinate space, avoiding the accumulation of errors caused by coordinate deviations, using the contour information of the color sorting image to determine the theoretical position of the material in the radiographic image, and accurately judging the movement state of the material relative to the conveyor belt by comparing the theoretical radiographic contour with the actual radiographic contour, which can provide more reliable data support for subsequent analysis. By comparing the theoretical radiographic contour with the actual radiographic contour, the degree of material deviation can be quantified, and the accuracy of judging the movement state of the material can be improved, thereby ensuring that the sorting device can accurately predict the trajectory of the material reaching the sorting position, reduce the misclassification rate, and improve the overall sorting efficiency and accuracy.

[0072] In some embodiments, Fig. 9 As shown, step S112, determining the relative motion state of the material and the conveyor belt according to the theoretical ray profile and the actual ray profile in the ray image, may include: steps S1121 to S1124.

[0073] Step S1121 matches the theoretical ray profile with the actual ray profile to determine multiple point pairs. The theoretical profile and the actual profile can be matched according to the mapping relationship between the ray image and the color sorting image, so that each contour point of the theoretical ray profile is matched one by one with each contour point of the actual ray profile, thereby obtaining multiple point pairs. The matching method of the contour point can be: nearest neighbor point matching, for each point on the theoretical ray profile, the closest point is found in the actual ray profile as the matching point. The iterative closest point algorithm can also be used to make it possible to more accurately match the contour points of the actual ray profile and the contour points of the theoretical ray profile.

[0074] Step S1122 determines the degree of deviation of the material based on the distance of each point pair. After completing the point pair matching, the spatial deviation between each point pair in the theoretical ray profile and the actual ray profile can be calculated, that is, the displacement of the material in different images. If the movement state of the material on the conveyor belt remains stable, the theoretical ray profile and the actual ray profile should be highly overlapped, and the distance between the corresponding point pairs should be close to zero; but if the material slips, rotates or jumps on the conveyor belt, the distance between these point pairs will increase significantly. By counting the distances of all point pairs, the degree of deviation of the material can be determined, so as to facilitate the subsequent and further determination of whether the material remains relatively stationary with the conveyor belt.

[0075] In step S1123, if the degree of deviation is less than or equal to the contour deviation threshold, it is determined that the material and the conveyor belt are in a relatively static state. For the degree of deviation of the material, a contour deviation threshold can be preset, which represents the range of small jitters that may exist in the material under normal conveyor belt operation. When the degree of deviation of multiple point pairs is within the threshold range, it means that the movement of the material is basically consistent with the conveyor belt, and no significant slip or rotation occurs. At this point, it can be considered that the material and the conveyor belt are in a relatively static state, that is, the material remains stable throughout the entire transmission process, and the time and position of its arrival at the sorting device can be directly calculated based on the running speed of the conveyor belt. In this state, the sorting equipment can complete the material sorting according to the predetermined trajectory without the need for additional motion compensation calculations, thereby improving the sorting accuracy and response speed.

[0076] In step S1124, if the deviation is greater than the profile deviation threshold, it is determined that the material and the conveyor belt are in relative motion. If the deviation of the material exceeds the set profile deviation threshold, it means that the material has undergone significant displacement or rotation in the process of moving from the ray device to the color sorting camera, which indicates that the material is in motion relative to the conveyor belt. In this state, directly calculating the sorting time and position of the material according to the conveyor belt speed may result in large errors, so it is necessary to further determine its actual motion trajectory based on the motion blur information of the material.

[0077] The material sorting method provided by the present embodiment, wherein, by comparing the theoretical ray profile with the actual ray profile and determining the corresponding point pair, the matching accuracy can be improved, and the wrong matching caused by rotation or noise can be avoided, thereby improving the accuracy of determining the motion state of the material. By determining the distance of the point pair to calculate the offset of the ray profile, the degree of deviation of the material can be accurately determined, and the relative movement of the material can be accurately analyzed. By comparing the degree of deviation of the material with the deviation threshold, the motion state of the material is determined, and stable materials and unstable materials can be effectively distinguished. That is, materials that remain relatively stationary with the conveyor belt and materials that move relative to the conveyor belt. According to the different relative motion states of the material and the conveyor belt, different sorting strategies are determined, which can reduce misjudgments, optimize the sorting process, improve sorting precision and accuracy, and reduce the waste of resources caused by incorrect sorting.

[0078] In some embodiments, Fig.10 As shown, step S1122: determining the degree of deviation of the material according to the distance between each point pair may include: steps S11221 to S11223.

[0079] Step S11221, based on multiple point pairs, determine the distance between the two points of each point pair. After the mapping relationship between the ray image and the color sorting image is established, the theoretical ray profile is matched with the actual ray profile, and multiple point pairs are selected. Each point pair consists of a point on the theoretical ray profile and a corresponding point on the actual ray profile. In this step, the distance between the two points in these point pairs can be calculated, that is, the degree of deviation between the theoretical position of each point on the material profile in the theoretical ray profile and the actual position in the actual profile. This distance can intuitively reflect the position change of the material at the time of shooting by the color sorting camera relative to the time of shooting by the ray device, and provide more accurate information for subsequent judgment of the movement state of the material.

[0080] Step S11222, based on the distance between the two points of each point pair, exclude abnormal point pairs, and determine the average, standard deviation, and maximum value of the Euclidean distance of multiple target point pairs. Since there may be abnormal point pairs in the matching process, such as incorrect matching point pairs caused by noise, illumination changes, or image edge errors, it is necessary to remove abnormal point pairs. Specifically, statistical methods can be used to exclude point pairs with abnormally large distances, the distance distribution of all point pairs can be calculated, and extreme offset points exceeding a certain threshold can be removed, or a median filter method or an abnormality detection method based on standard deviation can be used to ensure that the selected point pairs can represent the overall movement trend of the material. After the abnormal point pairs are removed, the average, standard deviation, and maximum value of the Euclidean distance can be calculated based on the remaining target point pairs: wherein the distance average can reflect the degree of overall material offset, that is, the overall trend of relative movement of the material on the conveyor belt. The standard deviation can reflect the stability of the material movement. If the standard deviation is large, it means that the movement state of the material is relatively uneven, and there may be rotation or irregular sliding. The maximum value can be used to determine whether there is a large deviation in a local area. For example, one end of the material slides far while the other end is relatively stable, which may indicate that the material has flipped or tilted.

[0081] Step S11223, determine the degree of deviation of the material according to the average value, standard deviation, and maximum value of the distances of multiple target point pairs. According to the determined average value, standard deviation, and maximum value of the distances of the target point pairs, the degree of deviation of the material can be quantified, thereby providing more accurate data support for subsequent sorting strategies. Specifically, if the average value of the distances of multiple target point pairs is close to zero, the standard deviation is small, and the maximum value is also small, it can be determined that the material remains basically stable during the transmission process and is in a relatively static state with the conveyor belt. If the average value of the distances of multiple target point pairs is large, the standard deviation is moderate, and the maximum value does not exceed a certain range, it can be determined that the material as a whole has slipped, but still maintains a certain stability. If the standard deviation of the distances of multiple target point pairs is large, and the maximum value is much larger than the average value, it may indicate that the material has rotated or tumbled, resulting in large differences in the degree of deviation of different parts.

[0082] According to the material sorting method provided in this embodiment, by calculating the distance of each point pair, the displacement of the material can be accurately calculated, intuitively reflecting the movement of the material relative to the conveyor belt, and at the same time, the offset information of each point can be quantified, which is helpful for further analyzing the overall motion state. By eliminating abnormal point pairs, the reliability of matching point pairs can be improved, and the interference of abnormal data on the results can be avoided. After obtaining the statistical parameters of the target point pairs, threshold rules can be set to determine the offset of the material relative to the conveyor belt, so that the relative motion state of the material and the conveyor belt can be judged more accurately, which can improve the accuracy and efficiency of the subsequent sorting strategy determination, thereby improving the efficiency and accuracy of material sorting.

[0083] 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. Certain features, structures or characteristics in one or more embodiments of the present application can be appropriately combined.

[0084] 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.

[0085] 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 mentioned in the claims. In fact, the features of the embodiments are less than all the features of the single embodiment disclosed above.

[0086] The basic concepts have been described above. Obviously, for those skilled in the art, the above disclosure is only an 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, applied to a material sorting device, comprising: Determine the relative motion state of the material and the conveyor belt according to the radiographic image and the color sorting image of the material respectively obtained by the radiographic device and the color sorting camera, and the mapping relationship between the radiographic image and the color sorting image; If it is determined that the material and the conveyor belt are in a relatively static state, then a material sorting strategy is determined according to the radiographic image, the distance between the color sorting camera and the radiographic device, and the running speed of the conveyor belt, wherein the sorting strategy includes a sorting time and a sorting position; If it is determined that the material and the conveyor belt are in a relative motion state, a sorting strategy is determined according to the motion blur of the material in the color sorting image; According to the sorting strategy, a sorting operation is performed on the material.

2. The material sorting method according to claim 1, wherein: Determining a sorting strategy according to the motion blur of the material in the color sorting image includes: Determining the degree of motion blur of the material in the sorted image; If the degree of motion blur is less than the motion blur threshold, a material sorting strategy is determined according to the radiographic image, the distance between the color sorting camera and the sorting mechanism, and the conveyor belt running speed; If the motion blur degree is greater than or equal to the motion blur threshold, the material sorting time is determined according to the motion blur of the material.

3. The material sorting method according to claim 2, wherein: The step of determining the material sorting time according to the motion blur of the material comprises: Determine the speed of the material reaching the ray device according to the distance between the ray device and the color sorting camera, the speed of the material when it reaches the color sorting camera, and the time it takes for the material to move from the ray device to the color sorting camera; Determine the acceleration of the material according to the speed of the material when it reaches the color sorting camera, the time it takes for the material to move from the radiation device to the color sorting camera, and the speed of the material when it reaches the radiation device; The material sorting time is determined according to the acceleration of the material, the speed of the material when it reaches the color sorting camera, and the speed of the material when it reaches the radiation device.

4. The material sorting method according to claim 3, wherein: Determining the material sorting time according to the acceleration of the material, the speed of the material when it reaches the color sorting camera, and the speed of the material when it reaches the radiation device includes: Determine the relative motion state of the material with respect to the conveyor belt before reaching the sorting device according to the acceleration of the material, the speed of the material when reaching the color sorting camera, and the speed of the material when reaching the ray device; If the material is relatively stationary with the conveyor belt before reaching the sorting device, the time required for the material and the conveyor belt to reach relative stationary state and the time required for the material and the conveyor belt to move to the sorting device after reaching relative stationary state are determined as the material sorting time; If the material moves relative to the conveyor belt before reaching the sorting device, the sorting time of the material is determined according to the acceleration of the material, the speed of the material when it reaches the color sorting camera, the movement speed of the conveyor belt, and the distance between the color sorting device and the sorting device.

5. The material sorting method according to claim 2, wherein: The determining of the material sorting time according to the motion blur of the material further includes: Determine the actual moving direction and moving speed of the material according to the motion blur of the material; Determining a theoretical moving direction of the material according to the radiographic image, the color sorting image, and a mapping relationship between the radiographic image and the color sorting image; Determining the deviation of the actual movement direction of the material from the theoretical movement direction of the material; If the deviation between the actual movement direction of the material and the theoretical movement direction of the material is less than the movement deviation threshold, the material sorting strategy is determined according to the radiographic image, the distance between the color sorting camera and the radiographic device, and the conveyor belt running speed; If the deviation between the actual moving direction of the material and the theoretical moving direction of the material is greater than or equal to the movement deviation threshold, the sorting operation on the material according to the sorting strategy is skipped.

6. The material sorting method according to claim 5, wherein: The determining the theoretical movement direction of the material according to the radiographic image, the color sorting image, and the mapping relationship between the radiographic image and the color sorting image includes: Determining a theoretical profile of the material in the color sorting image according to the radiographic image and a mapping relationship between the color sorting image and the radiographic image; According to the theoretical contour of the material in the color sorting image and the actual contour of the material in the color sorting image, determine the vector direction from the centroid of the theoretical contour of the material in the color sorting image to the centroid of the actual contour of the material in the color sorting image as the theoretical movement direction of the material; or, According to the theoretical contour of the material in the color sorting image and the actual contour of the material in the color sorting image, all contour points of the theoretical contour of the material in the color sorting image are determined, and the vector direction to all contour points of the actual contour of the material in the color sorting image is the theoretical movement direction of the material.

7. The material sorting method according to claim 5, wherein: The determining the actual moving direction and moving speed of the material according to the motion blur of the material comprises: According to the motion blur of the material, determining the blur direction and blur length of the material, and determining the blur direction as the actual motion direction of the material; The moving speed of the material is determined according to the exposure time of the color sorting camera and the blur length.

8. The material sorting method according to claim 1, wherein: The method of determining the relative motion state of the material and the conveyor belt according to the radiographic image, the color sorting image, and the mapping relationship between the radiographic image and the color sorting image of the material respectively obtained by the radiation device and the color sorting camera includes: According to the color sorting image and the mapping relationship between the radiographic image and the color sorting image, determining a theoretical position of the color sorting contour of the material on the radiographic image as a theoretical radiographic contour; The relative motion state of the material and the conveyor belt is determined based on the theoretical ray profile and the actual ray profile in the ray image.

9. The material sorting method according to claim 8, wherein: Determining the relative motion state of the material and the conveyor belt according to the theoretical ray profile and the actual ray profile in the ray image includes: Matching the theoretical ray profile with the actual ray profile to determine a plurality of point pairs; Determining the degree of deviation of the material according to the distance between each pair of points; If the degree of deviation is less than or equal to the profile deviation threshold, it is determined that the material and the conveyor belt are in a relatively static state; If the degree of deviation is greater than the profile deviation threshold, it is determined that the material and the conveyor belt are in a relative motion state.

10. The material sorting method according to claim 9, wherein: Determining the deviation degree of the material according to the distance of each point pair includes: Based on a plurality of point pairs, determining the distance between two points of each point pair; According to the distance between the two points of each point pair, the abnormal point pairs are excluded, and the average value, standard deviation and maximum value of the Euclidean distance of multiple target point pairs are determined; Determine the degree of deviation of the material based on the average, standard deviation, and maximum value of the distances between multiple target point pairs.

Citation Information

Patent Citations

  • Material sorting system and sorting method

    CN114798488A

  • Automatic sorting system for regenerated aluminum alloy raw materials

    CN117252784A

  • Intelligent ore sorting equipment and method based on visible light and X-ray image fusion

    CN117299581A

  • Material sorting method and material sorting device

    CN119259504A

  • Material sorting method, sorting equipment and computer readable storage medium

    CN119588642A

Cited By

  • Target area identification method, image acquisition system and sorting machine

    CN121504969A