Tobacco material flow detection method, device and computer equipment

Abstract

The present application relates to a method, device, computer equipment, storage medium and computer program product for detecting the flow rate of tobacco materials. The method includes: determining the cross-sectional area of the materials on the conveyor belt at each acquisition moment within each material passing time period according to the measured width of the conveyor belt, the first depth value set, the included angle and each second depth value set; determining the average material density on the conveyor belt within all material passing time periods according to the cross-sectional area of the materials on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period; and determining the material flow rate on the conveyor belt at each acquisition moment within each material passing time period according to the average material density. By using this method, the material flow rate of cigarette manufacturing enterprises can be precisely controlled and the management efficiency can be improved.

Description

Technical Field

[0001] The present application relates to the technical field of tobacco material flow control, and particularly to a method, device, and computer equipment for detecting the flow rate of tobacco materials. Background Art

[0002] In the process of cigarette manufacturing, in order to ensure the process quality, strict flow control is required in each process of the wire-making process. At present, in the wire-making production process, the flow rate of the belt feeding is mainly judged by an electronic scale. However, due to the high cost and large volume of the electronic belt, and the high installation requirements of the electronic belt, a non-horizontal belt will affect the accuracy of the electronic scale. When the inclination angle of the horizontal plane of the electronic belt is large, the flow rate cannot be measured by the electronic scale. Therefore, there is an urgent need for a method for detecting the flow rate of tobacco materials at present. Summary of the Invention

[0003] Based on this, in view of the above technical problems, it is necessary to provide a method, device, computer equipment, computer-readable storage medium, and computer program product for detecting the flow rate of tobacco materials.

[0004] In a first aspect, the present application provides a method for detecting the flow rate of tobacco materials. The method includes:

[0005] In the case where there is no material on the conveyor belt, obtain a first depth map of the conveyor belt collected by a 3D structured light camera, where the first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point;

[0006] Determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinates of the first midline;

[0007] Perform multi-segment equal division on the first midline, and form a first depth value set from the depth values of the pixels corresponding to each endpoint coordinate among all the endpoint coordinates of all the equal division lines formed;

[0008] In the case where there is material on the conveyor belt, obtain a second depth map of the conveyor belt within each material passing time period collected by the 3D structured light camera according to a preset collection period, where the material passing time period refers to the time period between the starting moment and the ending moment when the material is conveyed on the conveyor belt;

[0009] Determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map. Divide each second midline into multiple segments equally. The depth values of the pixels corresponding to each endpoint coordinate among all the endpoint coordinates of all the equally divided lines formed constitute the second depth value set corresponding to each second depth map;

[0010] According to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set, determine the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period;

[0011] According to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period, determine the average material density on the conveyor belt during all material passing time periods;

[0012] According to the average material density, determine the material flow rate on the conveyor belt at each acquisition moment within each material passing time period.

[0013] In one embodiment, according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinates of the first midline, determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, including:

[0014]

[0015] In formula (1), θ is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, z a and z b are the depth values of the pixels corresponding to the two endpoint coordinates respectively, and D is the measured width.

[0016] In one embodiment, according to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set, determine the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period, including:

[0017]

[0018] In formula (2), z i,1 is the i-th depth value in the first depth value set, z i,t is the i-th depth value in the second depth value set corresponding to the acquisition moment t within each material passing time period, S t is the cross-sectional area of the material on the conveyor belt at the acquisition moment t within each material passing time period, D is the measured width, θ is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, and n is the number of equal segments of the first midline.

[0019] In one embodiment, determining the average material density on the conveyor belt during all material passing time periods according to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and a preset acquisition period includes:

[0020] Determining the volume of the material on the conveyor belt at each acquisition moment within each material passing time period according to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period;

[0021] Summing up the volumes of the material on the conveyor belt at all acquisition moments within each material passing time period to determine the volume of the material on the conveyor belt within each material passing time period;

[0022] Determining the mass of the material on the conveyor belt within each material passing time period;

[0023] Dividing the mass of the material on the conveyor belt within each material passing time period by the volume of the material on the conveyor belt within the corresponding material passing time period to determine the material density on the conveyor belt within each material passing time period;

[0024] Taking the average of the material densities on the conveyor belt during all material passing time periods as the average material density.

[0025] In one embodiment, determining the volume of the material on the conveyor belt at each acquisition moment within each material passing time period according to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period includes:

[0026]

[0027] In formula (3), v is determined based on the motor frequency of the conveyor belt, v is the speed of the conveyor belt; S t is the cross-sectional area of the material on the conveyor belt at the acquisition moment t, V t is the volume of the material on the conveyor belt at the acquisition moment t, F is the frame rate of the 3D structured light camera, δ t is the preset acquisition period, Δt is a constant, and Δt is determined by selecting the maximum value between δ t and

[0028] In one embodiment, determining the material flow rate on the conveyor belt at each acquisition moment within each material passing time period according to the average material density includes:

[0029]

[0030] In formula (4), W t is the material flow rate on the conveyor belt at the acquisition moment t, V t ​Let \(t\) be the volume of the material on the conveyor belt at the acquisition moment, \(\rho\) be the average material density, \(F\) be the frame rate of the 3D structured light camera, and \(\delta\) t be the preset acquisition period, \(\Delta t\) be a constant, and \(\Delta t\) is determined by selecting the maximum value between \(\delta\) t and the two values.

[0031] In a second aspect, the present application also provides a tobacco material flow detection device. The device includes:

[0032] In the case where there is no material on the conveyor belt, obtain the first depth map of the conveyor belt collected by the 3D structured light camera. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point;

[0033] Determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinate points of the first midline;

[0034] Perform multi-segment equal division on the first midline, and form a first depth value set from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed;

[0035] In the case where there is material on the conveyor belt, obtain the second depth map of the conveyor belt in each material passing time period collected by the 3D structured light camera according to the preset acquisition period. The material passing time period refers to the time period between the start moment and the end moment when the material is conveyed on the conveyor belt;

[0036] Determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map, perform multi-segment equal division on each second midline, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed;

[0037] According to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set, determine the cross-sectional area of the material on the conveyor belt at each acquisition moment in each material passing time period;

[0038] According to the cross-sectional area of the material on the conveyor belt at each acquisition moment in each material passing time period and the preset acquisition period, determine the average material density on the conveyor belt in all material passing time periods;

[0039] According to the average material density, determine the material flow rate on the conveyor belt at each acquisition moment in each material passing time period.

[0040] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are implemented:

[0041] In the case where there is no material on the conveyor belt, obtain a first depth map of the conveyor belt collected by a 3D structured light camera. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt. Each pixel in the first depth map corresponds to a coordinate point.

[0042] Determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinate points of the first midline.

[0043] Perform multi-segment equal division on the first midline, and form a first depth value set from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed.

[0044] In the case where there is material on the conveyor belt, obtain a second depth map of the conveyor belt within each material passing time period collected by the 3D structured light camera according to a preset collection period. The material passing time period refers to the time period between the start time and the end time when the material is conveyed on the conveyor belt.

[0045] Determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map, perform multi-segment equal division on each second midline, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed.

[0046] According to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set, determine the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period.

[0047] According to the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period and the preset collection period, determine the average material density on the conveyor belt within all the material passing time periods.

[0048] According to the average material density, determine the material flow rate on the conveyor belt at each collection moment within each material passing time period.

[0049] In a fourth aspect, the present application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon. When the computer program is executed by a processor, the following steps are implemented:

[0050] In the case where there is no material on the conveyor belt, obtain the first depth map of the conveyor belt collected by a 3D structured light camera. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point;

[0051] Determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinate points of the first midline;

[0052] Perform multi-segment equal division on the first midline, and form a first depth value set from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed;

[0053] In the case where there is material on the conveyor belt, obtain the second depth map of the conveyor belt in each material passing time period collected by the 3D structured light camera according to a preset collection period. The material passing time period refers to the time period between the start time and the end time when the material is conveyed on the conveyor belt;

[0054] Determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map, perform multi-segment equal division on each second midline, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed;

[0055] Determine the cross-sectional area of the material on the conveyor belt at each collection moment in each material passing time period according to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set;

[0056] Determine the average material density on the conveyor belt in all material passing time periods according to the cross-sectional area of the material on the conveyor belt at each collection moment in each material passing time period and the preset collection period;

[0057] Determine the material flow rate on the conveyor belt at each collection moment in each material passing time period according to the average material density.

[0058] In a fifth aspect, the present application also provides a computer program product. The computer program product includes a computer program, and when the computer program is executed by a processor, the following steps are implemented:

[0059] In the case where there is no material on the conveyor belt, obtain the first depth map of the conveyor belt collected by a 3D structured light camera. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point;

[0060] Determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinates of the first midline;

[0061] Divide the first midline into multiple segments equally. The depth values of the pixels corresponding to each endpoint coordinate among all the endpoint coordinates of all the equally divided lines formed constitute the first depth value set;

[0062] When there is material on the conveyor belt, obtain the second depth map of the conveyor belt in each material passing time period collected by the 3D structured light camera according to a preset acquisition period. The material passing time period refers to the time period between the start time and the end time when the material is conveyed on the conveyor belt;

[0063] Determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map. Divide each second midline into multiple segments equally. The depth values of the pixels corresponding to each endpoint coordinate among all the endpoint coordinates of all the equally divided lines formed constitute the second depth value set corresponding to each second depth map;

[0064] According to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set, determine the cross-sectional area of the material on the conveyor belt at each acquisition moment in each material passing time period;

[0065] According to the cross-sectional area of the material on the conveyor belt at each acquisition moment in each material passing time period and the preset acquisition period, determine the average material density on the conveyor belt in all material passing time periods;

[0066] According to the average material density, determine the material flow rate on the conveyor belt at each acquisition moment in each material passing time period.

[0067] The above-mentioned tobacco material flow detection method, device, computer device, storage medium and computer program product, in the case where there is no material on the conveyor belt, obtain the first depth map of the conveyor belt collected by the 3D structured light camera; determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinates of the first midline; divide the first midline into multiple segments equally, and form a first depth value set from the depth values of the pixels corresponding to each endpoint coordinate among all the endpoint coordinates of all the equally divided lines formed; in the case where there is material on the conveyor belt, obtain the second depth map of the conveyor belt in each material passing time period collected by the 3D structured light camera according to the preset collection period, determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map, divide each second midline into multiple segments equally, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each endpoint coordinate among all the endpoint coordinates of all the equally divided lines formed; determine the cross-sectional area of the material on the conveyor belt at each collection moment in each material passing time period according to the measured width of the conveyor belt, the first depth value set, the angle and each second depth value set; determine the average material density on the conveyor belt in all material passing time periods according to the cross-sectional area of the material on the conveyor belt at each collection moment in each material passing time period and the preset collection period; determine the material flow on the conveyor belt at each collection moment in each material passing time period according to the average material density. It can enable the refined control of the material flow in cigarette manufacturing enterprises and improve the management efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 It is an application environment diagram of the tobacco material flow detection method in an embodiment;

[0069] Figure 2 It is a schematic flowchart of the tobacco material flow detection method in an embodiment;

[0070] Figure 3 It is a schematic front view of the 3D structured light camera and the conveyor belt in an embodiment;

[0071] Figure 4 It is a schematic top view of the 3D structured light camera and the conveyor belt in an embodiment;

[0072] Figure 5 It is a schematic side view of the 3D structured light camera and the conveyor belt in an embodiment;

[0073] Figure 6 It is a schematic diagram of the 3D structured light camera taking a depth map in an embodiment;

[0074] Figure 7 Schematic diagram of the first depth map in one embodiment;

[0075] Figure 8 Schematic diagram for calculating the cross-sectional area of the material on the conveyor belt at the t acquisition moment in each material passing time period in one embodiment;

[0076] Figure 9 Flow chart of the tobacco material flow detection method in another embodiment;

[0077] Figure 10 Structural block diagram of the tobacco material flow detection device in one embodiment;

[0078] Figure 11 Internal structure diagram of a computer device in one embodiment. Detailed implementation manners

[0079] In order to make the objectives, technical solutions and advantages of the present application clearer and more understandable, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0080] The tobacco material flow detection method provided by the embodiments of the present application can be applied to an application environment as Figure 1 shown. Among them, the terminal 101 communicates with the server 102 through a network. The data storage system can store the data that the server 102 needs to process. The data storage system can be integrated on the server 102, or can be placed in the cloud or other network servers. Among them, the terminal 101 can be, but is not limited to, various personal computers, laptop computers, tablet computers and Internet of Things devices. The server 102 can be implemented by an independent server or a server cluster composed of multiple servers.

[0081] In one embodiment, as Figure 2 shown, a tobacco material flow detection method is provided. Taking the method applied to the Figure 1 terminal as an example, the method includes the following steps:

[0082] 201. In the case where there is no material on the conveyor belt, obtain the first depth map of the conveyor belt collected by the 3D structured light camera. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point;

[0083] 202. Determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two end point coordinates of the first midline;

[0084] 203. Perform multi-segment equal division on the first center line, and form a first depth value set from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed.

[0085] 204. In the case where there is material on the conveyor belt, obtain the second depth map of the conveyor belt within each material passing time period collected by the 3D structured light camera according to a preset collection period. The material passing time period refers to the time period between the start time and the end time when the material is conveyed on the conveyor belt.

[0086] 205. Determine the center line of the conveyor belt in each second depth map as the second center line corresponding to the second depth map. Perform multi-segment equal division on each second center line, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed.

[0087] 206. Determine the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period according to the measured width of the conveyor belt, the first depth value set, the included angle, and each second depth value set.

[0088] 207. Determine the average material density on the conveyor belt within all the material passing time periods according to the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period and the preset collection period.

[0089] 208. Determine the material flow rate on the conveyor belt at each collection moment within each material passing time period according to the average material density.

[0090] In the above step 201, the front view, top view, and side view of the 3D structured light camera and the conveyor belt are respectively as Figure 3 、 Figure 4 and Figure 5 shown. The schematic diagram of the 3D structured light camera taking the depth map is as Figure 6 shown, where the plane where the camera of the 3D structured light camera is located is perpendicular to the plane where the conveyor belt is located. The 3D structured light camera can collect the depth map, and the information in the depth map includes coordinate points and depth values.

[0091] The 3D structured light camera is connected to the tobacco material control system. The depth map collected by the 3D structured light camera is transmitted to the tobacco material control system in real time, and the tobacco material control system calculates according to the received depth map to determine the real-time material flow rate on the conveyor belt.

[0092] Based on the vision technology of 3D structured light cameras, the overfeed flow rate on the conveyor belt during the cigarette making process can be discriminated in real time. In this application, the material flow rate also refers to the overfeed flow rate on the conveyor belt, and the material refers to cut tobacco or tobacco leaves with a brand. For the specific type of the material, the present invention does not make specific limitations. For example, the material can be any one of tobacco material types such as cut tobacco of brand A, cut tobacco of brand B, cut tobacco of brand C, tobacco leaves of brand D, or tobacco leaves of brand E.

[0093] The first depth map is as Figure 7 shown. The first midline in step 202 above is parallel to the bottom edge of the first depth map. Each pixel in the first depth map corresponds to a depth value.

[0094] In step 202 above, the measured width data of the conveyor belt is stored in the tobacco material control system. The tobacco material control system can calculate based on the measured width of the conveyor belt and the first depth map to determine the real-time material flow rate on the conveyor belt.

[0095] In addition, after the position of the 3D structured light camera is adjusted, it will not change. Therefore, when the positions of both the 3D structured light camera and the conveyor belt remain unchanged, the angle between the plane where the 3D structured light camera's camera is located and the plane where the conveyor belt is located is unchanged; if the position of the 3D structured light camera or the position of the conveyor belt changes, the angle between the plane where the 3D structured light camera's camera is located and the plane where the conveyor belt is located will change.

[0096] In step 203 above, the first midline is equally divided into multiple segments. Among them, the number of segments for equal division is determined according to actual needs, and the present invention's embodiments do not make specific limitations on it. The number of depth values in the first depth value set is related to the number of segments for equal division. For example, if the first midline is equally divided into n segments, the coordinate points of all endpoints of all equal division lines are p1, p2, p3,..., p n+1 , and the depth values in the first depth value set are z1, z2, z3,..., z n+1 .

[0097] In step 204 above, the preset acquisition period means setting the 3D structured light camera so that the 3D structured light camera performs a depth map acquisition on the conveyor belt every same time period. The material passing through the conveyor belt within each overfeed time period corresponds to a batch of materials.

[0098] Optionally, the 3D structured light camera can also perform depth map acquisition on the conveyor belt at different time intervals. That is, the time intervals between every two consecutive depth map acquisitions by the 3D structured light camera can be the same or different. Correspondingly, when there is material on the conveyor belt, according to the 3D structured light camera, depth maps of the conveyor belt are acquired at each acquisition moment within each material passing time period, and the acquisition interval duration corresponding to each acquisition moment is determined. The acquisition interval duration corresponding to each acquisition moment refers to the interval duration between the acquisition moment corresponding to the depth map at each acquisition moment and the next consecutive acquisition moment.

[0099] In addition, within one material passing time period, the grade and type of the material on the conveyor belt remain the same all the time. While in the next material passing time period, the material on the conveyor belt can be the same as or different from the material in the previous material passing time period in terms of grade and type.

[0100] In the above step 205, the positions of the 3D structured light camera and the conveyor belt when each second depth map is taken are the same as those when the first depth map is taken. Therefore, the midline of the conveyor belt in each second depth map is in the same position as the first midline in the above step 202.

[0101] In addition, the number of equal segments of each second midline is the same as that of the first midline. For example, if the first midline is equally divided into n segments, then each second midline is also equally divided into n segments, where n is an integer not less than 1. Correspondingly, the number of depth values in each second depth value set is n + 1.

[0102] Optionally, if the time interval between every two consecutive acquisition moments of the 3D structured light camera is different, then determine the time interval between every two consecutive acquisition moments of the 3D structured light camera as the acquisition duration of the acquisition moment that comes earlier in the corresponding two consecutive acquisition moments. According to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the acquisition duration corresponding to each acquisition moment, determine the average material density on the conveyor belt within all material passing time periods. For example, if the t acquisition moment and the t + 1 acquisition moment are two consecutive acquisition moments, and the interval duration between the t acquisition moment and the t + 1 acquisition moment is determined to be s, then s is taken as the acquisition duration of the t acquisition moment.

[0103] Specifically, according to the average material density, the mass of the material on the conveyor belt at each acquisition moment within each material passing time period can be determined, and according to the mass of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period, the material flow rate on the conveyor belt at each acquisition moment within each material passing time period can be determined.

[0104] The method provided by the embodiment of the present invention is based on the vision technology of a 3D structured light camera to determine the material flow rate on the conveyor belt at each acquisition moment during the wire-making production process, which can improve the accuracy of the material flow rate. At the same time, it can also improve the recognition speed of the material flow rate, so that the material flow of cigarette manufacturing enterprises can be finely controlled and the management efficiency can be improved.

[0105] Combined with the content of the above embodiments, in one embodiment, according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinate points of the first midline, to determine the included angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, including:

[0106]

[0107] In formula (5), θ is the included angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, z a and z b are respectively the depth values of the pixels corresponding to the two endpoint coordinate points, and D is the measured width of the conveyor belt.

[0108] Among them, the included angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located is fixed and unchanged.

[0109] Specifically, the measured width of the conveyor belt is stored in the tobacco material control system. The tobacco material control system calculates according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinate points of the first midline according to formula (5), and can determine the included angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located.

[0110] The method provided by the embodiment of the present invention determines the included angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinate points of the first midline.

[0111] Combined with the content of the above embodiments, in one embodiment, according to the measured width of the conveyor belt, the first depth value set, the included angle, and each second depth value set, to determine the material cross-sectional area on the conveyor belt at each acquisition moment within each material passing time period, including:

[0112]

[0113] In formula (6), z i,1 is the i-th depth value in the first depth value set, z i,t is the i-th depth value in the second depth value set corresponding to the t acquisition moment within each material passing time period, S tCollect the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period t. D is the measured width of the conveyor belt, θ is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, and n is the number of equal segments of the first median line.

[0114] Specifically, the schematic diagram for calculating the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period t is as Figure 8 shown, Figure 8 where θ is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, D is the measured width of the conveyor belt, z i,1 is the i-th depth value in the first depth value set, and z i,t is the i-th depth value in the second depth value set corresponding to each acquisition moment within each material passing time period t. S t is the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period t.

[0115] The method provided by the embodiments of the present invention can determine the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period through the measured width of the conveyor belt, the first depth value set, the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, and each second depth value set.

[0116] Combined with the content of the above embodiments, in one embodiment, according to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period, determine the average material density on the conveyor belt within all material passing time periods, including:

[0117] Determine the volume of the material on the conveyor belt at each acquisition moment within each material passing time period according to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period;

[0118] Sum up the volumes of the material on the conveyor belt at all acquisition moments within each material passing time period to determine the volume of the material on the conveyor belt within each material passing time period;

[0119] Determine the mass of the material on the conveyor belt within each material passing time period;

[0120] Divide the mass of the material on the conveyor belt within each material passing time period by the volume of the material on the conveyor belt within the corresponding material passing time period to determine the material density on the conveyor belt within each material passing time period;

[0121] Take the average value of the material densities on the conveyor belt within all material passing time periods as the average material density.

[0122] Among them, the mass of the material on the conveyor belt in each material passing time period corresponds to the total mass of the material in one batch; the total mass of the material in each batch can be determined by querying the production layout plan of the cigarette making workshop, and the unit of the queried material mass is Kg.

[0123] In one embodiment, summing the material volumes on the conveyor belt at all acquisition times in each material passing time period to determine the material volume on the conveyor belt in each material passing time period, including:

[0124]

[0125] In formula (7), V i is the material volume on the conveyor belt in the i-th material passing time period, t1 is the starting time when the material is conveyed on the conveyor belt in the i-th material passing time period, t2 is the ending time when the material is conveyed on the conveyor belt in the i-th material passing time period, and V t is the material volume on the conveyor belt at the t-th acquisition time in the i-th material passing time period.

[0126] In one embodiment, dividing the material mass on the conveyor belt in each material passing time period by the material volume on the conveyor belt in the corresponding material passing time period to determine the material density on the conveyor belt in each material passing time period, including:

[0127]

[0128] In formula (8), ρ i is the material density on the conveyor belt in the i-th material passing time period, M i is the material mass on the conveyor belt in the i-th material passing time period, V i is the material volume on the conveyor belt in the i-th material passing time period, and i is a constant.

[0129] In one embodiment, averaging the material densities on the conveyor belt in all material passing time periods as the average material density, including:

[0130]

[0131] In formula (9), ρ i is the material density on the conveyor belt in the i-th material passing time period, m is an integer not less than 1, m represents that there are m material passing time periods for the material, ρ represents the average material density, and i is a constant.

[0132] The method provided by the embodiment of the present invention can determine the average material density on the conveyor belt in all material passing time periods through the cross-sectional area of the material on the conveyor belt at each acquisition time in each material passing time period and the preset acquisition period.

[0133] Combined with the content of the above embodiments, in one embodiment, determining the material volume on the conveyor belt at each acquisition moment within each material passing time period according to the cross-sectional area of the material on the conveyor belt at each acquisition moment and the preset acquisition period includes:

[0134]

[0135] In formula (10), v is determined based on the motor frequency of the conveyor belt, and v is the speed of the conveyor belt; S t is the cross-sectional area of the material on the conveyor belt at the acquisition moment t, V t is the material volume on the conveyor belt at the acquisition moment t, F is the frame rate of the 3D structured light camera, δ t is the preset acquisition period, Δt is a constant, and Δt is determined by selecting the maximum value between δ t and

[0136] The calculation formula for the speed of the conveyor belt includes: v = k * f, where v is the speed of the conveyor belt, k is a constant, and f is the motor frequency of the conveyor belt. It is worth mentioning that the motor frequency of the conveyor belt is obtained through a PLC (Programmable Logic Controller).

[0137] The method provided by the embodiments of the present invention can determine the material volume on the conveyor belt at each acquisition moment within each material passing time period according to the cross-sectional area of the material on the conveyor belt at each acquisition moment and the preset acquisition period.

[0138] Combined with the content of the above embodiments, in one embodiment, determining the material flow rate on the conveyor belt at each acquisition moment within each material passing time period according to the average material density includes:

[0139]

[0140] In formula (11), W t is the material flow rate on the conveyor belt at the acquisition moment t, V t is the material volume on the conveyor belt at the acquisition moment t, ρ is the average material density, F is the frame rate of the 3D structured light camera, δ t is the preset acquisition period, Δt is a constant, and Δt is determined by selecting the maximum value between δ t and

[0141] ​​Specifically, after the tobacco flow control system calculates the material flow on the conveyor belt at each collection moment within each material passing time period based on the average material density, it will transmit the material flow on the conveyor belt at each collection moment within each material passing time period to the cut tobacco control system.

[0142] The method provided by the embodiment of the present invention can determine the material flow on the conveyor belt at each collection moment within each material passing time period according to the average material density, so that the cut tobacco control system can perform coordinated control and improve the accuracy of the control of the cut tobacco control system.

[0143] In one embodiment, a method for detecting the flow of tobacco materials is as Figure 9 shown, and the method further includes:

[0144] 901. Determine the measured width D of the conveyor belt, obtain the conveyor speed v of the conveyor belt, and the frame rate F of the 3D structured light camera;

[0145] 902. When there is no material on the conveyor belt, obtain the first depth map of the conveyor belt through the 3D structured light camera;

[0146] 903. When there is material on the conveyor belt, obtain the second depth map of the conveyor belt at each moment within each material passing time period through the 3D structured light camera, and determine the interval duration corresponding to each moment of the conveyor belt within each material passing time period;

[0147] 904. Determine the material flow on the conveyor belt at each collection moment within each material passing time period according to the measured width D of the conveyor belt, the conveyor speed of the conveyor belt, the frame rate of the 3D structured light camera, the first depth map of the conveyor belt, the second depth map of the conveyor belt at each moment within each material passing time period, and the interval duration corresponding to each moment of the conveyor belt within each material passing time period.

[0148] The method provided by the embodiment of the present invention can finely control the material flow of cigarette manufacturing enterprises and improve management efficiency according to the measured width D of the conveyor belt, the conveyor speed of the conveyor belt, the frame rate of the 3D structured light camera, the first depth map of the conveyor belt, the second depth map of the conveyor belt at each moment within each material passing time period, and the interval duration corresponding to each moment of the conveyor belt within each material passing time period.

[0149] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown in sequence according to the indications of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise clearly stated in this article, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0150] Based on the same inventive concept, an embodiment of the present application further provides a tobacco material flow detection device for implementing the tobacco material flow detection method described above. The solution provided by this device to solve the problem is similar to the solution described in the above method. Therefore, the specific limitations in one or more embodiments of the tobacco material flow detection device provided below can refer to the limitations on the tobacco material flow detection method in the above text, and will not be repeated here.

[0151] In one embodiment, as Figure 10 shown, a tobacco material flow detection device is provided, including: an acquisition module 1011, a first determination module 1012, an equal division module 1013, a collection module 1014, a second determination module 1015, a third determination module 1016, a fourth determination module 1017, and a fifth determination module 1018, where:

[0152] The acquisition module 1011 is configured to obtain a first depth map of the conveyor belt collected by a 3D structured light camera when there is no material on the conveyor belt. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point;

[0153] The first determination module 1012 is configured to determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two end point coordinates of the first midline;

[0154] The equal division module 1013 is configured to perform multi-segment equal division on the first midline, and form a first depth value set from the depth values of the pixels corresponding to each end point coordinate among all the end point coordinates of all the equal division lines formed;

[0155] The acquisition module 1014 is configured to, when there is material on the conveyor belt, obtain a second depth map of the conveyor belt within each material passing time period collected by the 3D structured light camera according to a preset acquisition period, where the material passing time period refers to the time period between the start time and the end time when the material is conveyed on the conveyor belt;

[0156] The second determination module 1015 is configured to determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map, equally divide each second midline into multiple segments, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equally divided lines;

[0157] The third determination module 1016 is configured to determine the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period according to the measured width of the conveyor belt, the first depth value set, the included angle, and each second depth value set;

[0158] The fourth determination module 1017 is configured to determine the average material density on the conveyor belt within all the material passing time periods according to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period;

[0159] The fifth determination module 1018 is configured to determine the material flow rate on the conveyor belt at each acquisition moment within each material passing time period according to the average material density;

[0160] In one embodiment, the first determination module 1012 includes:

[0161]

[0162] In formula (12), θ is the included angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, z a and z b are respectively the depth values of the pixels corresponding to the two endpoint coordinate points, and D is the measured width.

[0163] In one embodiment, the third determination module 1014 includes:

[0164]

[0165] In formula (13), z i,1 is the i-th depth value in the first depth value set, z i,t is the i-th depth value in the second depth value set corresponding to the t acquisition moment within each material passing time period, S tFor each material passing time period \(t\), collect the cross-sectional area of the material on the conveyor belt at the acquisition moment. \(D\) is the measurement width, \(\theta\) is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, and \(n\) is the number of equal segments of the first median line.

[0166] In one embodiment, the fourth determination module 1015 includes:

[0167] The first determination sub-module is configured to determine the volume of the material on the conveyor belt at each acquisition moment within each material passing time period according to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and a preset acquisition period.

[0168] The second determination sub-module is configured to sum up the volumes of the material on the conveyor belt at all acquisition moments within each material passing time period to determine the volume of the material on the conveyor belt within each material passing time period.

[0169] The third determination sub-module is configured to determine the mass of the material on the conveyor belt within each material passing time period.

[0170] The fourth determination sub-module is configured to divide the mass of the material on the conveyor belt within each material passing time period by the volume of the material on the conveyor belt within the corresponding material passing time period to determine the density of the material on the conveyor belt within each material passing time period.

[0171] The averaging sub-module is configured to average the densities of the material on the conveyor belt over all material passing time periods as the average material density.

[0172] In one embodiment, the first determination sub-module includes:

[0173]

[0174] In Equation (14), \(v\) is determined based on the motor frequency of the conveyor belt, and \(v\) is the speed of the conveyor belt; \(S\) t is the cross-sectional area of the material on the conveyor belt at the acquisition moment \(t\), \(V\) t is the volume of the material on the conveyor belt at the acquisition moment \(t\), \(F\) is the frame rate of the 3D structured light camera, \(\delta\) t is the preset acquisition period, \(\Delta t\) is a constant, and \(\Delta t\) is determined by selecting the maximum value between \(\delta\) t and .

[0175] In one embodiment, the fifth determination module includes:

[0176]

[0177] In Equation (15), \(W\) t is the material flow rate on the conveyor belt at the acquisition moment \(t\), \(V\) tLet \(V\) be the volume of the material on the conveyor belt at the acquisition moment \(t\), \(\rho\) be the average material density, \(F\) be the frame rate of the 3D structured light camera, and \(\delta\) t be the preset acquisition period, \(\Delta t\) be a constant, and \(\Delta t\) is determined by selecting the maximum value between \(\delta\) t and .

[0178] Each module in the above tobacco material flow detection device can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0179] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 11 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner, and the wireless manner can be implemented through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. The computer program, when executed by the processor, implements a tobacco material flow detection method. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, a touchpad, or a mouse, etc.

[0180] Those skilled in the art can understand that Figure 11 the structure shown in

[0181] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0182] In the case where there is no material on the conveyor belt, obtain the first depth map of the conveyor belt collected by the 3D structured light camera. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point.

[0183] Determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinate points of the first midline.

[0184] Perform multi-segment equal division on the first midline, and form a first depth value set from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed.

[0185] In the case where there is material on the conveyor belt, obtain the second depth map of the conveyor belt within each material passing time period collected by the 3D structured light camera according to a preset collection period. The material passing time period refers to the time period between the start time and the end time when the material is transported on the conveyor belt.

[0186] Determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map, perform multi-segment equal division on each second midline, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each endpoint coordinate point among all the endpoint coordinate points of all the equal division lines formed.

[0187] Determine the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period according to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set.

[0188] Determine the average material density on the conveyor belt within all the material passing time periods according to the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period and the preset collection period.

[0189] Determine the material flow rate on the conveyor belt at each collection moment within each material passing time period according to the average material density.

[0190] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0191] Determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinate points of the first midline, including:

[0192]

[0193] In Equation (16), θ is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, and z a and z b are the depth values of the pixels corresponding to the respective two endpoint coordinate points, and D is the measurement width.

[0194] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0195] According to the measurement width of the conveyor belt, the first depth value set, the angle, and each second depth value set, determine the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period, including:

[0196]

[0197] In Equation (17), z i,1 is the i-th depth value in the first depth value set, z i,t is the i-th depth value in the second depth value set corresponding to the t acquisition moment within each material passing time period, S t is the cross-sectional area of the material on the conveyor belt at the t acquisition moment within each material passing time period, D is the measurement width, θ is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, and n is the number of equal segments of the first median line.

[0198] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0199] According to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period, and the preset acquisition period, determine the average material density on the conveyor belt within all material passing time periods, including:

[0200] According to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period, determine the volume of the material on the conveyor belt at each acquisition moment within each material passing time period;

[0201] Sum up the volumes of the material on the conveyor belt at all acquisition moments within each material passing time period to determine the volume of the material on the conveyor belt within each material passing time period;

[0202] Determine the mass of the material on the conveyor belt within each material passing time period;

[0203] Divide the mass of the material on the conveyor belt within each material passing time period by the volume of the material on the conveyor belt within the corresponding material passing time period to determine the material density on the conveyor belt within each material passing time period;

[0204] Take the average of the material densities on the conveyor belt within all material passing time periods as the average material density.

[0205] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0206] According to the cross-sectional area of the material on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period, determine the volume of the material on the conveyor belt at each acquisition moment within each material passing time period, including:

[0207]

[0208] In formula (18), v is determined based on the motor frequency of the conveyor belt, and v is the speed of the conveyor belt; S t is the cross-sectional area of the material on the conveyor belt at the acquisition moment t, V t is the volume of the material on the conveyor belt at the acquisition moment t, F is the frame rate of the 3D structured light camera, δ t is the preset acquisition period, Δt is a constant, and Δt is determined by selecting the maximum value from δ t and between.

[0209] In one embodiment, when the processor executes the computer program, the following steps are further implemented:

[0210] According to the average material density, determine the material flow rate on the conveyor belt at each acquisition moment within each material passing time period, including:

[0211]

[0212] In formula (19), W t is the material flow rate on the conveyor belt at the acquisition moment t, V t is the volume of the material on the conveyor belt at the acquisition moment t, ρ is the average material density, F is the frame rate of the 3D structured light camera, δ t is the preset acquisition period, Δt is a constant, and Δt is determined by selecting the maximum value from δ t and between.

[0213] In one embodiment, a computer device is further provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, the steps in the above method embodiments are implemented.

[0214] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0215] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by the processor, the steps in the above method embodiments are implemented.

[0216] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data that have been authorized by the user or fully authorized by all parties.

[0217] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0218] The technical features of the above embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0219] The above-described embodiments merely represent several implementation manners of the present application. The description thereof is relatively specific and detailed, but it should not be construed as a limitation to the patent scope of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all fall within the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A method for detecting the flow rate of tobacco materials, characterized in that, The method includes: In the case where there is no material on the conveyor belt, obtain a first depth map of the conveyor belt collected by a 3D structured light camera. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point; Determine the center line of the conveyor belt in the first depth map as the first center line, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two end-point coordinate points of the first center line; the first center line is determined along the width direction of the conveyor belt; Perform multi-segment equal division on the first center line, and form a first depth value set from the depth values of the pixels corresponding to each end-point coordinate point among all the end-point coordinate points of all the equal division lines formed; In the case where there is material on the conveyor belt, obtain a second depth map of the conveyor belt within each material passing time period collected by the 3D structured light camera according to a preset collection period. The material passing time period refers to the time period between the starting moment and the ending moment when the material is conveyed on the conveyor belt; Determine the center line of the conveyor belt in each second depth map as the second center line corresponding to the second depth map, perform multi-segment equal division on each second center line, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each end-point coordinate point among all the end-point coordinate points of all the equal division lines formed; the second center line is determined along the width direction of the conveyor belt; Determine the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period according to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set; Determine the average material density on the conveyor belt within all the material passing time periods according to the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period and the preset collection period; Determine the material flow rate on the conveyor belt at each collection moment within each material passing time period according to the average material density; 2. The method according to claim 1, wherein The determining the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two end-point coordinate points of the first center line includes: Where, θ is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, and z a and z b are the depth values of the pixels corresponding to the two endpoint coordinate points respectively, and D is the measured width.

3. The method according to claim 2, characterized in that The determining the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period according to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set includes: where z i,1 is the i-th depth value in the first depth value set, and z i,t is the i-th depth value in the second depth value set corresponding to the acquisition moment t in each material passing time period. S t is the cross-sectional area of the material on the conveyor belt at the acquisition moment t in each material passing time period, D is the measurement width, θ is the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located, and n is the number of equal segments of the first median line.

4. The method according to claim 3, wherein The determining the average material density on the conveyor belt within all the material passing time periods according to the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period and the preset collection period includes: Determine the volume of the material on the conveyor belt at each collection moment within each material passing time period according to the cross-sectional area of the material on the conveyor belt at each collection moment within each material passing time period and the preset collection period; Sum the volumes of the materials on the conveyor belt at all acquisition moments within each material passing time period to determine the volume of the materials on the conveyor belt within each material passing time period. Determine the mass of the materials on the conveyor belt within each material passing time period. Divide the mass of the materials on the conveyor belt within each material passing time period by the volume of the materials on the conveyor belt within the corresponding material passing time period to determine the density of the materials on the conveyor belt within each material passing time period. Average the densities of the materials on the conveyor belt over all material passing time periods to obtain the average material density.

5. The method according to claim 4, characterized in that, Determining the volume of the materials on the conveyor belt at each acquisition moment within each material passing time period according to the cross-sectional area of the materials on the conveyor belt at each acquisition moment within each material passing time period and the preset acquisition period includes: wherein, v is determined based on the motor frequency of the conveyor belt, and v is the speed of the conveyor belt; S t is the cross-sectional area of the material on the conveyor belt at the t acquisition moment, V t is the volume of the material on the conveyor belt at the t acquisition moment, F is the frame rate of the 3D structured light camera, δ t is the preset acquisition period, Δt is a constant, and Δt is determined by selecting the maximum value between δ t and .

6. The method according to claim 5, wherein Determining the material flow rate of the materials on the conveyor belt at each acquisition moment within each material passing time period according to the average material density includes: Among them, W t is the material flow rate on the conveyor belt at the t acquisition moment, V t is the material volume on the conveyor belt at the t acquisition moment, ρ is the average material density, F is the frame rate of the 3D structured light camera, δ t is the preset acquisition period, Δt is a constant, and Δt is determined by selecting the maximum value between δ t and .

7. A tobacco material flow detection device, characterized in that, The device includes: An acquisition module, configured to, when there is no material on the conveyor belt, acquire a first depth map of the conveyor belt collected by a 3D structured light camera. The first depth map is collected by adjusting the shooting angle according to the transmission direction of the conveyor belt, and each pixel in the first depth map corresponds to a coordinate point. A first determination module, configured to determine the midline of the conveyor belt in the first depth map as the first midline, and determine the angle between the plane where the 3D structured light camera is located and the plane where the conveyor belt is located according to the measured width of the conveyor belt and the depth values of the pixels corresponding to the two endpoint coordinates of the first midline. The first midline is determined along the width direction of the conveyor belt. An equal division module, configured to perform multi-segment equal division on the first midline, and form a first depth value set from the depth values of the pixels corresponding to each endpoint coordinate among all the endpoint coordinates of all the equal division lines formed. An acquisition module, configured to, when there is material on the conveyor belt, acquire a second depth map of the conveyor belt within each material passing time period collected by the 3D structured light camera according to a preset acquisition period. The material passing time period refers to the time period between the start moment and the end moment when the material is conveyed on the conveyor belt. A second determination module, configured to determine the midline of the conveyor belt in each second depth map as the second midline corresponding to the second depth map, perform multi-segment equal division on each second midline, and form a second depth value set corresponding to each second depth map from the depth values of the pixels corresponding to each endpoint coordinate among all the endpoint coordinates of all the equal division lines formed. The second midline is determined along the width direction of the conveyor belt. A third determination module, configured to determine the cross-sectional area of the materials on the conveyor belt at each acquisition moment within each material passing time period according to the measured width of the conveyor belt, the first depth value set, the angle, and each second depth value set. A fourth determination module, configured to determine the average material density on the conveyor belt within all material passing time periods according to the material cross-sectional area on the conveyor belt at each collection moment within each material passing time period and the preset collection period; A fifth determination module, configured to determine the material flow rate on the conveyor belt at each collection moment within each material passing time period according to the average material density.

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

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

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

Images