Intelligent grabbing control method and device, electronic equipment and storage medium

Abstract

The invention provides an intelligent grabbing control method and device, electronic equipment and a storage medium. The method comprises the steps that a material pile image corresponding to a material pile located below a discharging port is collected through an image sensor; performing contour segmentation processing on the material pile image by using a preset image processing model, and determining a material pile contour and a formed material area; performing multi-dimensional feature analysis on the material region, determining a plurality of feature parameters, and calculating a stacking index of the material stack in the set region of interest according to the plurality of feature parameters; according to the accumulation index, whether the material pile reaches the grabbing standard or not is determined; and if the material pile reaches the grabbing standard, the crane is controlled to grab the material pile according to the multiple characteristic parameters. The material pile grabbing is automatically completed by recognizing the material stacking condition, and the material pile processing efficiency and stability are improved.

Description

Technical Field

[0001] The present application relates to the technical field of particulate material processing, and in particular to an intelligent grasping control method, device, electronic device and storage medium. Background Art

[0002] At present, the ash treatment of waste incineration power plants mainly relies on manual observation of the accumulation of ash at the outlet. The operator judges the timing of ash grabbing based on the images transmitted by the camera. The existing treatment methods usually include monitoring the images through cameras, operating cranes in combination with manual experience, or measuring the ash height based on simple sensors for feedback control. However, these methods have significant limitations in practical applications.

[0003] Manual monitoring methods are highly dependent on the operator's subjective judgment and energy state. Therefore, when long-term continuous monitoring is required, it is easily affected by factors such as human fatigue and distraction, resulting in low and unstable grasping efficiency, which in turn affects the production rhythm and effect of the entire ash treatment.

[0004] Although the sensor monitoring method can realize basic monitoring of the ash accumulation height, due to the irregular shape of the ash accumulation, the sensor can only provide local and rough height information and cannot fully reflect the overall distribution status of the ash. In other words, the sensor monitoring method lacks effective perception of the overall shape of the ash, making it difficult to ensure the accuracy of the judgment. In addition, the sensor installation and maintenance costs are high, and it is easily affected by factors such as dust and humidity in complex environments, which further increases the difficulty and instability of the application. Summary of the invention

[0005] In view of this, the purpose of the present application is to at least provide an intelligent grasping control method, device, electronic device and storage medium. The present application automatically completes the grasping of the material pile by identifying the material stacking situation, thereby improving the efficiency and stability of material pile processing.

[0006] This application mainly includes the following aspects:

[0007] In a first aspect, an embodiment of the present application provides an intelligent grasping control method, the method comprising: collecting a material pile image corresponding to a material pile located below a material discharge port through an image sensor; performing contour segmentation processing on the material pile image using a preset image processing model to determine the contour of the material pile and the material area formed by the material pile; performing multi-dimensional feature analysis on the material area to determine multiple feature parameters and calculate the stacking index of the material pile in a set area of ​​interest based on the multiple feature parameters; determining whether the material pile meets the grasping standard based on the stacking index; if the material pile meets the grasping standard, controlling the crane to grasp the material pile based on the multiple feature parameters.

[0008] In one possible implementation, the plurality of feature parameters include geometric features, texture features, and grayscale features, wherein the accumulation index of the material within a set region of interest is calculated in the following manner: extracting the geometric features, texture features, and grayscale features corresponding to the material region; performing feature fusion on the geometric features, texture features, and grayscale features corresponding to the material region according to given weights to determine the accumulation index.

[0009] In a possible implementation, the geometric features include an area ratio between the material region and the set region of interest and a shape factor, wherein the shape factor reflects the shape characteristics of the material region, wherein the stacking index is determined by the following formula:

[0010] Iaccum = w1×area ratio+w2×shape factor+w3×texture feature+w4

[0011] ×Grayscale Features

[0012] In this formula, Iaccum represents the accumulation index, the area ratio represents the ratio between the area of ​​the material region and the area of ​​the set area of ​​interest, w1 represents the weight corresponding to the area ratio, w2 represents the weight corresponding to the shape factor, w3 represents the weight corresponding to the texture feature, and w4 represents the weight corresponding to the grayscale feature.

[0013] In one possible implementation, whether the stacking index meets the grasping standard is determined in the following manner: the stacking index is compared with a preset stacking threshold; if the stacking index is greater than or equal to the preset stacking threshold, it is determined that the material meets the grasping standard; if the stacking index is less than the preset stacking threshold, it is determined that the material does not meet the grasping standard.

[0014] In a possible implementation, the step of controlling the crane to grab materials according to multiple characteristic parameters includes: determining multiple grabbing control quantities corresponding to the crane grabbing operation according to the multiple characteristic parameters; generating a crane grabbing instruction from the multiple grabbing control quantities; and sending the crane grabbing instruction to the crane to control the crane to grab the material pile.

[0015] In a possible implementation, the multiple grabbing control quantities include a grabbing angle, a grab height corresponding to the crane, and a grabbing force, wherein the multiple grabbing control quantities are determined in the following manner: obtaining the stacking height of the material pile from a material pile height acquisition sensor; calculating the grabbing angle based on the shape information corresponding to the material area and the material grabbing position; determining the grab height based on the stacking height, the discharge port height, and a preset safety margin; and determining the grab force based on the material density reflected by the texture features and grayscale features corresponding to the material area.

[0016] In a possible implementation, the method further includes: if the material pile does not meet the grabbing standard, determining whether the stacking index satisfies the grab movement trigger condition, the grab movement trigger condition being that the difference between a preset stacking threshold and the stacking index is less than a target trigger threshold; if the stacking index satisfies the grab movement trigger condition, determining whether the crane grab has moved to the material grabbing position; if the crane grab has moved to the material grabbing position, returning to execute the material pile image corresponding to the material pile located below the discharge port through the image sensor; if the crane grab has not moved to the material grabbing position, controlling the grab corresponding to the crane to move to the material grabbing position, and returning to execute the material pile image corresponding to the material pile located below the discharge port through the image sensor.

[0017] In a second aspect, an embodiment of the present application further provides an intelligent grasping control device, the device comprising: an image acquisition module, for acquiring a material pile image corresponding to the material pile located below the discharge port through an image sensor; a contour segmentation module, for performing contour segmentation processing on the material pile image using a preset image processing model, and determining the contour of the material pile and the material area formed by it; a feature analysis module, for performing multi-dimensional feature analysis on the material area, determining multiple feature parameters and calculating the stacking index of the material pile in a set area of ​​interest based on the multiple feature parameters; a judgment module, for determining whether the material pile meets the grasping standard based on the stacking index; and a grasping control module, for controlling the crane to grasp the material pile based on multiple feature parameters if the material pile meets the grasping standard.

[0018] In the third aspect, an embodiment of the present application also provides an electronic device, comprising: a processor, a memory and a bus, the memory storing machine-readable instructions executable by the processor, when the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the intelligent grasping control method in the above-mentioned first aspect or any possible implementation scheme of the first aspect.

[0019] In a fourth aspect, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of intelligent grasping control in the above-mentioned first aspect or any possible implementation of the first aspect are executed.

[0020] The embodiments of the present application provide an intelligent grasping control method, device, electronic device and storage medium, the method comprising: collecting a material pile image corresponding to a material pile located below a material discharge port through an image sensor; performing contour segmentation processing on the material pile image using a preset image processing model to determine the material pile contour and the material area formed by it; performing multi-dimensional feature analysis on the material area to determine multiple feature parameters and calculate the stacking index of the material pile in a set area of ​​interest based on the multiple feature parameters; determining whether the material pile meets the grasping standard based on the stacking index; if the material pile meets the grasping standard, controlling the crane to grasp the material pile based on the multiple feature parameters. The present application automatically completes the grasping of the material pile by identifying the material stacking situation, thereby improving the efficiency and stability of material pile processing.

[0021] In order to make the above-mentioned objects, features and advantages of the present application more obvious and easy to understand, preferred embodiments are specifically cited below and described in detail with reference to the attached drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flow chart of an intelligent grasping control method provided by an embodiment of the present application is shown;

[0024] Figure 2 An overall schematic diagram of a material processing area provided in an embodiment of the present application is shown;

[0025] Figure 3 A schematic diagram of material segmentation provided in an embodiment of the present application is shown;

[0026] Figure 4 A functional module diagram of an intelligent grasping control device provided in an embodiment of the present application is shown;

[0027] Figure 5 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0028] To make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. It should be understood that the drawings in the present application only serve the purpose of explanation and description and are not used to limit the scope of protection of the present application. In addition, it should be understood that the schematic drawings are not drawn in real proportion. The flowchart used in this application shows the operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowchart can be implemented out of sequence, and the steps without logical context can be reversed in order or implemented simultaneously. In addition, those skilled in the art, under the guidance of the content of the present application, can add one or more other operations to the flowchart, or remove one or more operations from the flowchart.

[0029] In addition, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the application claimed for protection, but merely represents the selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0030] At present, the ash treatment of waste incineration power plants mainly relies on manual observation of the accumulation of ash at the outlet. The operator judges the timing of ash grabbing based on the images transmitted by the camera. The existing treatment methods usually include monitoring the images through cameras, operating cranes in combination with manual experience, or measuring the ash height based on simple sensors for feedback control. However, these methods have significant limitations in practical applications.

[0031] The ash treatment method provided by the prior art has the following shortcomings:

[0032] 1. The manual monitoring method of material grabbing is heavily dependent on the operator's experience, and it is difficult to ensure 24-hour continuous monitoring. When the operator is tired or his attention is reduced, it is very easy to misjudge the timing of grabbing the material pile, which in turn affects the operating efficiency and stability of the system.

[0033] 2. The existing sensor monitoring method for material grabbing can only obtain rough information on the height of ash accumulation, and it is difficult to accurately evaluate the specific distribution pattern and volume of ash, especially when the ash accumulation pattern is complex, resulting in low reliability of monitoring accuracy and grasping timing judgment.

[0034] 3. The grabbing control system provided by the existing technology is not intelligent enough and lacks effective ash identification and decision-making means. It is difficult to accurately judge when to grab the ash, which increases the uncertainty of the grabbing operation and affects the overall efficiency and consistency of the ash treatment process.

[0035] 4. The ash has various and irregular shapes, and traditional monitoring methods are difficult to capture its detailed features, which in turn affects the accuracy of the grab control. In addition, due to the lack of consistency in manual judgment, especially after shift changes or long hours of work, the judgment results are prone to deviations, which directly affects the reliability of the ash treatment process.

[0036] Based on this, the embodiments of the present application provide an intelligent grasping control method, device, electronic device and storage medium, which automatically grasps the material pile by identifying the material accumulation situation, thereby improving the material pile processing efficiency and stability, as follows:

[0037] See also Figure 1 , Figure 1 FIG. 1 is a flow chart of an intelligent grasping control method provided by an embodiment of the present application. Figure 1 As shown, the method provided in the embodiment of the present application comprises the following steps:

[0038] S100, collecting a material pile image corresponding to the material pile located below the discharge port through an image sensor.

[0039] S200: Perform contour segmentation processing on the material pile image using a preset image processing model to determine the contour of the material pile and the material area formed by it.

[0040] S300, performing multi-dimensional feature analysis on the material area, determining multiple feature parameters and calculating the accumulation index of the material pile in the set area of ​​interest according to the multiple feature parameters.

[0041] S400: Determine whether the material pile meets the grabbing standard according to the pile index.

[0042] S500: If the material pile reaches the grabbing standard, control the crane to grab the material pile according to multiple characteristic parameters.

[0043] For specific implementation, see Figure 2 , Figure 2 FIG. 1 shows an overall schematic diagram of a material processing area provided in an embodiment of the present application. Figure 2 As shown, the material flows out from the discharge port 1, and the outflowing material accumulates below the discharge port 1 over time to form a material pile 2. The image sensor 3 is arranged above the material pile 2 to collect the material pile image of the material pile 2, wherein the image sensor 3 is a camera, and the material can be ash obtained by different industrial processes.

[0044] The present application collects the image of the material pile below the discharge port 1 through the image sensor 3, and uses a preset image processing model, such as a UNet model, to perform contour segmentation on the material pile image, obtain the material pile contour and determine the material area circled by the material pile contour, and determine the stacking index corresponding to the material pile by performing multi-dimensional feature analysis on the material area. The stacking index reflects the stacking condition of the material pile, and the stacking condition is compared with the grasping standard. The crane is controlled to grasp the material according to multiple feature parameters of the comparison result. The present application automatically identifies the stacking condition of the material pile and automatically controls the material grasping based on the stacking condition of the material pile, which can not only improve the material pile processing efficiency and stability, but also accurately evaluate the specific distribution form and volume of the material pile, and improve the accuracy of subsequent grasping control.

[0045] In one example, in step S100, the image sensor is used to monitor the accumulation of materials below the discharge port and provide a real-time video stream of the material pile. The real-time video stream includes multiple continuously collected images of the material pile. The image sensor provides basic data for the entire material identification and grasping process.

[0046] In step S200, the material pile in the material pile image is segmented using a pre-trained image processing model to obtain the material pile contour. The image processing model may be a UNet model. The UNet model includes multiple processing layers, including an input layer, a downsampling path (i.e., an encoder), an upsampling path (i.e., a decoder), and an output layer. The downsampling path is used to extract feature information of the material pile, and the upsampling path is used to gradually restore the resolution of the material pile image and generate a final segmentation result. The multiple processing layers are connected by jump connections to ensure that the UNet model retains important spatial information during the segmentation process. The UNet model can effectively extract and restore important features in the material pile image through the combination of the encoder and the decoder, making the segmentation effect more accurate.

[0047] The image sensor is set above the material pile. Therefore, in this application, the material pile outline refers to the top view of the material pile. Figure 3 , Figure 3 A schematic diagram of material segmentation provided in an embodiment of the present application is shown. Figure 3 As shown, Figure 3 The overall image is a material pile image collected by the image sensor. The preset image processing model is used to perform contour segmentation on the material pile image and identify the boundary information corresponding to the material pile. Figure 3 The yellow line corresponds to the material pile outline, and the inside of the material pile outline is the material area.

[0048] In step S300, the plurality of feature parameters include geometric features, texture features and grayscale features. In a preferred embodiment, step S300 includes:

[0049] The geometric features, texture features and grayscale features corresponding to the material area are extracted, and the geometric features, texture features and grayscale features corresponding to the material area are fused according to given weights to determine the accumulation index.

[0050] Specifically, the geometric features include but are not limited to at least one of the following items: the area, perimeter and shape factor corresponding to the material area, the texture features include grayscale co-occurrence matrix parameters, and the grayscale features include but are not limited to at least one of the following items: the average grayscale value and the grayscale variance.

[0051] Preferably, the geometric features also include the area ratio between the material region and the set area of ​​interest, the shape factor reflects the shape characteristics of the material region, and the texture characteristics and grayscale characteristics reflect the density of the material pile.

[0052] In a preferred embodiment, the stacking index is determined by the following formula:

[0053] Iaccum = w1×area ratio+w2×shape factor+w3×texture feature+w4

[0054] ×Grayscale Features

[0055] In this formula, Iaccum represents the accumulation index, the area ratio represents the ratio between the area of ​​the material area and the area of ​​the set area of ​​interest, the area ratio reflects the proportion of the material area in the set area of ​​interest, w1 represents the weight corresponding to the area ratio, w2 represents the weight corresponding to the shape factor, w3 represents the weight corresponding to the texture feature, and w4 represents the weight corresponding to the grayscale feature, wherein w1+w2+w3. +w4=1, w1, w2, w3 and w4 are determined based on experience or through machine learning methods.

[0056] In one example, the area ratio Rarea = A ash / A ROI , where A ash Indicates the area of ​​the material area, A ROI Indicates setting the area of ​​the region of interest.

[0057] The shape factor can be the circularity C, where circularity C = 4πA ash / P 2 , where P represents the perimeter of the material area.

[0058] return Figure 1 , in step S400, including:

[0059] The accumulation index Iaccum is compared with the preset accumulation threshold T. If the accumulation index Iaccum ≥ the preset accumulation threshold T, it is determined that the material meets the grasping standard. If the accumulation index Iaccum < the preset accumulation threshold T, it is determined that the material does not meet the grasping standard.

[0060] like Figure 1 , the method provided by the present application also includes:

[0061] S600: If the material pile does not meet the grabbing standard, determine whether the pile index meets the grab bucket movement triggering condition.

[0062] Among them, the grab bucket movement trigger condition is that the difference between the preset accumulation threshold and the accumulation index is less than the target trigger threshold.

[0063] S610: If the accumulation index satisfies the grab bucket movement triggering condition, determine whether the crane grab bucket has moved to the material grabbing position.

[0064] If the accumulation index does not meet the grab bucket movement triggering condition, the process returns to step S100.

[0065] If the crane grab bucket has moved to the material grabbing position, the process returns to step S100.

[0066] S620: If the grab bucket of the crane has not moved to the material grabbing position, control the grab bucket corresponding to the crane to move to the material grabbing position, and return to execute step S100.

[0067] In steps S600 to S620 of the present application, since it takes a certain amount of time for the crane grab to move from the initial position to the material grabbing position, if the present application controls the crane grab to move only after detecting that the stacking index reaches the grabbing standard, the best time to grab the material will be missed as the movement takes time. Therefore, the present application divides the material grabbing control process into two parts, one part is the movement control of the crane grab, and the other part is the drive control of the grabbing action. Based on these two parts, the present application respectively sets the grab movement triggering conditions for triggering the grab movement and the grabbing standards for triggering the grabbing action.

[0068] When the stacking index corresponding to the material pile image does not meet the grabbing standard, determine whether the stacking index meets the grab movement triggering condition. If the grab movement triggering condition is met, it means that the stacking index is about to meet the grabbing standard. At this time, the crane grab should be moved to the material grabbing position to avoid excessive material accumulation and miss the best grabbing opportunity. The material grabbing position is acquired in real time, and after the grab is controlled to move to the material grabbing position, return to execute step S100, analyze the next frame of the material pile image, and execute step S500 when it is detected that the stacking index meets the grabbing standard.

[0069] Before moving the crane grab bucket to the material grabbing position, it is necessary to first determine whether the crane grab bucket has moved to the material grabbing position. If it has moved to the material grabbing position, the grab bucket should not move. If the grab bucket has not moved to the material grabbing position, control the grab bucket to move to the material grabbing position.

[0070] In a preferred embodiment, step S500 includes:

[0071] According to a plurality of characteristic parameters, a plurality of grab control quantities corresponding to the crane grab operation are determined, a crane grab instruction is generated from the plurality of grab control quantities, and the crane grab instruction is sent to the crane to control the crane to grab the material pile.

[0072] In another preferred embodiment, the plurality of gripping control quantities include a gripping angle, a grabbing bucket height corresponding to the crane, and a gripping force, wherein the plurality of gripping control quantities are determined by:

[0073] The stacking height of the material pile is obtained from the material pile height collection sensor, and the grabbing angle is calculated according to the shape information corresponding to the material area and the material grabbing position. The grab height is determined according to the stacking height, the discharge port height and the preset safety margin, and the grabbing force is determined according to the material density reflected by the texture characteristics and grayscale characteristics corresponding to the material area.

[0074] According to the bottom contour of the material pile indicated by the shape information corresponding to the material area, determine the two target points on the bottom contour of the material pile that are farthest apart. According to the corresponding coordinates of the two target points, determine the center point of the bottom of the material pile, whose coordinates are (x1, y1), x1 represents the horizontal abscissa corresponding to the center point of the bottom of the material pile, y1 represents the horizontal ordinate corresponding to the center point of the bottom of the material pile, and the material grabbing position is the highest point of the material pile, and its corresponding coordinates are (x2, y2), x2 represents the horizontal abscissa of the material grabbing position, and y2 represents the horizontal ordinate of the material grabbing position.

[0075] In a preferred embodiment, the grip angle is determined by the following formula:

[0076] θ=arctan(y2-y1 / x2-x1)

[0077] In this formula, θ represents the grip angle.

[0078] In a preferred embodiment, the grab bucket height is determined by:

[0079] H=H base +H ash +Δh

[0080] In this formula, H represents the height of the grab bucket, H base Indicates the discharge port height, H ash It indicates the material stacking height, and Δh indicates the safety margin.

[0081] The gripping force is determined based on the material density reflected by the texture features and grayscale features corresponding to the material area.

[0082] In a preferred embodiment, the gripping force is determined by:

[0083] F=F max ×(1-σ gray / σ max )

[0084] In this formula, F represents the gripping force, F max represents the maximum grasping force, σ gray represents the grayscale variance, σ max Represents the maximum grayscale variance.

[0085] Based on the same application concept, an intelligent grasping control device corresponding to the intelligent grasping control method provided in the above embodiment is also provided in the embodiment of the present application. Since the principle of solving the problem by the device in the embodiment of the present application is similar to the intelligent grasping control method in the above embodiment of the present application, the implementation of the device can refer to the implementation of the method, and the repeated parts will not be repeated.

[0086] See also Figure 4 , Figure 4 FIG. 1 shows a functional module diagram of an intelligent grasping control device provided by an embodiment of the present application. Figure 4 As shown, the device comprises:

[0087] The image acquisition module 700 is used to acquire a material pile image corresponding to the material pile located below the discharge port through an image sensor.

[0088] The contour segmentation module 710 is used to perform contour segmentation processing on the material pile image using a preset image processing model to determine the contour of the material pile and the material area formed by it.

[0089] The feature analysis module 720 is used to perform multi-dimensional feature analysis on the material area, determine multiple feature parameters and calculate the accumulation index of the material pile in the set area of ​​interest based on the multiple feature parameters.

[0090] The determination module 730 is used to determine whether the material pile meets the grabbing standard according to the pile index.

[0091] The grab control module 740 is used to control the crane to grab the material pile according to multiple characteristic parameters if the material pile meets the grab standard.

[0092] Based on the same application idea, please refer to Figure 5 , Figure 5 FIG. 1 is a schematic diagram showing the structure of an electronic device provided by an embodiment of the present application. Figure 5As shown, the electronic device 800 includes: a processor 810, a memory 820 and a bus 830. The memory 820 stores machine-readable instructions executable by the processor 810. When the electronic device 800 is running, the processor 810 and the memory 820 communicate through the bus 830. The machine-readable instructions are executed by the processor 810 when it is running, such as the steps of the intelligent grasping control method provided in any of the above embodiments.

[0093] Based on the same application concept, an embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent grasping control method provided in the above embodiment are executed.

[0094] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, the specific working process of the system and device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here. In the several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. The device embodiments described above are merely schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some communication interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0095] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0096] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0097] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0098] The above are only specific implementations of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. An intelligent grasping control method, characterized in that: The method comprises: The image of the material pile corresponding to the material pile below the discharge port is collected by an image sensor; Performing contour segmentation processing on the material pile image using a preset image processing model to determine the material pile contour and the material area formed by it; Performing multi-dimensional characteristic analysis on the material area, determining a plurality of characteristic parameters and calculating a stacking index of the material pile in a set area of ​​interest according to the plurality of characteristic parameters; According to the accumulation index, determine whether the material pile meets the grabbing standard; If the material pile reaches the grabbing standard, the crane is controlled to grab the material pile according to the multiple characteristic parameters.

2. The method according to claim 1, characterized in that The multiple feature parameters include geometric features, texture features and grayscale features, The accumulation index of the material in the set area of ​​interest is calculated in the following way: Extracting geometric features, texture features and grayscale features corresponding to the material area; The geometric features, texture features and grayscale features corresponding to the material area are fused according to given weights to determine the accumulation index.

3. The method according to claim 2, characterized in that The geometric features include the area ratio between the material region and the set region of interest and the shape factor, the shape factor reflects the shape characteristics of the material region, Wherein, the stacking index is determined by the following formula: Iaccum=w1×area ratio+w2×shape factor+w3×texture feature+w4 ×Grayscale Features In this formula, Iaccum represents the accumulation index, the area ratio represents the ratio between the area of ​​the material region and the area of ​​the set area of ​​interest, w1 represents the weight corresponding to the area ratio, w2 represents the weight corresponding to the shape factor, w3 represents the weight corresponding to the texture feature, and w4 represents the weight corresponding to the grayscale feature.

4. The method according to claim 1, characterized in that: Whether the accumulation index meets the crawling standard is determined by the following method: comparing the accumulation index with a preset accumulation threshold; If the accumulation index is greater than or equal to the preset accumulation threshold, it is determined that the material meets the grabbing standard; If the accumulation index is less than the preset accumulation threshold, it is determined that the material does not meet the grabbing standard.

5. The method according to claim 1, characterized in that: The step of controlling the crane to grab the material according to the multiple characteristic parameters comprises: Determining a plurality of grab control quantities corresponding to the crane grab operation according to the plurality of characteristic parameters; generating a crane grabbing instruction based on the plurality of grabbing control quantities; The crane grabbing instruction is sent to the crane to control the crane to grab the material pile.

6. The method according to claim 5, characterized in that The multiple grab control quantities include the grab angle, the grab bucket height and the grab force corresponding to the crane, The multiple grab control quantities are determined in the following manner: Obtain the stacking height of the material pile from the material pile height acquisition sensor; Calculate the grab angle based on the shape information corresponding to the material area and the material grab position; Determine the height of the grab bucket according to the stacking height, the discharge port height and a preset safety margin; The grasping force is determined according to the material density reflected by the texture features and grayscale features corresponding to the material area.

7. The method according to claim 1, characterized in that The method further comprises: If the material pile does not meet the grabbing standard, determine whether the accumulation index meets the grab bucket movement trigger condition, and the grab bucket movement trigger condition is that the difference between the preset accumulation threshold and the accumulation index is less than the target trigger threshold; If the accumulation index satisfies the grab bucket movement trigger condition, determining whether the crane grab bucket has moved to the material grabbing position; If the crane grab has moved to the material grabbing position, the process returns to executing the process of collecting the material pile image corresponding to the material pile located below the discharge port through the image sensor; If the grab bucket of the crane does not move to the material grabbing position, the grab bucket corresponding to the crane is controlled to move to the material grabbing position, and the process returns to execute the material pile image corresponding to the material pile located below the discharge port collected by the image sensor.

8. An intelligent grasping control device, characterized in that: The device comprises: An image acquisition module, used for acquiring a material pile image corresponding to the material pile located below the discharge port through an image sensor; A contour segmentation module, used to perform contour segmentation processing on the material pile image using a preset image processing model to determine the material pile contour and the material area formed by it; A feature analysis module, used for performing multi-dimensional feature analysis on the material area, determining a plurality of feature parameters and calculating a stacking index of the material pile in a set area of ​​interest according to the plurality of feature parameters; A determination module is used to determine whether the material pile meets the grabbing standard according to the pile index; The grabbing control module is used to control the crane to grab the material pile according to the multiple characteristic parameters if the material pile reaches the grabbing standard.

9. An electronic device, characterized in that: include: A processor, a memory and a bus, wherein the memory stores machine-readable instructions executable by the processor. When the electronic device is running, the processor and the memory communicate through the bus, and the machine-readable instructions are executed by the processor to execute the steps of the intelligent grasping control method as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the intelligent grasping control method according to any one of claims 1 to 7 are executed.

Images