Coke powder proportion determination method and device, electronic equipment and storage medium

Abstract

The invention provides a coke powder proportion determination method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a coke image of a loading region, carrying out the image segmentation of the coke image, obtaining a coke powder region and a coke particle region, determining the particle fractal dimension and the particle area of each particle based on the coke particle region, and determining the proportion of the coke powder according to the particle fractal dimension. The particle fractal dimension and the particle area of each particle are fitted to obtain the particle total volume, the powder fractal dimension and the powder area are determined based on the coke powder area, and the powder fractal dimension and the powder area are fitted to obtain the powder total volume. The total particle mass is obtained according to the total particle volume and the preset particle density, the total powder mass is obtained according to the total powder volume and the preset powder density, and the coke powder proportion is determined according to the ratio of the total particle mass to the total powder mass, so that the technical problem of inaccurate manual identification of the coke powder proportion is solved.

Description

Technical Field

[0001] This invention relates to the field of image processing technology, and specifically to a method, apparatus, electronic device, and storage medium for determining the proportion of coke powder. Background Technology

[0002] In the production processes of metallurgical, chemical, and other industries, coke serves as an important raw material and fuel, and its physical properties have a decisive impact on the stable operation of subsequent processes, energy efficiency control, and product quality. Among these, the particle size distribution of the incoming coke is one of the key physical indicators.

[0003] Currently, in the coke processing stages of most factories, the judgment of the particle size distribution of incoming coke mainly relies on the on-site experience of operators. Specifically, operators typically visually inspect the coke on the conveyor belt or in the stockpile, relying on their subjective judgment to roughly assess the particle size and uniformity. This manual judgment method constitutes the current mainstream technology in the industry.

[0004] However, relying on human experience to judge the distribution of coke particles has the following problems: human judgment is highly subjective and lacks objectivity, which may lead to different judgment results from different people. Inaccurate coke particle distribution can lead to improper process parameter settings, which may result in increased production energy consumption and reduced production efficiency. Summary of the Invention

[0005] This invention provides a method, apparatus, electronic device, and storage medium for determining the proportion of coke powder, in order to solve the technical problem of inaccurate manual judgment.

[0006] This invention provides a method for determining the proportion of coke powder. The method includes: acquiring a coke image of a loading area; segmenting the coke image to obtain a coke powder region and a coke particle region; determining the particle fractal dimension and the particle area of ​​each particle based on the coke particle region; obtaining the total particle volume by fitting the particle fractal dimension and the particle area of ​​each particle; determining the powder fractal dimension and the powder region area based on the coke powder region; obtaining the total powder volume by fitting the powder fractal dimension and the powder region area; obtaining the total particle mass based on the total particle volume and a preset particle density; obtaining the total powder mass based on the total powder volume and a preset powder density; and determining the coke powder proportion based on the ratio of the total particle mass to the total powder mass.

[0007] In one embodiment of the present invention, image segmentation of the coke image includes: segmenting the coke image to obtain an initial coke powder region and an initial coke particle region; calculating the equivalent diameter of each particle based on the particle area of ​​each particle in the initial coke particle region; if the equivalent diameter of the particle is less than or equal to a preset diameter threshold, then marking the particle; dividing all marked particles into a newly added coke powder region, and adding the newly added coke powder region to the initial coke powder region to obtain the coke powder region; removing the newly added coke powder region from the initial coke particle region to obtain the coke particle region.

[0008] In one embodiment of the present invention, the total volume of the powder is obtained by fitting the fractal dimension of the powder and the area of ​​the powder region, including: counting the number of grids occupied by the boundaries of the coke powder region, wherein the coke powder region includes an initial coke powder region and a newly added coke powder region, and the number of grids is the number of square grids with a preset side length; determining the fractal dimension corresponding to the initial coke powder region based on the number of grids occupied by the boundaries of the initial coke powder region and the preset length; determining the fractal dimension corresponding to the newly added coke powder region based on the number of grids occupied by the boundaries of the newly added coke powder region and the preset length; and determining the powder fractal dimension based on the average of the fractal dimensions corresponding to the initial coke powder region and the newly added coke powder region.

[0009] In one embodiment of the present invention, before acquiring the image of coke in the loading area, the method further includes: acquiring the license plate image of a vehicle in the coke loading area of ​​the factory; performing text detection on the license plate image to obtain license plate information; comparing the license plate information with a preset valid license plate number; if the comparison is consistent, acquiring the image of coke in the loading area of ​​the vehicle as the coke image.

[0010] In one embodiment of the present invention, after determining the coke powder ratio based on the ratio of the total mass of the particles to the total mass of the powder, the distance between the loading area and the image acquisition device is obtained. If the distance is greater than or equal to a preset distance threshold, the method further includes: if the coke powder ratio is less than or equal to a preset ratio correction value, then the coke powder ratio is used as the corrected coke powder ratio; if the coke powder ratio is greater than the preset ratio correction value, then the preset ratio correction value is used as the corrected coke powder ratio.

[0011] In one embodiment of the present invention, after determining the coke powder ratio based on the ratio of the total mass of the particles to the total mass of the powder, the distance between the loading area and the image acquisition device is obtained. If the distance is less than a preset distance threshold, the method further includes: normalizing the coke powder ratio to obtain a processed coke powder ratio; and linearly scaling the processed coke powder ratio based on a preset scaling factor to obtain a corrected coke powder ratio.

[0012] In one embodiment of the present invention, after obtaining the corrected coke powder ratio, the method further includes: dividing the loading area into multiple region subsets based on a preset height ratio, and obtaining the subset area corresponding to the multiple region subsets according to the number of pixels occupied by the multiple region subsets; and obtaining the overall coke powder ratio according to the corrected coke powder ratio and subset area corresponding to the multiple region subsets.

[0013] This invention also provides a coke powder ratio determination device, the device comprising: an image processing module for acquiring a coke image of a loading area, performing image segmentation on the coke image to obtain a coke powder region and a coke particle region; a particle volume determination module for determining the particle fractal dimension and the particle area of ​​each particle based on the coke particle region, and obtaining the total particle volume by fitting the particle fractal dimension and the particle area of ​​each particle; a powder volume determination module for determining the powder fractal dimension and the powder region area based on the coke powder region, and obtaining the total powder volume by fitting the powder fractal dimension and the powder region area; and a powder ratio determination module for obtaining the total particle mass based on the total particle volume and a preset particle density, obtaining the total powder mass based on the total powder volume and the preset powder density, and determining the coke powder ratio based on the ratio of the total particle mass to the total powder mass.

[0014] The present invention also provides an electronic device, comprising: one or more processors; and one or more programs, which, when executed by the one or more processors, cause the electronic device to implement the coke powder ratio determination method as described in any of the above embodiments.

[0015] The present invention also provides a computer-readable storage medium storing a computer program, which, when executed by a computer processor, causes the computer to perform the coke powder ratio determination method described in any of the above embodiments.

[0016] The beneficial effects of this invention are as follows: This invention proposes a method, apparatus, electronic device, and storage medium for determining the proportion of coke powder. By acquiring a coke image of the loading area, the coke image is segmented to obtain a coke powder region and a coke particle region. Based on the coke particle region, the fractal dimension of the particles and the particle area of ​​each particle are determined. The total particle volume is obtained by fitting the fractal dimension of the particles and the particle area of ​​each particle. Based on the coke powder region, the fractal dimension of the powder and the area of ​​the powder region are determined. The total powder volume is obtained by fitting the fractal dimension of the powder and the area of ​​the powder region. The total particle mass is obtained based on the total particle volume and a preset particle density. The total powder mass is obtained based on the total powder volume and a preset powder density. The coke powder proportion is determined based on the ratio of the total particle mass to the total powder mass. Thus, coke powder and particles are identified through image segmentation and image morphology analysis. The coke powder proportion is automatically calculated, unaffected by human subjective judgment, thereby significantly improving production efficiency and product quality while reducing energy consumption. Furthermore, the automated identification method enables real-time monitoring and analysis, making the production process more efficient. It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention. It is obvious that the drawings described below are merely some embodiments of the invention, and those skilled in the art can obtain other drawings based on these drawings without any inventive effort.

[0018] In the attached diagram: Figure 1 This is a schematic diagram illustrating the implementation environment of a method for determining the proportion of coke powder according to an embodiment of the present invention. Figure 2 This is a flowchart of a method for determining the proportion of coke powder provided in one embodiment of the present invention; Figure 3 This is a schematic diagram of the loading area provided in one embodiment of the present invention; Figure 4 This is a schematic diagram of a coke image provided in one embodiment of the present invention; Figure 5 This is a block diagram of a coke powder ratio determination device provided in one embodiment of the present invention; Figure 6 This is a schematic diagram of an electronic device provided in one embodiment of the present invention. Detailed Implementation

[0019] The following specific examples illustrate the implementation of the present invention. Those skilled in the art can easily understand other advantages and effects of the present invention from the content disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present invention. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0020] It should be noted that the illustrations provided in the following embodiments are only schematic representations of the basic concept of the present invention. The drawings only show the components related to the present invention and are not drawn according to the actual number, shape and size of the components in the actual implementation. In the actual implementation, the form, quantity and proportion of each component can be arbitrarily changed, and the layout of the components may also be more complex.

[0021] In the following description, numerous details are explored to provide a more thorough explanation of embodiments of the invention. However, it will be apparent to those skilled in the art that embodiments of the invention may be practiced without these specific details. In other embodiments, well-known structures and devices are shown in block diagram form rather than in detail to avoid obscuring embodiments of the invention.

[0022] Please see Figure 1 , Figure 1 This is a schematic diagram illustrating the implementation environment of a method for determining the proportion of coke powder according to an embodiment of the present invention.

[0023] like Figure 1 As shown, the implementation environment may include an image acquisition device 110 and a computer device 120. The computer device 120 may be at least one of a microcomputer, an embedded computer, a neural network computer, etc. The image acquisition device 110 includes a camera set near or above the coke filling area of ​​the factory, used to acquire images of vehicle license plate numbers and images of coke in the loading area of ​​the vehicles within the coke filling area of ​​the factory.

[0024] Please see Figure 2 , Figure 2 This is a flowchart illustrating a method for determining the proportion of coke powder according to an embodiment of the present invention. This method can be applied to... Figure 1 The implementation environment shown can also be applied to other exemplary implementation environments and specifically executed by devices in other implementation environments. This embodiment does not limit the implementation environment to which the method is applicable.

[0025] like Figure 2 As shown, in an exemplary embodiment, the method for determining the proportion of coke powder includes at least steps S210 to S240, which are described in detail below: Step S210: Obtain a coke image of the loading area, and perform image segmentation on the coke image to obtain a coke powder area and a coke particle area.

[0026] In one embodiment of the present invention, image segmentation of a coke image includes: segmenting the coke image to obtain an initial coke powder region and an initial coke particle region; calculating the equivalent diameter of each particle based on the particle area of ​​each particle in the initial coke particle region; marking the particle if the equivalent diameter of the particle is less than or equal to a preset diameter threshold; dividing all marked particles into a newly added coke powder region, and adding the newly added coke powder region to the initial coke powder region to obtain the coke powder region; and removing the newly added coke powder region from the initial coke particle region to obtain the coke particle region.

[0027] For example, calculating the equivalent diameter of each particle based on the particle area of ​​each particle in the initial coke particle region includes: Equation (1) In equation (1), For the equivalent diameter, This represents the particle area of ​​each particle.

[0028] For example, the rule for determining whether a particle belongs to powder is as follows: ,in, To preset the diameter threshold, particles identified as powder are marked as newly added coke powder regions. The powder region segmentation accuracy is optimized by combining the output results of the deep learning segmentation model and re-labeling the particle categories to achieve more accurate region division.

[0029] For example, historical coke images are obtained as training images. Pixel-level contours are labeled on the coke regions in the training images. Pixel-level contours are also labeled on the coke powder regions, coke particle regions, and background within the coke regions. The labeled training images are used as the training set to train a preset model to obtain a particle segmentation model. The particle segmentation model is used to segment the coke powder regions and coke particle regions in the coke images. The preset model includes, but is not limited to, the segformer-b0 model and the YOLO model.

[0030] For example, to reduce the computational complexity of the granular segmentation model, a scaling factor is added to the self-attention mechanism of the granular segmentation model, thereby reducing the computational complexity of each self-attention mechanism module. The self-attention mechanism of the granular segmentation model is as follows: Equation (2) In equation (2), Q, K, and V are N*C feature maps in the self-attention mechanism, where N is the number of all local region blocks in the feature map, and C is the dimension corresponding to each local region block. For variance, when hour, The variance of each element in the matrix becomes 1, and T represents the matrix transpose. Introducing this feature can help keep the gradient values ​​stable during training.

[0031] In this process, the coke image is normalized and then input into a feature extraction network. Downsampling is used to generate multi-channel feature maps of a specific size. Each spatial location in the feature map corresponds to a local region (receptive field) of the original image at the downsampling ratio, used to record different abstract information such as texture and shape.

[0032] The computational complexity of the original self-attention algorithm is as follows: Based on this, a scaling factor R is added, and the N*C feature map is transformed through a reshape operation. The feature map is then processed through a fully connected layer. Transform into This reduces computational complexity to .

[0033] In one embodiment of the present invention, before acquiring the image of coke in the loading area, the method further includes: acquiring the license plate image of a vehicle in the coke loading area of ​​the factory, performing text detection on the license plate image to obtain license plate information; comparing the license plate information with a preset valid license plate number, and if the comparison is consistent, acquiring the image of coke in the loading area of ​​the vehicle as the coke image.

[0034] For example, historical license plate images are obtained as license plate sample images, and the license plate numbers in the license plate sample images are labeled for training a license plate recognition model. The license plate recognition model includes, but is not limited to, the PaddleOCR model and the LPNne model.

[0035] For example, the license plate of a vehicle entering the coke loading area of ​​the factory is identified by the license plate recognition model. It is determined whether the license plate number is consistent with the preset valid license plate number. If they are consistent, the vehicle is recorded as a valid vehicle. The coke image in the loading area of ​​the vehicle is obtained, and the particle segmentation model is triggered to segment the coke particle area and coke powder area of ​​the coke image until the valid vehicle leaves the coke loading area of ​​the factory.

[0036] For example, when the loading area of ​​the vehicle begins to be filled with coke, obtain as... Figure 3 The loading area diagram shown is cropped to obtain the following: Figure 4The diagram shown is a schematic representation of a coke image, which is used as the coke image. In this embodiment, during the process of loading coke into the vehicle, multiple frames of images are acquired and cropped to obtain multiple coke images.

[0037] Step S220: Determine the fractal dimension of the coke particles and the particle area of ​​each particle based on the coke particle region, and obtain the total particle volume by fitting the fractal dimension of the particles and the particle area of ​​each particle.

[0038] For example, the number of pixels occupied by a single coke particle is determined, and the physical area of ​​a single pixel is determined according to the image resolution. The particle area of ​​the coke particle is obtained by the product of the number of pixels occupied by a single coke particle and the physical area of ​​a single pixel.

[0039] Exemplarily by using the fractal dimension of particles and particle area The total volume of particles was obtained by fitting. Specifically, it includes: Equation (3) In equation (3), Represents the fractal dimension of the particles. This indicates the number of grid cells occupied by the boundary of the coke particle region. The preset side length of the grid.

[0040] Equation (4) In equation (4), This indicates the volume of each particle. These are the preset fitting coefficients for particulate materials. Represents the fractal dimension of the particles. This represents the particle area of ​​each particle.

[0041] Equation (5) In equation (5), Indicates the total volume of the particles. This represents the volume of the m-th particle.

[0042] Step S230: Determine the fractal dimension and area of ​​the powder region based on the coke powder region, and obtain the total volume of the powder by fitting the fractal dimension and area of ​​the powder region.

[0043] In one embodiment of the present invention, the total volume of the powder is obtained by fitting the fractal dimension of the powder and the area of ​​the powder region, including: counting the number of grids occupied by the boundaries of the coke powder region, the coke powder region including the initial coke powder region and the newly added coke powder region, the number of grids being the number of square grids with a preset side length; determining the fractal dimension corresponding to the initial coke powder region based on the number of grids occupied by the boundaries of the initial coke powder region and the preset length, determining the fractal dimension corresponding to the newly added coke powder region based on the number of grids occupied by the boundaries of the newly added coke powder region and the preset length; and determining the powder fractal dimension based on the average of the fractal dimensions corresponding to the initial coke powder region and the newly added coke powder region.

[0044] For example, the fractal dimension of the powder is calculated for a powder region. The obtained powder regions are then merged into a single entity, namely the initial coke powder region and the newly added coke powder region. The fractal dimension of each of the initial and newly added coke powder regions is calculated separately, including: Equation (6) In equation (6), This represents the fractal dimension corresponding to a single powder region. The number of grid cells occupied by the boundary of this single powder region. The preset side length of the grid.

[0045] For example, approximating the powder fractal dimension for all powder regions by calculating the average value includes: Equation (7) In equation (7), The fractal dimension of the powder. Let be the fractal dimension corresponding to the j-th powder region.

[0046] The total volume of the powder is obtained by fitting the fractal dimension and the area of ​​the powder regions, including: Equation (8) In equation (8), This refers to the total volume of the powder. These are the preset fitting coefficients for the powder material. The fractal dimension of the powder. This indicates the area of ​​the powder region.

[0047] For example, the area of ​​the powder region is determined by the product of the number of pixels occupied by all coke powder regions and the physical area of ​​a single pixel.

[0048] Step S240: Obtain the total mass of particles based on the total volume of particles and the preset particle density; obtain the total mass of powder based on the total volume of powder and the preset powder density; and determine the coke powder ratio based on the ratio of the total mass of particles to the total mass of powder.

[0049] In one embodiment of the present invention, after determining the coke powder ratio based on the ratio of the total mass of particles to the total mass of powder, the distance between the loading area and the image acquisition device is obtained. If the distance is greater than or equal to a preset distance threshold, the method further includes: if the coke powder ratio is less than or equal to a preset ratio correction value, then the coke powder ratio is used as the corrected coke powder ratio; if the coke powder ratio is greater than the preset ratio correction value, then the preset ratio correction value is used as the corrected coke powder ratio.

[0050] In one embodiment of the present invention, after determining the coke powder ratio based on the ratio of the total mass of particles to the total mass of powder, the distance between the loading area and the image acquisition device is obtained. If the distance is less than a preset distance threshold, the method further includes: normalizing the coke powder ratio to obtain a processed coke powder ratio; and linearly scaling the processed coke powder ratio based on a preset scaling factor to obtain a corrected coke powder ratio.

[0051] For example, a dynamic adjustment mechanism adapting to the distance between the loading area and the camera is used to correct the coke powder ratio, resulting in a corrected coke powder ratio. For loading areas at a distance, an upper bound constraint on the ratio value is introduced to ensure that the coke powder ratio remains stable within a high range. By hard-limiting ratio values ​​exceeding a threshold, unreasonable impacts on subsequent calculations due to excessively high ratio values ​​are effectively prevented, especially in imaging analysis of long-distance areas, thus avoiding distortion in ratio calculations. For loading areas at a close distance, the nonlinear characteristics of a power function are used to smooth and correct the coke powder ratio value. Normalization is performed using a reference ratio coefficient, and the scaling range of the normalized value is controlled by a reciprocal power operation. The scaling coefficient is used to further adjust the output amplitude of the result, making the adjusted ratio value more consistent with the requirements of actual application scenarios within the dynamic range.

[0052] For example, the corrected coke powder ratio is obtained by linearly scaling the processed coke powder ratio based on a preset scaling factor, including: Equation (9) In equation (9), This indicates a correction to the coke powder ratio. This indicates the original proportion of coke powder. It is a preset scaling factor used for normalization processing. It is the reciprocal of the preset power exponent that controls the correction magnitude. It is a preset scaling factor used to linearly scale the proportion of coke powder after normalization.

[0053] In one embodiment of the present invention, after obtaining the corrected coke powder ratio, the method further includes: dividing the loading area into multiple region subsets based on a preset height ratio, and obtaining the subset area corresponding to the multiple region subsets according to the number of pixels occupied by the multiple region subsets; and obtaining the overall coke powder ratio according to the corrected coke powder ratio and the subset area corresponding to the multiple region subsets.

[0054] For example, it can be represented as: Equation (10) In equation (10), This indicates the overall proportion of coke powder. It is the number of region subsets. It is the first The subset area of ​​a region subset. It is the first The corrected coke powder ratio corresponding to each region subset.

[0055] For example, the corrected coke powder ratio for each region subset is calculated based on the above steps, and the overall coke powder ratio is obtained based on the corrected coke powder ratios for multiple region subsets and the subset area.

[0056] For example, by using a slicing logic partitioning refinement method, the material area is divided into multiple region subsets according to a preset height ratio. The coke powder ratio is calculated for each region subset, and after correction based on the distance between the region and the camera, the corrected coke powder ratio is obtained. The overall coke powder ratio is then calculated by combining the region area weight with the corresponding corrected coke powder ratio. This method considers the contribution ratio of different regions to the overall result, avoiding unreasonable amplification or reduction of the global ratio value by the result of a single region. Especially in the case of multi-region distribution, it can significantly improve the accuracy and robustness of the result and optimize the recognition accuracy in scenarios with uneven material distribution.

[0057] Please see Figure 5 , Figure 5 This is a block diagram of a coke powder ratio determining device provided in one embodiment of the present invention. This device can be applied to... Figure 1 The implementation environment shown can also be applied to other exemplary implementation environments and specifically configured in other devices. This embodiment does not limit the implementation environment to which the device is applicable.

[0058] like Figure 5 As shown, the exemplary coke powder ratio determining device includes: Image processing module 510 is used to acquire a coke image of the loading area, perform image segmentation on the coke image, and obtain a coke powder area and a coke particle area. The particle volume determination module 520 is used to determine the fractal dimension of the particles and the particle area of ​​each particle based on the coke particle region, and to obtain the total particle volume by fitting the fractal dimension of the particles and the particle area of ​​each particle. The powder volume determination module 530 is used to determine the fractal dimension of the powder and the area of ​​the powder region based on the coke powder region, and to obtain the total powder volume by fitting the fractal dimension of the powder and the area of ​​the powder region. The powder ratio determination module 540 is used to obtain the total mass of particles based on the total volume of particles and the preset particle density, obtain the total mass of powder based on the total volume of powder and the preset powder density, and determine the coke powder ratio based on the ratio of the total mass of particles to the total mass of powder.

[0059] The aforementioned device enables the identification of coke powder and particles through image segmentation and image morphology analysis, and automatically calculates the proportion of coke powder without being affected by human subjective judgment, thereby significantly improving production efficiency and product quality while reducing energy consumption. Furthermore, the automated identification method enables real-time monitoring and analysis, making the production process more efficient.

[0060] It is understood that the coke powder ratio determination device and the coke powder ratio determination method provided in the above embodiments belong to the same concept. The specific operation of the coke powder ratio determination method has been described in detail in the above embodiments and will not be repeated here. In practical applications, the coke powder ratio determination device provided in the above embodiments can be assigned to different functional modules as needed. That is, the internal structure of the coke powder ratio determination device can be divided into different functional modules, and then all or part of the functions of the corresponding functional modules can be implemented through the coke powder ratio determination method described in the above embodiments. No specific limitations are imposed here. For example, the image processing module 510 includes steps for executing step S210 and related steps, the particle volume determination module 520 includes steps for executing step S220 and related steps, the powder volume determination module 530 includes steps for executing step S230 and related steps, and the powder ratio determination module 540 includes steps for executing step S240 and related steps.

[0061] Figure 6 This is a schematic diagram of an electronic device provided in one embodiment of the present invention. It should be noted that... Figure 6 The computer system 600 of the electronic device shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of the present invention.

[0062] like Figure 6As shown, the computer system 600 includes a Central Processing Unit (CPU) 601, which can perform various appropriate actions and processes based on programs stored in Read-Only Memory (ROM) 602 or programs loaded from storage portion 608 into Random Access Memory (RAM) 603, such as performing the methods described in the above embodiments. The RAM 603 also stores various programs and data required for system operation. The CPU 601, ROM 602, and RAM 603 are interconnected via a bus 604. An Input / Output (I / O) interface 605 is also connected to the bus 604.

[0063] The following components are connected to I / O interface 605: an input section 606 including a keyboard, mouse, etc.; an output section 607 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 608 including a hard disk, etc.; and a communication section 609 including a network interface card such as a LAN (Local Area Network) card, modem, etc. The communication section 609 performs communication processing via a network such as the Internet. A drive 610 is also connected to I / O interface 605 as needed. A removable medium 611, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on drive 610 as needed so that computer programs read from it can be installed into storage section 608 as needed.

[0064] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing computer programs for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 609, and / or installed from removable medium 611. When the computer program is executed by central processing unit (CPU) 601, it performs various functions defined in the system of the present invention.

[0065] It should be noted that the computer-readable medium shown in the embodiments of the present invention can be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium can be, for example, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying a computer-readable computer program. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media can also be any computer-readable medium other than computer-readable storage media, which can send, propagate, or transmit a program for use by or in connection with an instruction execution system, apparatus, or device. The computer program contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0066] The flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. Each block in a flowchart or block diagram may represent a module, segment, or portion of code containing one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions indicated in the blocks may occur in a different order than those indicated in the drawings. For example, two consecutively indicated blocks may actually be executed substantially in parallel, and they may sometimes be executed in reverse order. It should also be noted that each block in a block diagram or flowchart, and combinations of blocks in a block diagram or flowchart, may be implemented using a dedicated hardware-based system that performs the specified function or operation, or using a combination of dedicated hardware and computer instructions.

[0067] The units described in the embodiments of the present invention can be implemented in software or hardware, and the described units can also be located in a processor. The names of these units do not necessarily limit the specific unit itself.

[0068] Another aspect of the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a computer's processor, causes the computer to perform the coke powder ratio determination method as described above. This computer-readable storage medium may be included in the electronic device described in the above embodiments, or it may exist independently and not assembled into that electronic device.

[0069] Another aspect of the present invention provides a computer program product or computer program comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the coke powder ratio determination method provided in the various embodiments described above.

[0070] The above embodiments are merely illustrative of the principles and effects of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or alter the above embodiments without departing from the spirit and scope of the present invention. Therefore, all equivalent modifications or alterations made by those skilled in the art without departing from the spirit and technical concept disclosed in the present invention should still be covered by the claims of the present invention.

Claims

1. A method for determining the proportion of coke powder, characterized in that, The method includes: Acquire a coke image of the loading area, and perform image segmentation on the coke image to obtain a coke powder area and a coke particle area; Based on the coke particle region, the fractal dimension of the particles and the particle area of ​​each particle are determined, and the total particle volume is obtained by fitting the fractal dimension of the particles and the particle area of ​​each particle. The fractal dimension and area of ​​the powder region are determined based on the coke powder region, and the total powder volume is obtained by fitting the fractal dimension and area of ​​the powder region. The total mass of the particles is obtained based on the total volume of the particles and the preset particle density. The total mass of the powder is obtained based on the total volume of the powder and the preset powder density. The proportion of coke powder is determined based on the ratio of the total mass of the particles to the total mass of the powder.

2. The method for determining the proportion of coke powder according to claim 1, characterized in that, Image segmentation of the coke image includes: The coke image is segmented to obtain an initial coke powder region and an initial coke particle region. The equivalent diameter of each particle is calculated based on the particle area of ​​each particle in the initial coke particle region. If the equivalent diameter of the particle is less than or equal to a preset diameter threshold, then the particle is marked. All marked particles are divided into newly added coke powder regions, and the initial coke powder region plus the newly added coke powder region is taken as the coke powder region. The initial coke particle region is obtained by removing the newly added coke powder region.

3. The method for determining the proportion of coke powder according to claim 2, characterized in that, The total powder volume is obtained by fitting the fractal dimension of the powder and the area of ​​the powder region, including: The number of grids occupied by the boundary of the coke powder region is counted. The coke powder region includes the initial coke powder region and the newly added coke powder region. The number of grids is the number of square grids with a preset side length. Based on the number of grids occupied by the boundary of the initial coke powder region and the preset length, the fractal dimension corresponding to the initial coke powder region is determined. Based on the number of grids occupied by the boundary of the newly added coke powder region and the preset length, the fractal dimension corresponding to the newly added coke powder region is determined. The powder fractal dimension is determined based on the average of the fractal dimensions corresponding to the initial coke powder region and the newly added coke powder region.

4. The method for determining the proportion of coke powder according to any one of claims 1-3, characterized in that, Before acquiring the coke image of the loading area, the following steps are also included: Obtain vehicle license plate images within the coke loading area of ​​the factory, perform text detection on the license plate images, and obtain license plate information; The license plate number information is compared with a preset valid license plate number. If the comparison is consistent, an image of coke in the loading area of ​​the vehicle is captured as the coke image.

5. The method for determining the proportion of coke powder according to claim 1, characterized in that, After determining the coke powder ratio based on the ratio of the total mass of the particles to the total mass of the powder, the distance between the loading area and the image acquisition device is obtained. If the distance is greater than or equal to a preset distance threshold, the method further includes: If the coke powder ratio is less than or equal to the preset ratio correction value, then the coke powder ratio is used as the corrected coke powder ratio. If the proportion of coke powder is greater than the preset proportion correction value, then the preset proportion correction value is used as the corrected coke powder proportion.

6. The method for determining the proportion of coke powder according to claim 1, characterized in that, After determining the coke powder ratio based on the ratio of the total mass of the particles to the total mass of the powder, the distance between the loading area and the image acquisition device is obtained. If the distance is less than a preset distance threshold, the method further includes: normalizing the coke powder ratio to obtain the processed coke powder ratio. The proportion of the processed coke powder is linearly scaled based on a preset scaling factor to obtain a corrected coke powder proportion.

7. The method for determining the proportion of coke powder according to claim 5 or 6, characterized in that, After obtaining the corrected coke powder ratio, the following is also included: The loading area is divided into multiple subsets based on a preset height ratio, and the area of ​​each subset is obtained according to the number of pixels occupied by each subset. The overall coke powder ratio is obtained based on the corrected coke powder ratio and the subset area corresponding to the multiple region subsets.

8. A device for determining the proportion of coke powder, characterized in that, The device includes: The image processing module is used to acquire a coke image of the loading area, and to perform image segmentation on the coke image to obtain a coke powder area and a coke particle area. The particle volume determination module is used to determine the fractal dimension of the particles and the particle area of ​​each particle based on the coke particle region, and to obtain the total particle volume by fitting the fractal dimension of the particles and the particle area of ​​each particle. The powder volume determination module is used to determine the fractal dimension of the powder and the area of ​​the powder region based on the coke powder region, and to obtain the total powder volume by fitting the fractal dimension of the powder and the area of ​​the powder region. The powder ratio determination module is used to obtain the total mass of particles based on the total volume of particles and the preset particle density, obtain the total mass of powder based on the total volume of powder and the preset powder density, and determine the coke powder ratio based on the ratio of the total mass of particles to the total mass of powder.

9. An electronic device, characterized in that, The electronic device includes: One or more processors; A storage device for storing one or more programs, which, when executed by one or more processors, cause the electronic device to implement the method for determining the coke powder ratio as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, It stores a computer program that, when executed by the computer's processor, causes the computer to perform the coke powder ratio determination method as described in any one of claims 1-7.

Images