A method for identifying taphole mud in complex environments and an automated taphole mud filling system

Abstract

The present application relates to a method for identifying cannon mud in a complex environment and an automated cannon mud filling system. The method includes responding to an acquired grabbing instruction, moving to the grabbing area and acquiring an image of the grabbing area or directly acquiring an image of the grabbing area and using a polarized image to synthesize a feature image containing a grab target and using the content in the feature image to synthesize the edge contour features of the grab target. When the integrity of the grab target in the polarized image does not meet the requirements, a candidate light source is used to regenerate the polarized image. The candidate light source is a monochromatic light source, and the image includes multiple polarized images. The cannon mud identification method and automated cannon mud filling system in a complex environment disclosed in the present application use polarized images for initial content identification and grabbing, and then use a synthetic processing method to obtain the contour features of the cannon mud, and at the same time shield dust interference during the synthetic processing process to achieve better recognition accuracy.

Description

Technical Field

[0001] The present application relates to the field of automated production technology, and in particular to a method for identifying taphole mud in a complex environment and an automated taphole mud filling system. Background Art

[0002] During the discharge stage of blast furnace steelmaking, it is necessary to make a breach at the iron outlet of the blast furnace to allow the refined molten iron to flow out, and then the breach at the iron outlet needs to be sealed. The equipment used for sealing is a blast furnace mud cannon, which can quickly and accurately block the iron outlet after the iron is discharged, so that the blast furnace can quickly enter the next cycle of operation.

[0003] Blast furnace mud cannons are divided into pneumatic mud cannons, electric mud cannons and hydraulic mud cannons according to their power types. Since the thrust of pneumatic mud cannons is limited by certain conditions and the mud pushing capacity cannot be further increased, it has been eliminated in practice. Electric mud cannons and hydraulic mud cannons are mostly used in production.

[0004] In order to achieve rapid plugging, blast furnace mud guns mostly use push-in operation, which leads to a relatively harsh working environment for blast furnace mud guns, with high temperature and dust as the main influencing factors. In order to solve this problem, blast furnace mud guns began to use loading manipulators to load mud. Compared with manual loading, loading manipulators have considerable advantages in loading speed and heavy-load work.

[0005] However, due to the working environment, the loading robot still has certain errors in identifying the loading object, which is mainly affected by high temperature and dust. High temperature will cause the image obtained by the image sensor to be incomplete and distorted, and dust will directly affect the image quality. The use of high-precision image acquisition methods can solve this problem to a certain extent, but there is a problem of slow processing speed, which will affect the plugging work of the blast furnace mud gun. Summary of the invention

[0006] The present application provides a method for identifying cannon clay and an automated cannon clay filling system in a complex environment, which uses polarized images for initial content recognition and capture, and then uses a synthetic processing method to obtain the contour features of the cannon clay. At the same time, dust interference is shielded during the synthetic processing process to achieve better recognition accuracy.

[0007] The above-mentioned purpose of the present application is achieved through the following technical solutions:

[0008] In a first aspect, the present application provides a method for identifying taphole mud in a complex environment, comprising:

[0009] In response to the acquired grabbing instruction, move to the grabbing area and acquire an image of the grabbing area or directly acquire an image of the grabbing area, wherein the image includes a plurality of polarization images;

[0010] Using the polarization image to synthesize a feature image containing the grasped target and using the content in the feature image to synthesize edge contour features of the grasped target;

[0011] When the completeness of the captured object in the polarization image does not meet the requirement, a candidate light source is used to regenerate the polarization image, and the candidate light source is a monochromatic light source.

[0012] In a possible implementation manner of the first aspect, using the polarization image to synthesize a feature image containing the grasped target includes:

[0013] A polarization image whose placement area meets the requirements is selected from the multiple polarization images obtained, and recorded as a basic polarization image;

[0014] Identify and obtain characteristic areas on the basic polarization image;

[0015] Using the characteristic region to crop other polarization images to obtain cropped polarization images, the number of cropped polarization images is multiple;

[0016] The base polarization image and the cropped polarization image are used to synthesize a feature image containing the grasped target.

[0017] In a possible implementation manner of the first aspect, using content in the feature image to synthesize edge contour features of the grasped object includes:

[0018] Establishing an analysis straight line on the cropped polarization image and establishing a characteristic curve based on the analysis straight line;

[0019] The characteristic curve is transferred into the time domain and frequency domain for decomposition to obtain a characteristic curve group;

[0020] Determine the starting position point and the ending position point of each sub-characteristic curve in the characteristic curve group and mark the obtained starting position point and the ending position point on the analysis straight line;

[0021] Merging the corresponding analysis lines on the basic polarization image and the cropped polarization image to obtain a merged analysis line;

[0022] Merge the position segments on the merge analysis straight line. When merging, delete the position segments on other position segments.

[0023] The remaining position segments are displayed on the basic polarization image to obtain a feature image containing the grasped target.

[0024] In a possible implementation manner of the first aspect, transferring the characteristic curve into the time domain and the frequency domain for decomposition includes:

[0025] Loading the characteristic curves onto a plurality of different acquisition windows respectively to obtain a plurality of distinguishing characteristic curves, wherein the number of the distinguishing characteristic curves is a plurality;

[0026] Perform fast Fourier transform on the distinguishing characteristic curve;

[0027] The fast Fourier transformed distinguishing characteristic curves are added and averaged to obtain a characteristic curve spectrum curve;

[0028] A wavelet is generated using the characteristic curve spectrum curve and the generated wavelet is superimposed on the characteristic curve, and a starting position point and a cutoff position point of a sub-characteristic curve corresponding to the wavelet are determined.

[0029] In a possible implementation manner of the first aspect, determining the integrity of the captured target in the polarization image includes:

[0030] Draw the outer contour of the grasped object and calculate the distinguishing features of the outer contour, including length, width and enclosed area;

[0031] Use distinguishing features to determine the completeness of the grasped target;

[0032] When there is at least one grasping target whose completeness meets the requirement on the polarization image, the polarization image is not regenerated using the candidate light source.

[0033] In a possible implementation of the first aspect, when there is at least one grasped target whose completeness meets the requirements on the polarization image, it is also necessary to compare the obtained grasped target with the model targets in the model library. When there is at least one model target similar to the obtained grasped target, the polarization image is not regenerated using the backup light source.

[0034] In a possible implementation of the first aspect, when the polarization image is regenerated using a backup light source, the position line segment of the regenerated polarization image and the position line segment when the polarization image regeneration is triggered are located on the same straight line motion trajectory of the automated taphole mud filling system.

[0035] In the second aspect, the present application provides a device for identifying cannon mud in a complex environment, comprising:

[0036] An image acquisition unit, configured to respond to the acquired grabbing instruction, move to the grabbing area and acquire an image of the grabbing area or directly acquire an image of the grabbing area, wherein the image includes a plurality of polarization images;

[0037] An image processing unit, used for synthesizing a feature image containing a grasped target using the polarization image and synthesizing edge contour features of the grasped target using the content in the feature image;

[0038] When the completeness of the captured object in the polarization image does not meet the requirement, a candidate light source is used to regenerate the polarization image, and the candidate light source is a monochromatic light source.

[0039] In a third aspect, the present application provides an automated taphole mud filling system, the system comprising:

[0040] one or more memories for storing instructions; and

[0041] One or more processors, used to call and run the instructions from the memory to execute the method as described in the first aspect and any possible implementation of the first aspect.

[0042] In a fourth aspect, the present application provides a computer-readable storage medium, the computer-readable storage medium comprising:

[0043] Program, when the program is executed by a processor, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0044] In a fifth aspect, the present application provides a computer program product, comprising program instructions. When the program instructions are executed by a computing device, the method described in the first aspect and any possible implementation of the first aspect is executed.

[0045] In a sixth aspect, the present application provides a chip system, which includes a processor for implementing the functions involved in the above aspects, for example, generating, receiving, sending, or processing the data and / or information involved in the above methods.

[0046] The chip system may be composed of chips, or may include chips and other discrete devices.

[0047] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wired or wireless means, or the processor and the memory can also be coupled on the same device. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 This is a schematic flowchart of the steps of a method for identifying cannon mud in a complex environment provided by the present application.

[0049] Figure 2 It is a schematic diagram of obtaining a characteristic image by synthesizing multiple polarization images provided in the present application.

[0050] Figure 3 It is a schematic diagram of a characteristic curve provided in this application.

[0051] Figure 4 This is a schematic diagram of a sub-characteristic curve provided by the present application, which is represented by using a starting position point and an ending position point.

[0052] Figure 5 This is a schematic diagram of merging position line segments provided by the present application.

[0053] Figure 6 It is a schematic diagram of the appearance of a kind of cannon mud provided in this application.

[0054] Figure 7 It is a schematic diagram of the appearance of another type of taphole clay provided in this application.

[0055] Figure 8 It is a schematic diagram of the appearance of another kind of cannon clay provided in this application. DETAILED DESCRIPTION

[0056] The technical solution in this application is further described in detail below in conjunction with the accompanying drawings.

[0057] This application discloses a method for identifying taphole mud in complex environments. Figure 1 In some examples, the method for identifying taphole mud in a complex environment disclosed in this application includes the following steps:

[0058] S101, in response to an acquired grabbing instruction, acquiring an image of the grabbing area after moving to the grabbing area or directly acquiring an image of the grabbing area, wherein the image includes a plurality of polarization images;

[0059] S102, using the polarization image to synthesize a feature image containing the grasped target and using the content in the feature image to synthesize edge contour features of the grasped target;

[0060] When the completeness of the captured object in the polarization image does not meet the requirement, a candidate light source is used to regenerate the polarization image, and the candidate light source is a monochromatic light source.

[0061] First of all, it is necessary to explain the application scenario of the technical solution disclosed in this application. The gun mud identification method in a complex environment disclosed in this application is applied to an automated gun mud filling system. The automated gun mud filling system consists of two parts: a filling robot and a controller.

[0062] The automated mud filling system is located between the mud placement area and the blast furnace mud cannon, and is responsible for placing the mud from the mud placement area into the filling cavity on the blast furnace mud cannon. The automated mud filling system is connected to the control unit of the blast furnace mud cannon and is linked with the blast furnace mud cannon. The advantage of the linkage is that it can automatically trigger the filling signal and determine the filling position. Because the filling position of the blast furnace mud cannon can be determined in three-dimensional space according to the size and movement process of the blast furnace mud cannon, that is, based on the linkage, the position coordinates of the filling cavity on the blast furnace mud cannon are known quantities.

[0063] The controller of the automated taphole mud filling system acquires images with the aid of a polarization image sensor. In step S101, in response to an acquired grasping instruction, the filling robot moves to the grasping area and acquires an image of the grasping area or directly acquires an image of the grasping area.

[0064] In some possible implementations, the polarization image sensor is deployed at the far end of the loading robot, so that the polarization image sensor can be as close to the cannon mud as possible, which helps to obtain a clearer image. After the loading robot moves to the grasping area, obtaining an image of the grasping area indicates that the loading robot is now located at another position, and directly obtaining an image of the grasping area indicates that the loading robot is now located in the cannon mud placement area.

[0065] The images acquired by the polarization image sensor are multiple polarization images, and the relevant contents are as follows:

[0066] Light is reflected from the surface of an object as polarized light and unpolarized light. The degree of polarization of the reflected light depends on the surface condition of the object (metal, color, roughness, etc.) and the reflection angle. The polarization direction can provide information about the reflective surface of the object because different colors have different polarization directions.

[0067] See also Figure 2 By synthesizing multiple polarization images, a feature image containing the grasped target can be obtained. That is, in step S202, the polarization images are used to synthesize the feature image containing the grasped target. After obtaining the feature image, the content in the feature image is used to synthesize the edge contour features of the grasped target.

[0068] Of course, at this time, we are faced with the situation that the integrity of the grasped target is insufficient. At this time, we need to use a candidate light source to regenerate the polarization image. The candidate light source is a monochromatic light source. The advantage of a monochromatic light source is that it can obtain more information and improve the integrity of the grasped target.

[0069] In some examples, the specific method of using the polarization image to synthesize a feature image containing the grasped target is:

[0070] S201, selecting a polarization image whose placement area meets the requirements from the obtained multiple polarization images, and recording it as a basic polarization image;

[0071] S202, identifying and obtaining a feature area on the basic polarization image;

[0072] S203, using the characteristic region to crop other polarization images to obtain cropped polarization images, where the number of cropped polarization images is multiple;

[0073] S204, synthesizing a feature image including the grasped target using the basic polarization image and the cropped polarization image.

[0074] In step S201 to step S204, a polarization image whose placement area meets the requirements is first selected from the multiple polarization images obtained and recorded as the basic polarization image. The purpose of selecting the basic polarization image is to use the basic polarization image to process the feature area, and the feature area here refers to the placement area of ​​the cannon mud.

[0075] The placement area meets the requirements means that the clarity of the placement area meets the requirements. In the polarization image, the clarity of the placement area means that the placement area can be judged by the content displayed on the polarization image, because the shape of the placement area is fixed.

[0076] After obtaining the basic polarization image, the feature area is identified and obtained on the basic polarization image, and then the feature area is used to crop other polarization images to obtain a cropped polarization image. Finally, the basic polarization image and the cropped polarization image are used to synthesize a feature image containing the captured target.

[0077] Compared with directly synthesizing using polarization images, the above method removes some areas on polarization images other than the basic polarization image. This method can limit the processing range to within the feature area.

[0078] It should be noted here that the placement area of ​​the cannon clay is generally processed with additional colors to make it different from the surrounding environmental color and the cannon clay color. When selecting a polarization image whose placement area meets the requirements from the multiple polarization images obtained, it is determined based on the completeness of the placement area in the obtained polarization image. The completeness of the placement area here refers to the completeness of the edge.

[0079] After obtaining the feature image containing the grasped target, it is necessary to use the content in the feature image to synthesize the edge contour features of the grasped target. The specific steps are as follows:

[0080] S301, establishing an analysis line on the cropped polarization image and establishing a characteristic curve based on the analysis line;

[0081] S302, transferring the characteristic curve into the time domain and the frequency domain for decomposition to obtain a characteristic curve group;

[0082] S303, determining the starting position point and the ending position point of each sub-characteristic curve in the characteristic curve group and marking the obtained starting position point and the ending position point on the analysis line;

[0083] S304, merging corresponding analysis lines on the basic polarization image and the cropped polarization image to obtain a merged analysis line;

[0084] S305, merging the position line segments on the merge analysis straight line, and deleting the position line segments located on other position line segments during the merging process;

[0085] S306, displaying the remaining position line segments on the basic polarization image to obtain a feature image including the captured target.

[0086] Specifically, in step S301, an analysis line is first established on the cropped polarization image and a characteristic curve is established based on the analysis line. The characteristic curve is established by creating discrete points in a coordinate system, where the horizontal coordinates of the discrete points are the sequential coordinates of the pixel points and the vertical coordinates are the numerical coordinates of the pixel points. The discrete points are connected by a curve to obtain a characteristic curve, such as Figure 3 shown.

[0087] Then in S302, the characteristic curve is transferred into the time domain and the frequency domain for decomposition to obtain a characteristic curve group. At this time, the sub-characteristic curve in the characteristic curve group has a starting time point and an ending time point, and the starting time point and the ending time point correspond to the starting position point and the ending position point respectively.

[0088] In step S303, the starting position point and the ending position point of each sub-characteristic curve in the characteristic curve group are determined and the obtained starting position point and the ending position point are marked on the analysis line. That is, in this step, each sub-characteristic curve is represented by the starting position point and the ending position point, and the starting position point and the ending position point are represented by a position line segment, and the two endpoints of the position line segment are the starting position point and the ending position point respectively. Figure 4 shown.

[0089] In step S304, the corresponding analysis lines on the basic polarization image and the cropped polarization image are merged to obtain a merged analysis line. The merged analysis line is composed of multiple analysis lines. It can be considered that the clones of the merged analysis line at multiple polarization angles are merged.

[0090] In step S305, the position segments on the combined analysis line are combined. During the combination process, the position segments on other position segments are deleted. The purpose of this method is to reduce the number of position segments as much as possible. Figure 5 shown.

[0091] Finally, in step S306, the remaining position line segments are displayed on the basic polarization image to obtain a feature image containing the grasped target. At this time, the color of the grasped target contained in the feature image tends to be uniform.

[0092] The above processing method can be regarded as processing the image on different layers. The gun mud placement area, mud gun and dust are located in different layers respectively. For the information on different layers, the information is directly converted into position segments. Taking dust as an example, the position segment corresponding to the dust is very short. In this application, the length comparison method can be used to remove it, avoiding the problems of large processing range and high recognition difficulty of the recognition method.

[0093] And during the removal process, other position line segments will not be affected, that is, during the removal process, the cannon clay image will not be damaged on a large scale, resulting in the subsequent inability to identify the contour of the cannon clay.

[0094] In some examples, the characteristic curves are transferred into the time domain and frequency domain for decomposition as follows:

[0095] Loading the characteristic curves onto a plurality of different acquisition windows respectively to obtain a plurality of distinguishing characteristic curves, wherein the number of the distinguishing characteristic curves is a plurality;

[0096] Perform fast Fourier transform on the distinguishing characteristic curve;

[0097] The fast Fourier transformed distinguishing characteristic curves are added and averaged to obtain a characteristic curve spectrum curve;

[0098] A wavelet is generated using the characteristic curve spectrum curve and the generated wavelet is superimposed on the characteristic curve, and a starting position point and a cutoff position point of a sub-characteristic curve corresponding to the wavelet are determined.

[0099] In the above method, a multi-window spectrum processing method is used, and the relevant introduction is as follows:

[0100] Multi-window spectral processing is a non-parametric spectral estimation method that uses multiple orthogonal or nearly orthogonal conical windows to segment the signal, and then performs Fourier transform on each segment to obtain multiple independent spectral estimates. By averaging these spectral estimates, a more stable spectral estimation result with smaller variance can be obtained.

[0101] In the present application, multi-window spectrum processing is used to reduce spectrum leakage, so that when the characteristic curve spectrum curve is used to generate wavelets, the matching degree of the wavelets can be improved to avoid erroneous starting and ending position points.

[0102] The specific method for judging the integrity of the captured target in the polarization image is as follows:

[0103] Draw the outer contour of the grasped object and calculate the distinguishing features of the outer contour, including length, width and enclosed area;

[0104] Use distinguishing features to determine the completeness of the grasped target;

[0105] When there is at least one grasping target whose completeness meets the requirement on the polarization image, the polarization image is not regenerated using the candidate light source.

[0106] It should be understood that the specifications of the cannon clay used at a fixed position are fixed. Although the cannon clay may have different outer contours due to issues such as placement, placement angle, and overlap, the differences can be statistically analyzed. One feasible way is to create a model library that stores images of cannon clay in different postures. Figures 6 to 8 As shown, these images all have three distinguishing features: length, width and enclosed area. By using these three distinguishing features for comparison, the completeness of the grasped target can be determined.

[0107] The reason for determining the completeness of the grasping target is that during the recognition process, part of the two outer contours may be reconstructed into a contour. At this time, the contour obtained is not the contour of the cannon clay, and it needs to be identified and eliminated, because this grasping target will cause the robot arm to be unable to grasp the cannon clay.

[0108] In some possible implementations, when there is at least one grasped target on the polarization image whose completeness meets the requirements, it is also necessary to compare the obtained grasped target with the model targets in the model library. When there is at least one model target similar to the obtained grasped target, the polarization image is not regenerated using the backup light source.

[0109] In a possible implementation of the first aspect, when the polarization image is regenerated using a backup light source, the position line segment of the regenerated polarization image and the position line segment when the polarization image regeneration is triggered are located on the same straight line motion trajectory of the automated taphole mud filling system.

[0110] This method allows the recovered polarization image to be used only by zooming in and out, without the need for spatial posture correction, and has advantages in terms of data processing volume, data processing error, and data processing speed.

[0111] The present application also provides a device for identifying cannon mud in a complex environment, comprising:

[0112] An image acquisition unit, configured to respond to the acquired grabbing instruction, move to the grabbing area and acquire an image of the grabbing area or directly acquire an image of the grabbing area, wherein the image includes a plurality of polarization images;

[0113] An image processing unit, used for synthesizing a feature image containing a grasped target using the polarization image and synthesizing edge contour features of the grasped target using the content in the feature image;

[0114] When the completeness of the captured object in the polarization image does not meet the requirement, a candidate light source is used to regenerate the polarization image, and the candidate light source is a monochromatic light source.

[0115] Furthermore, it also includes:

[0116] An image selection unit, used to select a polarization image whose placement area meets the requirements from the obtained multiple polarization images, and record it as a basic polarization image;

[0117] A feature region recognition unit, used for recognizing and obtaining a feature region on a basic polarization image;

[0118] A cutting unit, used to cut other polarization images using the characteristic area to obtain a cut polarization image, where the number of the cut polarization images is multiple;

[0119] The synthesis unit is used to synthesize a feature image containing a grasped target by using a basic polarization image and a cropped polarization image.

[0120] Furthermore, it also includes:

[0121] A curve establishing unit, used for establishing an analysis straight line on the cropped polarization image and establishing a characteristic curve based on the analysis straight line;

[0122] A curve decomposition unit is used to transfer the characteristic curve into the time domain and the frequency domain for decomposition to obtain a characteristic curve group;

[0123] A position processing unit, used for determining a starting position point and an ending position point of each sub-characteristic curve in the characteristic curve group and marking the obtained starting position point and the ending position point on the analysis straight line;

[0124] A first merging processing unit, used for merging corresponding analysis lines located on the basic polarization image and the cropped polarization image to obtain a merged analysis line;

[0125] A second merging processing unit is used to merge the position line segments on the merge analysis straight line, and during the merging process, the position line segments located on other position line segments are deleted;

[0126] The display processing unit is used to display the remaining position segments on the basic polarization image to obtain a feature image containing the captured target.

[0127] Furthermore, it also includes:

[0128] A loading unit, used for loading the characteristic curves onto a plurality of different acquisition windows respectively to obtain a plurality of distinguishing characteristic curves;

[0129] A transform unit, for performing a fast Fourier transform on the distinguishing characteristic curve;

[0130] An addition and average processing unit, used for adding and averaging the distinguishing characteristic curves after fast Fourier transformation to obtain a characteristic curve spectrum curve;

[0131] The superposition processing unit is used to generate a wavelet using the characteristic curve spectrum curve and superimpose the generated wavelet on the characteristic curve, and determine the starting position point and the ending position point of the sub-characteristic curve corresponding to the wavelet.

[0132] Furthermore, it also includes:

[0133] A distinguishing feature processing unit, used for drawing the outer contour of the grasped target and calculating the distinguishing features of the outer contour, wherein the distinguishing features include length, width and enclosed area;

[0134] A completeness processing unit, for determining the completeness of the grasped object using the distinguishing features;

[0135] When there is at least one grasping target whose completeness meets the requirement on the polarization image, the polarization image is not regenerated using the candidate light source.

[0136] Furthermore, when there is at least one grasping target whose completeness meets the requirements on the polarization image, it is also necessary to compare the obtained grasping target with the model targets in the model library. When there is at least one model target similar to the obtained grasping target, the alternative light source is not used to regenerate the polarization image.

[0137] Furthermore, when the polarization image is regenerated using a backup light source, the position line segment of the regenerated polarization image and the position line segment when the polarization image regeneration is triggered are located on the same linear motion trajectory of the automated taphole mud filling system.

[0138] In one example, the unit in any of the above devices can be one or more integrated circuits configured to implement the above methods, such as: one or more application specific integrated circuits (ASICs), or, one or more digital signal processors (DSPs), or, one or more field programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0139] For another example, when the units in the device can be implemented in the form of a processing element scheduling program, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor that can call a program. For another example, these units can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0140] Various objects such as various messages / information / equipment / network elements / systems / devices / actions / operations / processes / concepts that may appear in this application are named. It can be understood that these specific names do not constitute a limitation on the relevant objects. The names assigned may change with factors such as scenarios, contexts or usage habits. The understanding of the technical meaning of the technical terms in this application should be mainly determined from the functions and technical effects embodied / executed in the technical scheme.

[0141] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0142] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as 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 interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0143] 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.

[0144] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0145] It should also be understood that in various embodiments of the present application, the first, second, etc. are only used to indicate that multiple objects are different. For example, the first time window and the second time window are only used to indicate different time windows. They should not have any impact on the time window itself, and the first, second, etc. mentioned above should not impose any limitations on the embodiments of the present application.

[0146] It should also be understood that in the various embodiments of the present application, unless otherwise specified or there is a logical conflict, the terms and / or descriptions between different embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their internal logical relationships.

[0147] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a computer-readable storage medium, including several instructions for 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 methods described in each embodiment of the present application. The aforementioned computer-readable storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0148] The present application also provides an automated taphole mud filling system, the system comprising:

[0149] one or more memories for storing instructions; and

[0150] One or more processors are used to call and run the instructions from the memory to execute the method as described above.

[0151] The present application also provides a computer program product, which includes instructions. When the instructions are executed, the terminal device and the network device perform operations of the terminal device and the network device corresponding to the above method.

[0152] The present application also provides a chip system, which includes a processor for implementing the functions involved in the above content, such as generating, receiving, sending, or processing the data and / or information involved in the above method.

[0153] The chip system may be composed of chips, or may include chips and other discrete devices.

[0154] The processor mentioned in any of the above places can be a CPU, a microprocessor, an ASIC, or one or more integrated circuits for executing programs for controlling the above-mentioned feedback information transmission method.

[0155] In a possible design, the chip system also includes a memory, which is used to store necessary program instructions and data. The processor and the memory can be decoupled and respectively set on different devices, connected by wire or wireless means to support the chip system to implement various functions in the above embodiments. Alternatively, the processor and the memory can also be coupled on the same device.

[0156] Optionally, the computer instructions are stored in a memory.

[0157] Optionally, the memory is a storage unit within the chip, such as a register, a cache, etc. The memory can also be a storage unit within the terminal located outside the chip, such as a ROM or other types of static storage devices that can store static information and instructions, RAM, etc.

[0158] It can be understood that the memory in the present application can be a volatile memory or a non-volatile memory, or can include both volatile and non-volatile memories.

[0159] The non-volatile memory may be a ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), or a flash memory.

[0160] The volatile memory may be a RAM, which is used as an external cache. There are many different types of RAM, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), and direct memory bus RAM.

[0161] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. A method for identifying taphole mud in a complex environment, characterized in that: include: In response to the acquired grabbing instruction, move to the grabbing area and acquire an image of the grabbing area or directly acquire an image of the grabbing area, wherein the image includes a plurality of polarization images; Using the polarization image to synthesize a feature image containing the grasped target and using the content in the feature image to synthesize edge contour features of the grasped target; When the integrity of the captured target in the polarization image does not meet the requirements, a candidate light source is used to regenerate the polarization image, and the candidate light source is a monochromatic light source; Using polarization images to synthesize images containing features of the grasped target includes: A polarization image whose placement area meets the requirements is selected from the multiple polarization images obtained, and recorded as a basic polarization image; Identify and obtain characteristic areas on the basic polarization image; Using the characteristic region to crop other polarization images to obtain cropped polarization images, the number of cropped polarization images is multiple; Using the basic polarization image and the cropped polarization image to synthesize a feature image containing the grasped target; Using the content in the feature image to synthesize the edge contour features of the grasped target includes: Establishing an analysis straight line on the cropped polarization image and establishing a characteristic curve based on the analysis straight line; The characteristic curve is transferred into the time domain and frequency domain for decomposition to obtain a characteristic curve group; Determine the starting position point and the ending position point of each sub-characteristic curve in the characteristic curve group and mark the obtained starting position point and the ending position point on the analysis straight line; Merging the corresponding analysis lines on the basic polarization image and the cropped polarization image to obtain a merged analysis line; Merge the position segments on the merge analysis straight line. When merging, delete the position segments on other position segments. The remaining position segments are displayed on the basic polarization image to obtain a feature image containing the grasped target.

2. The method for identifying taphole mud in a complex environment according to claim 1, characterized in that: Transferring the characteristic curve into the time domain and frequency domain for decomposition includes: Loading the characteristic curves onto a plurality of different acquisition windows respectively to obtain a plurality of distinguishing characteristic curves, wherein the number of the distinguishing characteristic curves is a plurality; Perform fast Fourier transform on the distinguishing characteristic curve; The fast Fourier transformed distinguishing characteristic curves are added and averaged to obtain a characteristic curve spectrum curve; A wavelet is generated using the characteristic curve spectrum curve and the generated wavelet is superimposed on the characteristic curve, and a starting position point and a cutoff position point of a sub-characteristic curve corresponding to the wavelet are determined.

3. The method for identifying taphole mud in a complex environment according to claim 1 or 2, characterized in that: Judging the integrity of the captured object in the polarization image includes: Draw the outer contour of the grasped object and calculate the distinguishing features of the outer contour, including length, width and enclosed area; Use distinguishing features to determine the completeness of the grasped target; When there is at least one grasping target whose completeness meets the requirement on the polarization image, the polarization image is not regenerated using the candidate light source.

4. The method for identifying taphole mud in a complex environment according to claim 3, characterized in that: When there is at least one grasping target whose completeness meets the requirements on the polarization image, it is also necessary to compare the obtained grasping target with the model target in the model library. When there is at least one model target similar to the obtained grasping target, the alternative light source is not used to regenerate the polarization image.

5. The method for identifying taphole mud in a complex environment according to claim 1, characterized in that: When the polarization image is regenerated using a candidate light source, the position line segment of the regenerated polarization image and the position line segment when the polarization image regeneration is triggered are located on the same linear motion trajectory of the automated taphole mud filling system.

6. A device for identifying taphole mud in a complex environment, characterized in that: include: An image acquisition unit, configured to respond to the acquired grabbing instruction, move to the grabbing area and acquire an image of the grabbing area or directly acquire an image of the grabbing area, wherein the image includes a plurality of polarization images; An image processing unit, used for synthesizing a feature image containing a grasped target using the polarization image and synthesizing edge contour features of the grasped target using the content in the feature image; When the integrity of the captured target in the polarization image does not meet the requirements, a candidate light source is used to regenerate the polarization image, and the candidate light source is a monochromatic light source; An image selection unit, used to select a polarization image whose placement area meets the requirements from the obtained multiple polarization images, and record it as a basic polarization image; A feature region recognition unit, used for recognizing and obtaining a feature region on a basic polarization image; A cutting unit, used to cut other polarization images using the characteristic area to obtain a cut polarization image, where the number of the cut polarization images is multiple; A synthesis unit, used for synthesizing a feature image containing a grasped target using a basic polarization image and a cropped polarization image; A curve establishing unit, used for establishing an analysis straight line on the cropped polarization image and establishing a characteristic curve based on the analysis straight line; A curve decomposition unit is used to transfer the characteristic curve into the time domain and the frequency domain for decomposition to obtain a characteristic curve group; A position processing unit, used for determining a starting position point and an ending position point of each sub-characteristic curve in the characteristic curve group and marking the obtained starting position point and the ending position point on the analysis straight line; A first merging processing unit, used for merging corresponding analysis lines located on the basic polarization image and the cropped polarization image to obtain a merged analysis line; A second merging processing unit is used to merge the position line segments on the merge analysis straight line, and during the merging process, the position line segments located on other position line segments are deleted; The display processing unit is used to display the remaining position segments on the basic polarization image to obtain a feature image containing the captured target.

7. An automated taphole mud filling system, characterized in that: The system comprises: one or more memories for storing instructions; and One or more processors, configured to call and execute the instructions from the memory to perform the method according to any one of claims 1 to 5.

8. A computer-readable storage medium, characterized in that: The computer readable storage medium comprises: The program, when the program is executed by a processor, the method according to any one of claims 1 to 5 is executed.

Images