Sintering pallet wheel deviation detection method and device

Abstract

The invention relates to a sintering pallet wheel deviation detection method, the sintering pallet comprises a transport carriage and wheels located on the two sides of the transport carriage, and the method comprises the following steps that images of the wheels in the driving process are obtained through camera lenses arranged downwards above the wheels; detecting the position of a wheel in the image through a target detection model; delineating a to-be-detected roi area of the track in the first image according to the detected positions of the adjacent wheels, and detecting the position of the track through an image processing algorithm; and calculating the change of the offset difference between the wheel and the track and recording the change as a detection result. The invention further provides a corresponding device for detecting the deviation of the wheels of the sintering pallet. According to the sintering pallet wheel deviation detection method, the accuracy and the working efficiency of sintering pallet wheel deviation detection can be improved, the operation safety is improved, the installation and maintenance cost is reduced, and the distance deviating from the track can be calculated and recorded.

Description

Technical Field

[0001] The present application relates to a technical field related to sintering trolley track safety, and in particular to a sintering trolley wheel deviation detection method and device. Background Art

[0002] The sintering trolley is the main operating component of the sintering machine. During the operation of the sintering trolley, wheel deviation and derailment often occur, causing sintering machine failure and shutdown, thus affecting production efficiency, operation safety and equipment life. Therefore, monitoring the travel of the sintering wheels is crucial for the stable operation of the sintering machine. However, due to the high temperature and complex environment of the sintering process, existing monitoring methods such as manual monitoring and distance measuring equipment may have the following disadvantages:

[0003] On the one hand, manual monitoring of the wheel driving status can be used to respond to emergencies, but the work intensity is high and it is easy to miss detections. In high temperature and dusty environments, it may affect the health and safety of workers.

[0004] On the other hand, when using distance measuring equipment to track wheel position, there may be problems such as high installation and maintenance costs, possible interference in complex environments, and low accuracy.

[0005] On the other hand, when visual algorithms such as machine learning are currently used to monitor wheels, the main method is to determine whether the wheels are offset based on image features, without real-time calculation, recording, and monitoring of the distance the wheels deviate from the track. This may lead to the problem of not discovering safety hazards in a timely manner.

[0006] Therefore, in this context, how to provide a sintering trolley wheel offset detection method that can improve the accuracy and work efficiency of sintering trolley wheel offset detection, improve operation safety, reduce installation and maintenance costs, and calculate and record the distance of deviation from the track is a technical problem to be solved. Summary of the invention

[0007] In view of the above problems in the prior art, the present application provides a method and device for detecting wheel deviation of a sintering trolley, so as to improve the accuracy and work efficiency of wheel deviation detection of the sintering trolley, enhance operational safety, reduce installation and maintenance costs, and calculate and record the distance of deviation from the track.

[0008] To achieve the above-mentioned object, the first aspect of the present application provides a method for detecting wheel deviation of a sintering trolley, wherein the sintering trolley comprises a transport carriage and wheels located on both sides of the transport carriage;

[0009] The method comprises:

[0010] Acquiring an image of the wheel during driving as a first image through a camera lens arranged downward above the wheel;

[0011] Acquire the position of the adjacent wheels located on one side of the transport carriage in the first image through the target detection model;

[0012] According to the positions of the adjacent wheels obtained by the detection, the ROI region to be detected of the track in the first image is circled as the second image;

[0013] detecting the track position in the second image by an image processing algorithm;

[0014] The change of the offset difference between the wheel and the track is calculated and recorded as the detection result.

[0015] From the above, by using cameras as detection tools, operational safety can be improved and installation and maintenance costs can be reduced; by using target detection models, the accuracy of wheel offset detection can be improved; by combining with track detection methods based on image processing, the efficiency of detection can be improved; by calculating the offset interpolation between the wheel and the track, the operation of the trolley can be effectively monitored to prevent the wheel from deviating from the track and causing danger.

[0016] As a possible implementation of the first aspect, the target detection model uses a yolov5s pre-trained model; after the target detection model detects the first image, it returns the size and position information P of the minimum circumscribed rectangle of the wheel, where P is expressed by the following formula:

[0017] P=(X lt ,Y lt ,Width,Height)

[0018] Among them, X lt ,Y lt is the coordinate of one corner of the minimum bounding rectangle; Width and Height are the width and height of the minimum bounding rectangle.

[0019] From the above, using yolov5s and the training model as the target detection model eliminates the tediousness of collecting data for model training. It has higher recognition accuracy and faster response speed, which can meet the actual computing and monitoring needs.

[0020] As a possible implementation of the first aspect, the camera lens acquires the first image including the adjacent wheels by setting a fixed frame number; the adjacent wheels include a first wheel and a second wheel; the sizes and position information of the minimum circumscribed rectangles of the first wheel and the second wheel obtained by the detection are recorded as P1 and P2 respectively;

[0021] The ROI area to be detected of the track line is determined according to the coordinates of the two adjacent corners of the minimum circumscribed rectangle corresponding to P1 of the first wheel and the minimum circumscribed rectangle corresponding to P2 of the second wheel as the second image.

[0022] From the above, by setting a fixed frame number, the processing efficiency can be improved while controlling the data volume, and higher-quality wheel images can be obtained; by limiting the detection area by the front and rear wheels, the computational burden of subsequent image processing can be reduced and the recognition accuracy can be improved.

[0023] As a possible implementation manner of the first aspect, the image processing algorithm includes:

[0024] Preprocessing the second image using a median filtering method to eliminate interference caused by image noise;

[0025] Using morphological opening operation to eliminate the influence of light and noise and compensate for the image loss caused by the median filter;

[0026] Using edge detection, all edge information in the second image is extracted.

[0027] From the above, by using the median filtering method, the salt and pepper noise in the image can be effectively removed and the edge information can be retained; the morphological opening method can be used to smooth the boundaries of larger objects through the process of first corrosion and then expansion, and the area of ​​the foreground object can be restored while removing smaller objects and small extensions; the edge detection algorithm can quickly and accurately extract the edge information in the image for subsequent track line detection.

[0028] As a possible implementation manner of the first aspect, the edge information is screened to extract a set of coordinate points in the second detection area that include the edge position of the track; and a unique straight line of the track is obtained by using Hough line detection, where the straight line is expressed by the following formula:

[0029] ρ=x·cos(θ)+y·sin(θ)

[0030] Wherein, ρ is the vertical distance from the origin to the straight line; θ is the angle between the normal of the straight line and the positive direction of the x-axis; x, y are the x-axis and y-axis coordinates of the track edge position coordinate point, respectively;

[0031] The slope of the straight line is obtained according to the following formula:

[0032] m=-cot(θ)

[0033] Where m is the slope of the line.

[0034] From the above, by filtering the track edge position information obtained by edge detection and using the Hough line to detect the unique straight line of the track, it has wider adaptability and can extract global features from local measurements.

[0035] As a possible implementation manner of the first aspect, the position of the circumscribed rectangle of the wheel is adjusted by the slope of the track straight line, so that the circumscribed rectangle of the wheel is parallel to the track straight line.

[0036] From the above, adjusting the wheel circumscribed rectangle to be parallel to the track straight line can accurately determine the direction of the wheel and facilitate calculation of the distance between the wheel and the track.

[0037] As a possible implementation manner of the first aspect, the offset difference d between the wheel and the track is obtained according to the following formula:

[0038] d=|x i ·cos(θ)+y i ·sin(θ)-ρ|

[0039] Among them, x i ,y i are respectively the coordinates of a fixed position point in the circumscribed rectangle of the wheel.

[0040] From the above, by calculating and recording the offset difference between the wheel and the track, it is possible to monitor whether the wheel deviates from the track to prevent safety hazards.

[0041] A second aspect of the present application provides a sintering trolley wheel deviation detection device, comprising:

[0042] An image collection module, used for acquiring an image of the wheel during driving as a first image through a camera lens arranged downward above the wheel;

[0043] An image processing module, which obtains the position of the adjacent wheels located on one side of the transport carriage in the first image by using a target detection algorithm; based on the positions of the front and rear wheels obtained by detection, delineates the ROI area to be detected of the track in the first image as the second image; and detects the track position in the second image by using an image processing algorithm;

[0044] The calculation output module calculates the change of the offset difference between the wheel and the track and records it as the detection result.

[0045] A third aspect of the present application provides a computing device, comprising: a processor and a memory, on which program instructions are stored, and when the program instructions are executed by the processor, the processor executes the sintering trolley wheel deviation detection method according to any one of the first aspects.

[0046] A fourth aspect of the present application provides a computer-readable storage medium having program instructions stored thereon, wherein when the program instructions are executed by a computer, the computer executes the sintering trolley wheel deviation detection method according to any one of the first aspects. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] Figure 1 is a flow chart of a first embodiment of a sintering trolley wheel deviation detection method of the present application;

[0048] Figure 2 is a flow chart of a second embodiment of the sintering trolley wheel deviation detection method of the present application;

[0049] Figure 3 is a schematic diagram of camera position settings provided in an embodiment of the present application;

[0050] Figure 4 is a schematic diagram of a sintering trolley wheel deviation detection device provided in an embodiment of the present application;

[0051] Figure 5 It is a structural schematic diagram of a computing device provided in an embodiment of the present application.

[0052] It should be understood that the size and shape of each block diagram in the above structural diagram are for reference only and should not constitute an exclusive interpretation of the embodiment of the present invention. The relative position and inclusion relationship between the blocks presented in the structural diagram are only schematic representations of the structural association between the blocks, and do not limit the physical connection method of the embodiment of the present invention. DETAILED DESCRIPTION

[0053] The technical solution provided by the present application is further described below with reference to the accompanying drawings and examples. It should be understood that the system structure and business scenarios provided in the examples of the present application are mainly to illustrate the possible implementation methods of the technical solution of the present application and should not be interpreted as the only limitation on the technical solution of the present application. It is known to those of ordinary skill in the art that with the evolution of the system structure and the emergence of new business scenarios, the technical solution provided by the present application is also applicable to similar technical problems.

[0054] It should be understood that the sintering trolley wheel offset calculation scheme provided in the embodiments of the present application includes a sintering trolley wheel offset method, apparatus, computing device and computer-readable storage medium. Since the principles of solving the problems in these technical schemes are the same or similar, some repetitions may not be repeated in the introduction of the following specific embodiments, but it should be regarded that these specific embodiments have been referenced to each other and can be combined with each other.

[0055] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by technicians in the technical field of this application. In the event of any inconsistency, the meaning described in this specification or the meaning derived from the contents recorded in this specification shall prevail. In addition, the terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application. In order to accurately describe the technical content in this application and to accurately understand the present invention, the following explanations or definitions are given to the terms used in this specification before describing the specific embodiments:

[0056] 1) You Only Look Once version 5 small model (YOLOv5s): It is a version in the YOLO model series of real-time target detection algorithm. It is fast and accurate. It can complete target detection and classification tasks in a single forward propagation. YOLOv5s provides an option that balances speed and accuracy.

[0057] 2) Edge Detection Algorithm: It is a key technology in image processing and computer vision. It determines the edge by detecting significant changes in pixel intensity in the image. Common edge detection algorithms include Sobel edge detection and Canny edge detection. These algorithms play a key role in many applications such as image segmentation, feature extraction, and target recognition.

[0058] The sintering trolley wheel offset calculation scheme provided in the embodiment of the present application can obtain the image of the wheel during driving through the camera lens set above the wheel and facing downward; detect the position of the wheel through the target detection algorithm; detect the track position through the image processing algorithm based on the detected wheel position; and finally calculate the offset difference between the wheel and the track. This method can improve the accuracy and work efficiency of the sintering trolley wheel offset detection, improve work safety, reduce installation and maintenance costs, and can calculate and record the distance of deviation from the track. The embodiment of the present application can be applied to wheel offset detection in the fields of sintering trolleys, other types of rail transportation, etc. Referring to the accompanying drawings below, each embodiment of the present application is described in detail.

[0059] The first embodiment of the present application provides a method for detecting wheel deviation of a sintering trolley, wherein the sintering trolley includes a transport carriage and wheels located on both sides of the transport carriage. Figure 1 , the implementation of each step of the method is specifically described, including steps S10-S50.

[0060] S10: Acquire an image of the wheel during driving as a first image through a camera lens arranged downward above the wheel.

[0061] In some embodiments, industrial cameras are used as image data acquisition tools; wherein the industrial cameras may include area array cameras, line array cameras, and other cameras that can acquire images containing visual information.

[0062] In some embodiments, the camera lens can be installed directly above the wheel by hoisting, shooting the wheel and track downward; it can also be fixed in the scene by other methods relative to the track. The vertical direction of the picture taken by the camera can be roughly parallel to the track direction. The relationship between the specific picture direction and the track and the travel direction is not limited, and can be selected according to specific usage requirements, and the related parameters affected by it can be transformed and adjusted.

[0063] In some embodiments, the camera may be set to capture video data at a fixed frame rate for subsequent processing; or the required data may be acquired by rapidly taking multiple static images.

[0064] In some embodiments, the camera can capture at least two adjacent front and rear wheels; the front and rear positions of the wheels can also be calculated by obtaining parameters such as the wheel spacing and the trolley running speed through other means.

[0065] In some embodiments, the acquired image can be processed in real time with the PLC system through a communication protocol; it can also be sent to a suitable processing device for subsequent processing and feedback through a communication protocol or other means of transmitting data.

[0066] S20: Acquire the positions of adjacent wheels located on one side of the transport carriage in the first image through the target detection model.

[0067] In some embodiments, a deep learning target detection algorithm is used to detect the position of the wheel, such as yolov5s can be used as the algorithm used for target detection; wherein, pre-trained models such as yolov5s can be directly used for wheel position detection; the results can also be verified and fine-tuned by collecting the wheel position data of the running trolley; the training and verification data can also be re-collected, and deep learning, machine learning, statistical learning and other models can be built for training and adjustment to obtain a target detection model.

[0068] In some embodiments, the position information of the wheel can be represented by the coordinates of the minimum circumscribed rectangle of the wheel and a fixed position on the wheel image, such as the coordinates of the upper left corner of the minimum circumscribed rectangle; it can also be represented by a set of wheel contour points or other data that can represent the position and direction of the wheel; wherein the position information is the result returned by the target detection model or the result obtained after further calculation.

[0069] In some embodiments, it can be determined whether a wheel is missing based on the wheel position result; if a wheel that should be present is missing in the image, a safety warning is prompted to the corresponding staff.

[0070] S30: According to the detected positions of the adjacent wheels, the ROI region to be detected of the track in the first image is circled as the second image.

[0071] In some embodiments, the position of the track is obtained based on the positions of adjacent wheels. For example, in the first image acquired, the wheel on the top is the first wheel and the wheel on the bottom is the second wheel. The area of ​​the track can be obtained based on the coordinates of the exposed part between the two wheels.

[0072] In some embodiments, the position of the track can be determined by algorithms such as deep learning, machine learning, statistical learning, and probability distribution.

[0073] In some embodiments, the second image is cropped from the first image for subsequent analysis, and image pixels within a certain range around the second image may be retained to retain edge features for subsequent calculations; the first image may also be directly used as data input for subsequent detection of track position using an image processing algorithm.

[0074] S40: Detecting the track position in the second image by using an image processing algorithm.

[0075] In some embodiments, the image processing algorithm first preprocesses the input image; wherein the preprocessing may include steps such as median filtering, morphological opening operation, grayscale, normalization, Gaussian filtering, local enhancement, etc.; by further using morphological opening operation after using median filtering, small noise in the image is eliminated and the area of ​​the lost foreground object is restored.

[0076] In some embodiments, edge detection is used to obtain the track position in the image; wherein, the edge detection algorithm may use the Sobel operator, Canny operator, Laplacian operator, Prewitt operator, Roberts operator, etc.; by detecting all edges in the image, the coordinates of the edge points of the track are screened, and the straight line formula of the track position is obtained by methods such as Hough line detection and straight line fitting; wherein, a unique track line can be obtained by setting the threshold of the Hough line detection algorithm; a unique track line can also be obtained by screening possible track lines using methods such as probability distribution; wherein the track line can be represented in the form of polar coordinates or rectangular coordinates.

[0077] In some embodiments, the orbital position can also be obtained using target detection algorithms such as deep learning.

[0078] S50: Calculate the change of the offset difference between the wheel and the track and record it as a curve detection result.

[0079] In some embodiments, the slope of the track line can be calculated and the detected outer contour of the wheel can be adjusted to make it parallel to the track line to calculate the distance between the two; wherein, the distance from a point at a fixed position on the circumscribed rectangle of the wheel image to the track line can be calculated as the offset interpolation between the wheel and the track; the change of the offset interpolation is recorded as a curve, and the operation of the wheel can be monitored in the real-time system for subsequent maintenance and adjustment.

[0080] In some embodiments, different relative distance detection methods may be used according to specific needs, or intermittent collection and calculation methods may be used to save computing resources.

[0081] The second embodiment of the present application provides a method for detecting wheel deviation of a sintering trolley, wherein the sintering trolley includes a transport carriage and wheels located on both sides of the transport carriage. An industrial camera is set at a position opposite to the wheels on both sides of the carriage, with the lens facing vertically downward, so as to capture the position of the wheel and track images. Figure 2 The method provided by the second embodiment includes the following steps S200-S250.

[0082] S200: Using an industrial camera to obtain an image of the wheel during the driving process as a first image.

[0083] The industrial camera is Figure 3 Set up as shown.

[0084] During the driving process of the sintering trolley, an industrial camera is used through remote control to obtain an image containing two adjacent wheels in front and behind, and the track should be clearly visible between the wheels.

[0085] The obtained image is sent to a computing device as a first image.

[0086] S210: Obtain the positions of adjacent wheels in the first image through the yolov5s pre-trained model.

[0087] In the computing device, the first image is input into the calibrated and verified yolov5 pre-trained model to obtain the position information P of the wheel in the first image in the following format:

[0088] P=(X lt ,Y lt ,Width,Height)

[0089] Among them, X lt ,Y lt is the coordinate of the upper left corner of the minimum circumscribed rectangle of the wheel, Width and Height are the width and height of the circumscribed rectangle.

[0090] The position information of adjacent wheels is recorded, and the wheel position information of the image pixel at the top of the screen is recorded as P1, and the wheel position information of the image pixel at the bottom of the screen is recorded as P2.

[0091] S220: According to the positions of the adjacent wheels obtained by the detection, the ROI area to be detected of the track in the first image is circled as the second image.

[0092] According to the obtained position information of P1 and P2, the coordinates of the lower left corner of P1 and the upper right corner of P2 are calculated, and a rectangle parallel to the x-axis and y-axis of the image is obtained according to the coordinates of the lower left corner of P1 and the upper right corner of P2; this part of the rectangle records the roi area of ​​the track that is not blocked by the wheels and is exposed, and this part of the area is used as the second image.

[0093] S230: Detect all edge information in the second image using an image processing algorithm.

[0094] The interference caused by noise in the second image is eliminated by the median filtering technology; the influence of light and other noises is further eliminated by the morphological opening operation, and the over-filtering and image loss caused by the median filtering technology are compensated.

[0095] The edge detection algorithm is used on the second image after the above preprocessing to extract all edge information in the image, and the edge information including the coordinates of the edge points is recorded as a set l(x, y).

[0096] S240: Extract a unique track straight line formula through Hough straight line detection and calculate its slope.

[0097] The set l(x,y) is filtered by setting thresholds such as slope and length to select the edge point set (x j ,y j ), (x j ,y j )∈l(x,y). For the edge point set (x j ,y j )Use Hough transform to fit the straight line and get the unique straight line formula converted to the polar coordinate system:

[0098] ρ=x·cos(θ)+y·sin(θ)

[0099] Wherein, ρ is the vertical distance from the origin to the straight line; θ is the angle between the normal of the straight line and the positive direction of the x-axis; x, y are the x-axis and y-axis coordinates of the track edge position coordinate point in the plane rectangular coordinate system, respectively.

[0100] The slope of the line is calculated using the following formula:

[0101] m=-cot(θ)

[0102] Where m is the slope of the line.

[0103] S250: Calculate the change of the offset difference between the wheel and the track and record it as a curve.

[0104] The wheel circumscribed rectangle is adjusted according to the slope of the track line so that the wheel circumscribed rectangle is parallel to the track line.

[0105] Select a fixed position point of the image inside the adjusted wheel circumscribed rectangle, denoted as (x i ,y i ), then according to the point-to-straight-line distance formula, the distance between the wheel and the track is obtained:

[0106] d=|x i ·cos(θ)+y i ·sin(θ)-ρ|

[0107] Among them, x i ,y i are respectively the coordinates of a fixed position point in the circumscribed rectangle of the wheel.

[0108] The obtained distance is recorded as a curve according to the change of time and fed back to the relevant staff to facilitate safety monitoring and maintenance.

[0109] The third embodiment of the present application provides a sintering trolley wheel deviation detection device, which can be used to implement the sintering trolley wheel deviation detection method in the above embodiment, such as Figure 4 As shown, the sintering trolley wheel deviation detection device includes:

[0110] The image collection module is used to obtain the image of the wheel during driving as the first image through a camera lens arranged vertically downward just above the wheel; the image collection module can be used to implement step S10 in the first embodiment and its optional embodiments.

[0111] An image processing module is used to obtain the positions of adjacent wheels in the first image through a target detection algorithm; based on the detected positions of the front and rear wheels, the ROI area to be detected of the track in the first image is circled as the second image; the track position in the second image is detected through an image processing algorithm; the image processing module can be used to implement steps S20-S40 in the first embodiment and its optional embodiments.

[0112] The calculation output module calculates the change of the offset difference between the wheel and the track and records it as a curve. The calculation output module can be used to implement step S50 in the first embodiment and its optional embodiments.

[0113] Figure 5 900 is a schematic structural diagram of a computing device 900 provided in an embodiment of the present application. The computing device can execute each optional embodiment of the above method, and the computing device can be a terminal, or a chip or chip system inside the terminal. Figure 5 As shown, the computing device 900 includes: a processor 910 , a memory 920 , and a communication interface 930 .

[0114] It should be understood that Figure 5 The communication interface 930 in the computing device 900 shown may be used to communicate with other devices, and may specifically include one or more transceiver circuits or interface circuits.

[0115] The processor 910 may be connected to a memory 920. The memory 920 may be used to store the program code and data. Therefore, the memory 920 may be a storage unit inside the processor 910, or an external storage unit independent of the processor 910, or a component including a storage unit inside the processor 910 and an external storage unit independent of the processor 910.

[0116] Optionally, the computing device 900 may further include a bus. The memory 920 and the communication interface 930 may be connected to the processor 910 via the bus. The bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 5 A line without an arrow is used to represent the bus, but this does not mean that there is only one bus or one type of bus.

[0117] It should be understood that in the embodiment of the present application, the processor 910 may adopt a central processing unit (CPU). The processor may also be other general-purpose processors, digital signal processors (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. Alternatively, the processor 910 may adopt one or more integrated circuits to execute relevant programs to implement the technical solutions provided in the embodiment of the present application.

[0118] The memory 920 may include a read-only memory and a random access memory, and provides instructions and data to the processor 910. A portion of the processor 910 may also include a nonvolatile random access memory. For example, the processor 910 may also store information on the device type.

[0119] When the computing device 900 is running, the processor 910 executes the computer-executable instructions in the memory 920 to perform any operation step of the above method and any optional embodiment thereof.

[0120] It should be understood that the computing device 900 according to the embodiment of the present application can correspond to the corresponding subjects in the methods according to the embodiments of the present application, and the above-mentioned and other operations and / or functions of each module in the computing device 900 are respectively for implementing the corresponding processes of each method of the present embodiment. For the sake of brevity, they will not be repeated here.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0126] 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 storage medium and includes 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 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.

[0127] An embodiment of the present application also provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, it is used to execute the above method, which includes at least one of the solutions described in the above embodiments.

[0128] The computer storage medium of the embodiment of the present application can adopt any combination of one or more computer-readable media. Computer-readable media can be computer-readable signal media or computer-readable storage media. Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or devices, or any combination of the above. More specific examples (non-exhaustive lists) of computer-readable storage media include: electrical connections with one or more wires, portable computer disks, hard disks, random access memories (RAM), read-only memories (ROM), erasable programmable read-only memories (EPROM or flash memory), optical fibers, portable compact disk read-only memories (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination of the above. In this document, computer-readable storage media can be any tangible medium containing or storing programs, which can be used by instruction execution systems, devices or devices or used in combination with them.

[0129] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0130] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0131] Computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).

[0132] In addition, the words "first, second, third, etc." or module A, module B, module C and other similar terms in the specification and claims are only used to distinguish similar objects and do not represent a specific ordering of the objects. It can be understood that the specific order or sequence can be interchanged where permitted so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein.

[0133] In the above description, the numbers representing the steps, such as S110, S120, etc., do not necessarily mean that the steps will be executed in this manner. If permitted, the order of the steps can be interchanged or they can be executed simultaneously.

[0134] The term "comprising" as used in the description and claims should not be interpreted as being limited to what is listed thereafter; it does not exclude other elements or steps. Therefore, it should be interpreted as specifying the presence of the features, integers, steps or components mentioned, but does not exclude the presence or addition of one or more other features, integers, steps or components and groups thereof. Therefore, the expression "a device comprising means A and B" should not be limited to a device consisting of components A and B only.

[0135] References to "one embodiment" or "an embodiment" in this specification mean that a particular feature, structure, or characteristic described in conjunction with the embodiment is included in at least one embodiment of the present application. Therefore, the phrases "in one embodiment" or "in an embodiment" appearing in various places in this specification do not necessarily refer to the same embodiment, but may refer to the same embodiment. In addition, in one or more embodiments, the particular features, structures, or characteristics can be combined in any appropriate manner, as would be apparent to one of ordinary skill in the art from this disclosure.

[0136] Note that the above are only preferred embodiments of the present application and the technical principles used. Those skilled in the art will understand that the present application is not limited to the specific embodiments described herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present application. Therefore, although the present application is described in more detail through the above embodiments, the present application is not limited to the above embodiments, and may also include more other equivalent embodiments without departing from the concept of the present application, all of which belong to the scope of protection of the present application.

Claims

1. A method for detecting wheel deviation of a sintering trolley, characterized in that: The sintering trolley comprises a transport carriage and wheels located on both sides of the transport carriage; The method comprises: Acquiring an image of the wheel during driving as a first image through a camera lens arranged downward above the wheel; Acquire the position of the adjacent wheels located on one side of the transport carriage in the first image through the target detection model; According to the positions of the adjacent wheels obtained by the detection, the ROI region to be detected of the track in the first image is circled as the second image; detecting the track position in the second image by an image processing algorithm; The change of the offset difference between the wheel and the track is calculated and recorded as the detection result.

2. The method according to claim 1, characterized in that The target detection model uses the yolov5s pre-trained model; after the target detection model detects the first image, it returns the size and position information P of the minimum circumscribed rectangle of the wheel, where P is expressed by the following formula: P=(X lt ,Y lt ,Width,Height) Among them, X lt ,X lt is the coordinate of one corner of the minimum bounding rectangle; Width and Height are the width and height of the minimum bounding rectangle.

3. The method according to claim 2, characterized in that The camera lens acquires the first image including the adjacent wheels by setting a fixed frame number; the adjacent wheels include a first wheel and a second wheel; the size and position information of the minimum circumscribed rectangle of the first wheel and the second wheel obtained by the detection are recorded as P1 and P2 respectively; The ROI area to be detected of the track line is determined according to the coordinates of the two adjacent corners of the minimum circumscribed rectangle corresponding to P1 of the first wheel and the minimum circumscribed rectangle corresponding to P2 of the second wheel as the second image.

4. The method according to claim 1, characterized in that: The image processing algorithm includes: Preprocessing the second image using a median filtering method to eliminate interference caused by image noise; Using morphological opening operation to eliminate the influence of light and noise and compensate for the image loss caused by the median filter; Using edge detection, all edge information in the second image is extracted.

5. The method according to claim 4, characterized in that The edge information is screened to extract a set of coordinate points in the second detection area that include the edge position of the track; and a unique straight line of the track is obtained by using Hough line detection, and the straight line is expressed by the following formula: ρ=x·cos(θ)+y·sin(θ) Wherein, ρ is the vertical distance from the origin to the straight line; θ is the angle between the normal of the straight line and the positive direction of the x-axis; x, y are the x-axis and y-axis coordinates of the track edge position coordinate point respectively; The slope of the straight line is obtained according to the following formula: m=-cot(θ) Where m is the slope of the line.

6. The method according to claim 5, characterized in that The position of the circumscribed rectangle of the wheel is adjusted by the slope of the track straight line so that the circumscribed rectangle of the wheel is parallel to the track straight line.

7. The method according to claim 6, characterized in that The offset difference d between the wheel and the track is obtained according to the following formula: d=|x i ·cos(θ)+y i ·sin(θ)-ρ| Among them, x i ,y i are respectively the coordinates of a fixed position point in the circumscribed rectangle of the wheel.

8. A sintering trolley wheel deviation detection device, characterized in that: include: An image collection module, used for acquiring an image of the wheel during driving as a first image through a camera lens arranged downward above the wheel; The image processing module obtains the position of the adjacent wheels located on one side of the transport carriage in the first image through the target detection algorithm; then, according to the detected positions of the front and rear wheels, the ROI area to be detected of the track in the first image is circled as the second image; and the track position in the second image is detected through the image processing algorithm; The calculation output module calculates the change of the offset difference between the wheel and the track and records it as the detection result.

9. A computing device, characterized in that include: processor, and A memory having program instructions stored thereon, wherein when the program instructions are executed by the processor, the processor executes the sintering trolley wheel deviation detection method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: Program instructions are stored thereon, and when the program instructions are executed by a computer, the computer executes the sintering trolley wheel deviation detection method according to any one of claims 1 to 7.

Images