Method, device, electronic device and storage medium for identifying center steel bars

Abstract

The application relates to a center-positioned steel bar recognition method and device, an electronic device and a storage medium. The center-positioned steel bar recognition method comprises the following steps: extracting a steel bar end surface image in a to-be-detected image; constructing a search box containing a center point of the steel bar end surface image in the steel bar end surface image; detecting a circle contained in the search box and determining the center of each detected circle; determining the deviation of each determined center from the center point, and determining that a circle corresponding to a minimum value in each deviation is a target circle; and determining a steel bar corresponding to the target circle as a center-positioned steel bar. Through the application, the problem of low recognition accuracy of the center-positioned steel bar in the related art is solved, and the recognition accuracy of the center-positioned steel bar is improved.

Description

Technical Field

[0001] The present application relates to the field of image processing, and in particular to a method, device, electronic device and storage medium for identifying center-position steel bars. Background Art

[0002] As a key pillar of the national economy, the steel industry has long attracted significant attention. Steel production involves delivering bars to customers in bundles. Each bundle requires labels and signs displaying information such as the steel grade, furnace number, specification, and length. These signs act as the bars' "identity cards," reflecting their quality and contributing to increased added value. Consequently, these signs are highly valued by many steel companies. The process of attaching these signs is known as rebar marking, and currently, companies primarily rely on manual labor for positioning and welding the labels. However, with the accelerating pace of production, the high-intensity, repetitive work of markers can lead to fatigue and boredom, resulting in reduced efficiency and incorrect marking placement. Furthermore, the harsh environment, characterized by high dust and noise levels, can also pose a risk to workers. These challenges hinder further development for companies, and intelligent and automated transformation and upgrading offer effective solutions.

[0003] Usually, when steel bar labels are pasted, they are pasted on the steel bar at the outermost center position of the entire bundle of steel bars. This method is convenient to operate and easy to identify. Therefore, how to accurately locate the steel bar at the outer center position is the key to achieving automated marking.

[0004] With regard to the problem of low recognition accuracy of center steel bars in related technologies, no effective solution has been proposed so far. Summary of the Invention

[0005] In this embodiment, a method, device, electronic device and storage medium for identifying center-position steel bars are provided to solve the problem of low accuracy in identifying center-position steel bars in related technologies.

[0006] In a first aspect, a method for identifying a center steel bar is provided in this embodiment, comprising:

[0007] Extracting the steel bar end face image from the image to be detected;

[0008] In the steel bar end face image, constructing a search box including the center point of the steel bar end face image;

[0009] Detecting circles contained in the search box, and determining the center of each detected circle;

[0010] Determining the deviations between the centers of the circles and the center point, and determining the circle corresponding to the minimum value of the deviations as the target circle;

[0011] The steel bar corresponding to the target circle is determined as the center steel bar.

[0012] In some embodiments, extracting the steel bar end face image from the image to be detected includes:

[0013] The image to be detected is input into a trained steel bar end face image detection model to obtain the steel bar end face image; wherein the steel bar end face detection model is trained using the steel bar end face image based on a machine learning method.

[0014] In some embodiments, in the steel bar end face image, constructing a search box including a center point of the steel bar end face image includes:

[0015] Determining the center point of the steel bar end face image;

[0016] A search box including the center point of the steel bar end face image is constructed with the center point as a reference point; wherein the area included in the search box is smaller than the area included in the steel bar end face image.

[0017] In some embodiments, constructing a search box containing the center point of the steel bar end face image using the center point as a reference point includes:

[0018] Determining the center point of the steel bar end surface image and the perimeter of the steel bar end surface image;

[0019] The search box is constructed with the center point of the steel bar end face image as the center point of the search box and a preset multiple of the perimeter of the steel bar end face image as the perimeter of the search box; wherein the preset multiple is a value greater than 0 and less than 1.

[0020] In some embodiments, detecting circles contained in the search box and determining the center of each detected circle includes:

[0021] Clustering the steel bar end face images in the search box based on the ISODATA clustering algorithm;

[0022] Detecting circles contained in the search box after clustering, and determining the center of each detected circle.

[0023] In some embodiments, detecting circles contained in the search box and determining the center of each detected circle includes:

[0024] performing image binarization processing on the steel bar end face image within the search box after clustering, removing the background area of ​​the steel bar end face image within the search box after clustering, and obtaining a target steel bar end face image;

[0025] Detecting circles contained in the target steel bar end face image, and determining the center of each detected circle.

[0026] In some embodiments, determining the deviations between the centers of the circles and the center point, and determining a circle corresponding to a minimum value among the deviations as the target circle includes:

[0027] Calculating the Euclidean distance between each circle center and the center point respectively;

[0028] Determining the degree of deviation between each of the circle centers and the center point based on the Euclidean distance between each of the circle centers and the center point;

[0029] Based on the deviations between the centers of the circles and the center point, a circle corresponding to a minimum value of the deviations is determined as a target circle.

[0030] In a second aspect, a device for identifying a central steel bar is provided in this embodiment, which is characterized by comprising:

[0031] An extraction module, used for extracting the steel bar end face image from the image to be detected;

[0032] A construction module, configured to construct a search box containing a center point of the steel bar end surface image in the steel bar end surface image;

[0033] a detection module, configured to detect circles contained in the search box and determine the center of each detected circle;

[0034] A first determining module is configured to determine the deviations between the centers of the circles and the center point, and to determine a circle corresponding to a minimum value among the deviations as a target circle;

[0035] The second determining module is used to determine the steel bar corresponding to the target circle as the center steel bar.

[0036] In a third aspect, an electronic device is provided in this embodiment, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for identifying the center steel bars described in the first aspect above is implemented.

[0037] In a fourth aspect, a storage medium is provided in this embodiment, on which a computer program is stored. When the program is executed by a processor, the method for identifying the center steel bar described in the first aspect is implemented.

[0038] Compared with the related art, the method, device, electronic device and storage medium for identifying center-position steel bars provided in this embodiment extract the steel bar end face image in the image to be detected; construct a search box containing the center point of the steel bar end face image in the steel bar end face image; detect the circles contained in the search box, and determine the center of each detected circle; determine the deviation between each center of the circle and the center point, and determine the circle corresponding to the minimum value of each deviation as the target circle; determine the steel bar corresponding to the target circle as the center-position steel bar, which solves the problem of low recognition accuracy of center-position steel bars in the related art and improves the recognition accuracy of center-position steel bars.

[0039] The details of one or more embodiments of the present application are set forth in the following drawings and description to make other features, objects, and advantages of the present application more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS

[0040] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0041] Figure 1 4 is a hardware structure block diagram of a terminal of the method for identifying a center steel bar of this embodiment;

[0042] Figure 2 Flowchart of the method for identifying the center steel bar of this embodiment;

[0043] Figure 3 is a schematic diagram of the construction of the search box of this embodiment;

[0044] Figure 4 This is a flow chart of a method for identifying center steel bars of this embodiment;

[0045] Figure 5 4 is a structural block diagram of the device for identifying the center steel bar of this embodiment. DETAILED DESCRIPTION

[0046] In order to more clearly understand the purpose, technical solutions and advantages of the present application, the present application is described and illustrated below in conjunction with the accompanying drawings and embodiments.

[0047] Unless otherwise defined, technical terms or scientific terms used in the present application shall have the same meaning as those commonly understood by a person of ordinary skill in the art to which the present application belongs. The terms "one", "a", "an", "the", "these", and similar terms in the present application do not indicate quantity, and they can be singular or plural. The terms "include", "contain", "have", and any variants thereof in the present application are intended to cover non-exclusive inclusion; for example, a process, method, and system, product or device containing a series of steps or modules (units) are not limited to the listed steps or modules (units), but can include steps or modules (units) not listed, or can include other steps or modules (units) inherent to the process, method, product or device. The terms "connect", "connect", "couple" and the like in the present application are not limited to physical or mechanical connection, but can include electrical connection, whether direct or indirect. The term "multiple" in the present application refers to two or more. The term "and / or" describes the association between the associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that A exists alone, A and B exist together, and B exists alone. Generally, the character " / " represents an "or" relationship between the objects before and after. The terms "first", "second", "third" and the like in the present application are only used to distinguish similar objects, and do not represent a specific order of the objects.

[0048] The method embodiments provided in the present embodiment can be executed in a terminal, a computer or a similar computing device. For example, the method embodiments are executed on a terminal, Figure 1 is a hardware structure block diagram of the terminal of the identification method of the central position steel bar of the present embodiment. As shown in Figure 1 , the terminal can include one or more (only one is shown in Figure 1 ) processor 102 and memory 104 for storing data, wherein the processor 102 can include but not limited to processing device such as microprocessor MCU or programmable logic device FPGA. The above terminal can also include transmission device 106 for communication function and input / output device 108. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above terminal. For example, the terminal can also include more or less components than Figure 1 shown, or have a different configuration from Figure 1 shown.

[0049] Memory 104 can be used to store computer programs, such as application software programs and modules, such as the computer program corresponding to the method for identifying center-positioned rebars in this embodiment. Processor 102 executes the computer programs stored in memory 104 to execute various functional applications and data processing, thereby implementing the aforementioned method. Memory 104 can include high-speed random access memory (RAM) and non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, memory 104 may further include memory remotely located from processor 102, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0050] The transmission device 106 is used to receive or send data via a network. The network may include a wireless network provided by the terminal's telecommunications provider. In one embodiment, the transmission device 106 includes a network interface controller (NIC), which can be connected to other network devices via a base station to enable communication with the Internet. In another embodiment, the transmission device 106 may be a radio frequency (RF) module, which is used to communicate with the Internet wirelessly.

[0051] In this embodiment, a method for identifying central steel bars is provided. Figure 2 Flowchart of the method for identifying the center steel bar of this embodiment is shown in FIG. Figure 2 As shown, the process includes the following steps:

[0052] Step S201: extracting the end face image of the steel bar in the image to be detected.

[0053] In this step, the image to be detected can be acquired in real time by a camera device, or can be acquired from a database storing images to be detected; the image to be detected includes an image of the end face of a steel bar.

[0054] It should be noted that in the embodiments of the present application, any method that can recognize images can be used to extract the end face image of the steel bar in the image to be detected, such as using a deep learning image recognition model and a traditional image processing algorithm to extract the above-mentioned end face image of the steel bar.

[0055] For example, in some embodiments, extracting the steel bar end face image from the image to be detected may include: inputting the image to be detected into a trained steel bar end face image detection model to obtain the steel bar end face image; wherein the steel bar end face detection model is based on a machine learning method and is trained using the steel bar end face image.

[0056] In this embodiment, the trained steel bar end face image detection model is used to preliminarily screen out steel bar end face images from the images to be detected, thereby realizing the extraction of steel bar end face images and improving the accuracy of steel bar end face image extraction to a certain extent.

[0057] It should be noted that the trained steel bar end face image detection model is a target detection model trained based on steel bar end face images and has a certain preset recognition degree. Its detection target is the steel bar end face image. For the overall steel bar end face with more obvious features, the deep learning model often shows stronger advantages than the traditional image processing algorithm.

[0058] In some of the embodiments, the image to be detected is input into the trained steel bar end face image detection model to obtain the steel bar end face image, and the image to be detected can also be preprocessed, where the preprocessing includes: image flipping processing, contrast adjustment processing, brightness adjustment processing, and image size processing.

[0059] In this embodiment, by preprocessing the image to be detected, namely image flipping, contrast adjustment, brightness adjustment, and image size processing, it helps to quickly train and predict the preset steel bar end face image detection module.

[0060] It should be noted that image size processing may refer to processing the image into a size that is the same as the training image size preset by the trained steel bar end face image detection model.

[0061] Step S202: constructing a search box containing the center point of the steel bar end face image in the steel bar end face image.

[0062] In this step, by re-establishing a search box containing the center point of the steel bar end face image on the steel bar end face image, hierarchical processing of the image to be detected is achieved, and the search area of ​​the center steel bar is gradually narrowed, which reduces the difficulty of locating the center steel bar to a certain extent, and improves the accuracy and robustness of locating the center steel bar.

[0063] Step S203: Detect the circles contained in the search box and determine the center of each detected circle.

[0064] In this step, the circle in the steel bar end face image can be a circular shape representing the steel bar end face, and there may be one or more circular shapes of steel bar end faces in a steel bar end face image within a search box. In this embodiment, the steel bars within the search box are detected by detecting the circles contained in the search box and determining the centers of each detected circle, so that the center steel bar can be determined subsequently based on the circle corresponding to each steel bar in the steel bar end face image.

[0065] Step S204 : determining the deviations between the centers of the circles and the center point, and determining the circle corresponding to the minimum value of the deviations as the target circle.

[0066] Step S205: Determine the steel bar corresponding to the target circle as the center steel bar.

[0067] Based on the above steps S201 to S205, by constructing a search box containing the center point of the steel bar end face image in the steel bar end face image, hierarchical processing of the image to be detected is achieved, and the search area of ​​the center steel bar is gradually narrowed, which reduces the difficulty of locating the center steel bar to a certain extent. Then, by detecting the circles contained in the search box, determining the centers of the detected circles, determining the deviations of the centers of the circles from the center point, and determining the circle corresponding to the minimum value of each deviation as the target circle, and determining the steel bar corresponding to the target circle as the center steel bar, the marking of the center steel bar is achieved, avoiding the problem of low recognition accuracy of the center steel bar caused by the use of deep learning algorithms to achieve automatic marking in related technologies, and improving the recognition accuracy of the center steel bar.

[0068] In some embodiments, constructing a search box on the steel bar end face image includes: determining the center point of the steel bar end face image and the perimeter of the steel bar end face image; constructing the search box with the center point of the steel bar end face image as the center point of the search box and a preset multiple of the perimeter of the steel bar end face image as the perimeter of the search box; wherein the preset multiple is a value greater than 0 and less than 1.

[0069] In this embodiment, by taking the center point of the steel bar end face image as the center point of the search box and the preset multiple of the circumference of the steel bar end face image as the circumference of the search box, a search box is constructed, so that the search box can be adaptively transformed according to the actual size of the steel bar end face image to achieve the effect of gradually reducing the search area of ​​the center steel bar, reducing the difficulty of locating the center steel bar to a certain extent, and improving the accuracy and robustness of locating the center steel bar.

[0070] Ideally, the search box is the location of the target steel bar. However, due to the irregular distribution of steel bars, the search box location may have deviations and other problems, so the center coordinates need to be processed for fault tolerance. Figure 3 As shown, the center point (x, y) of the steel bar end face image is used as the center point of the search box, and 1 / 10 of the perimeter L of the steel bar end face image (i.e., the preset multiple in the above embodiment) is used as the perimeter L / 10 of the search box to construct a search box for the center steel bar. Subsequent detection of the center steel bar is only performed in this search box. In this way, the two-level reduction and positioning of the image to be detected are achieved, which on the one hand increases the fault tolerance of the center point coordinates, and on the other hand reduces the difficulty of detecting the entire image.

[0071] In some embodiments, detecting the circles contained in the search box and determining the centers of the detected circles comprises: clustering the steel bar end surface images in the search box based on an ISODATA clustering algorithm; detecting the circles contained in the search box after clustering and determining the centers of the detected circles.

[0072] In the present embodiment, in the scenario of center bit steel bar detection, the ISODATA clustering algorithm using the merging and splitting mechanism has the following main advantages compared with the common division-based clustering algorithm (such as the K-means clustering algorithm): the number of classes in the clustering of the ISODATA clustering algorithm is automatically determined through algorithm iteration, and in the clustering process, when the number of samples in a certain class in the clustering result is too small or the distance between two classes is too close, the two classes are merged into one class, and vice versa, when the class variance of a certain class in the clustering result is too large, the class is split into two classes, and through iteration, the number of classes and the corresponding centers are constantly adjusted, and the final clustering effect is often better than that of the K-means algorithm. By clustering the steel bar end surface images in the search box based on the ISODATA clustering algorithm, the detection of the steel bar clustering center point is realized, the clustering effect of the steel bar end surface images in the search box is improved, and the software has strong expandability and is convenient for iterative upgrading of the algorithm.

[0073] It should be noted that the ISODATA clustering algorithm is a clustering algorithm based on the k-means algorithm, with two operations of "merging" and "splitting" of the clustering result and setting algorithm running control parameters; in the present embodiment, the final result of the ISODATA clustering algorithm can also be changed through the number of iterations, so that the result of the ISODATA clustering algorithm is more accurate.

[0074] In some embodiments, detecting the circles contained in the search box and determining the centers of the detected circles comprises: performing image binarization processing on the steel bar end surface images in the search box after clustering, removing the background area of the steel bar end surface images in the search box after clustering, and obtaining a target steel bar end surface image; detecting the circles contained in the target steel bar end surface image and determining the centers of the detected circles.

[0075] In the present embodiment, the inter-class pixel values in the steel bar end surface images in the search box after clustering can be averaged to represent the class data, and then the image binarization processing is performed for threshold segmentation in units of classes to distinguish the steel bar and the background area, and the background area is removed, so that the target steel bar end surface image is extracted, facilitating the subsequent detection of the circles in the steel bar end surface image.

[0076] It should be noted that the image binarization processing can be a big law binarization processing manner in the related art, or other ways capable of realizing background removal.

[0077] In some embodiments, detecting the circles in the target steel bar end face image and the center of each circle corresponding to the circle includes: detecting the circles in the target steel bar end face image based on Hough transform, and outputting the center of each circle.

[0078] In the embodiment, based on the target steel bar end face image after the image binarization processing and the background area is removed, the Hough transform is used to detect all the circles in the target steel bar end face image, and the center and radius corresponding to the circle are outputted, so that the target steel bar end face image is realized, which is convenient for subsequent positioning of the center point steel bar based on the center of each circle.

[0079] In some embodiments, determining the deviation of each center from the center point, and determining the circle corresponding to the minimum value in each deviation as the target circle includes: calculating the Euclidean distance of each center from the center point respectively; determining the deviation of each center from the center point based on the Euclidean distance of each center from the center point; determining the circle corresponding to the minimum value in each deviation as the target circle based on the deviation of each center from the center point.

[0080] In the embodiment, the deviation of each center from the center point is determined according to the size of the Euclidean distance of each center from the center point, that is, if the Euclidean distance is large, it can be determined that the distance between the center and the center point is large, and through the above-mentioned manner, the deviation between the center and the center point is calculated, so as to determine the circle corresponding to the minimum value in each deviation as the target circle.

[0081] It should be noted that the Euclidean metric (euclidean metric) is also called Euclidean distance, which is a commonly used distance definition, which refers to the real distance between two points in m-dimensional space, or the natural length of the vector (i.e. the distance from the origin). The Euclidean distance in two-dimensional and three-dimensional space is the actual distance between two points.

[0082] The preferred embodiment will be described and explained below.

[0083] Figure 4 The flowchart of the center point steel bar recognition method of the embodiment is shown in Figure 4 The center point steel bar recognition method includes the following steps:

[0084] Step S401, acquiring a to-be-detected image.

[0085] Step S402, performing image preprocessing on the to-be-detected image.

[0086] Step S403: extracting the steel bar end face image in the image to be detected by using the trained steel bar end face image detection model.

[0087] It should be noted that the trained steel bar end face image detection model can be obtained through deep learning model training.

[0088] Step S404: determine the center point of the steel bar end face image.

[0089] Step S405: constructing a search box containing the center point of the steel bar end face image in the steel bar end face image.

[0090] Step S406: clustering the steel bar end face images in the search box based on the ISODATA clustering algorithm.

[0091] Step S407 , performing image binarization processing on the clustered steel bar end face images in the search box in cluster units to obtain target steel bar end face images.

[0092] Step S408 : detecting circles and the center of each circle in the target steel bar end face image based on Hough transform.

[0093] Step S409: Determine the steel bar corresponding to the circle with the smallest deviation from the center point based on the Euclidean distance algorithm.

[0094] In this step, the deviation between the circle and the midline may be determined based on the Euclidean distance between the center point and the circle center point.

[0095] In step S410, the steel bar corresponding to the circle with the smallest deviation from the center point is determined as the center steel bar.

[0096] In this embodiment, through the above-mentioned method, it is achieved that the center steel bar can be identified and located using lightweight calculations, so that the camera equipment can perform local calculations after collecting the image data to be detected, and return the calculation results to the operation control center, which greatly reduces the transmission bandwidth and can ensure the real-time processing of image data. At the same time, it combines deep learning with traditional image processing to achieve hierarchical processing of the image to be detected and gradually narrows the search area of ​​the center steel bar, which to a certain extent reduces the difficulty of locating the center steel bar and improves the accuracy and robustness of the center steel bar positioning; further, by constructing a search box, the interference of external factors is avoided, and the identification and positioning of the center steel bar in any environment can be accurately adapted.

[0097] This embodiment also provides a device for identifying center-positioned steel bars, which is used to implement the above-mentioned embodiments and preferred implementations. Details already described will not be repeated here. The terms "module," "unit," "subunit," etc., used below, may refer to a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented using software, implementation using hardware, or a combination of software and hardware, is also possible and contemplated.

[0098] Figure 5 : is a structural block diagram of the central steel bar identification device of this embodiment, as shown in FIG. Figure 5 As shown, the device includes:

[0099] Extraction module 51, used for extracting the steel bar end face image in the image to be detected;

[0100] A construction module 52, coupled to the extraction module 51, is used to construct a search box containing a center point of the steel bar end surface image in the steel bar end surface image;

[0101] a detection module 53, coupled to the construction module 52, for detecting circles contained in the search box and determining the center of each detected circle;

[0102] A first determination module 54, coupled to the detection module 53, is configured to determine the deviations between the centers of the circles and the center point, and to determine the circle corresponding to the minimum value of the deviations as the target circle;

[0103] The second determining module 55 is coupled to the first determining module 54 and is configured to determine the steel bar corresponding to the target circle as the center steel bar.

[0104] In some embodiments, the extraction module 51 includes: an input unit for inputting the image to be detected into a trained steel bar end face image detection model to obtain a steel bar end face image, wherein the steel bar end face detection model is based on a machine learning method and is trained using steel bar end face images.

[0105] In some embodiments, the construction module 52 includes: a first determination unit for determining the center point of the steel bar end face image; a construction unit for constructing a search box containing the center point of the steel bar end face image with the center point as a reference point; wherein the area contained in the search box is smaller than the area contained in the steel bar end face image.

[0106] In some embodiments, the construction unit includes: a determination subunit for determining the circumference of the steel bar end face image; a construction subunit for constructing a search box with the center point of the steel bar end face image as the center point of the search box and a preset multiple of the circumference of the steel bar end face image as the circumference of the search box; wherein the preset multiple is a value greater than 0 and less than 1.

[0107] In some embodiments, the detection module 53 includes: a clustering unit for clustering the steel bar end face images in the search box based on the ISODATA clustering algorithm; a detection unit for detecting the circles contained in the search box after clustering, and determining the center of each detected circle.

[0108] In some embodiments, the detection unit includes: a binarization processing subunit, used to perform image binarization processing on the steel bar end face image in the search box after clustering, remove the background area of ​​the steel bar end face image in the search box after clustering, and obtain the target steel bar end face image; a detection subunit, used to detect the circles contained in the target steel bar end face image, and determine the center of each detected circle.

[0109] In some embodiments, the first determination module 54 includes: a calculation unit for respectively calculating the Euclidean distance between each circle center and the center point; a second determination unit for determining the deviation between each circle center and the center point based on the Euclidean distance between each circle center and the center point; and a third determination unit for determining, based on the deviation between each circle center and the center point, that the circle corresponding to the minimum value of each deviation is the target circle.

[0110] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can be located in the same processor; or the above modules can be located in different processors in any combination.

[0111] This embodiment further provides an electronic device, including a memory and a processor, wherein the memory stores a computer program, and the processor is configured to run the computer program to execute the steps in any one of the above method embodiments.

[0112] Optionally, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor, and the input / output device is connected to the processor.

[0113] Optionally, in this embodiment, the processor may be configured to execute the following steps through a computer program:

[0114] Step S201: extracting the end face image of the steel bar in the image to be detected.

[0115] Step S202: constructing a search box containing the center point of the steel bar end face image in the steel bar end face image.

[0116] Step S203: Detect the circles contained in the search box and determine the center of each detected circle.

[0117] Step S204 : determining the deviations between the centers of the circles and the center point, and determining the circle corresponding to the minimum value of the deviations as the target circle.

[0118] Step S205: Determine the steel bar corresponding to the target circle as the center steel bar.

[0119] It should be noted that, for specific examples in this embodiment, reference may be made to the examples described in the above embodiments and optional implementation modes, and will not be repeated in this embodiment.

[0120] In addition, in conjunction with the center steel bar identification method provided in the above embodiments, a storage medium may be provided in this embodiment to implement the method. The storage medium stores a computer program; when the computer program is executed by a processor, the center steel bar identification method of any of the above embodiments is implemented.

[0121] It should be understood that the specific embodiments described herein are only used to explain this application and are not used to limit it. Based on the embodiments provided in this application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0122] Obviously, the accompanying drawings are merely examples or embodiments of the present application. A person skilled in the art can also apply the present application to other similar situations based on these drawings without inventive effort. Furthermore, it is understandable that, although the work involved in this development process may be complex and lengthy, certain design, manufacturing, or production changes based on the technical content disclosed in this application are merely routine technical means for a person skilled in the art and should not be considered to constitute a deficiency in the disclosure of the present application.

[0123] The term "embodiment" as used in this application refers to specific features, structures, or characteristics described in conjunction with the embodiment that can be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily mean that the embodiment is the same, nor does it mean that it is mutually exclusive with other embodiments and is independent or optional. It is understood, either explicitly or implicitly, by those skilled in the art that the embodiments described in this application can be combined with other embodiments when there is no conflict.

[0124] The above-described embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of patent protection. It should be noted that a person of ordinary skill in the art may make various modifications and improvements without departing from the spirit of the present application, and these modifications and improvements fall within the scope of protection of the present application. Therefore, the scope of protection of the present application shall be determined by the appended claims.

Claims

1. A method for identifying center steel bars, characterized in that: include: Extracting the steel bar end face image from the image to be detected; In the steel bar end face image, constructing a search box including the center point of the steel bar end face image; Detecting circles contained in the search box, and determining the center of each detected circle; Determining the deviations between the centers of the circles and the center point, and determining the circle corresponding to the minimum value of the deviations as the target circle; Determine the steel bar corresponding to the target circle as the center steel bar; Determining the deviations between the centers of the circles and the center point, and determining a circle corresponding to a minimum value of the deviations as a target circle includes: Calculating the Euclidean distance between each circle center and the center point respectively; Determining the degree of deviation between each of the circle centers and the center point based on the Euclidean distance between each of the circle centers and the center point; Based on the deviations between the centers of the circles and the center point, a circle corresponding to a minimum value of the deviations is determined as a target circle.

2. The method for identifying center steel bars according to claim 1, wherein: Extracting the steel bar end face image from the image to be detected includes: The image to be detected is input into a trained steel bar end face image detection model to obtain the steel bar end face image; wherein the steel bar end face detection model is trained using the steel bar end face image based on a machine learning method.

3. The method for identifying center steel bars according to claim 1, wherein: In the steel bar end face image, constructing a search box including the center point of the steel bar end face image includes: Determining the center point of the steel bar end face image; A search box including the center point of the steel bar end face image is constructed with the center point as a reference point; wherein the area included in the search box is smaller than the area included in the steel bar end face image.

4. The method according to claim 3, characterized in that The step of constructing a search box containing the center point of the steel bar end face image using the center point as a reference point includes: Determining the perimeter of the steel bar end face image; The search box is constructed with the center point of the steel bar end face image as the center point of the search box and a preset multiple of the perimeter of the steel bar end face image as the perimeter of the search box; wherein the preset multiple is a value greater than 0 and less than 1.

5. The method for identifying center steel bars according to claim 1, wherein: Detecting circles contained in the search box and determining the center of each detected circle includes: Clustering the steel bar end face images in the search box based on the ISODATA clustering algorithm; Detecting circles contained in the search box after clustering, and determining the center of each detected circle.

6. The method for identifying center steel bars according to claim 5, characterized in that: Detecting circles contained in the search box and determining the center of each detected circle includes: performing image binarization processing on the steel bar end face image within the search box after clustering, removing the background area of ​​the steel bar end face image within the search box after clustering, and obtaining a target steel bar end face image; Detecting circles contained in the target steel bar end face image, and determining the center of each detected circle.

7. A device for identifying center steel bars, characterized in that: include: An extraction module, used for extracting the steel bar end face image from the image to be detected; A construction module, configured to construct a search box containing a center point of the steel bar end surface image in the steel bar end surface image; a detection module, configured to detect circles contained in the search box and determine the center of each detected circle; A first determining module is configured to determine the deviations between the centers of the circles and the center point, and to determine a circle corresponding to a minimum value among the deviations as a target circle; A second determining module is used to determine the steel bar corresponding to the target circle as the center steel bar; The first determining module includes: A calculation unit, used to calculate the Euclidean distance between each circle center and the center point; a second determining unit, configured to determine a degree of deviation between each of the circle centers and the center point based on a Euclidean distance between each of the circle centers and the center point; The third determining unit is configured to determine, based on the deviations between the centers of the circles and the center point, a circle corresponding to a minimum value of the deviations as a target circle.

8. An electronic device comprising a memory and a processor, characterized in that: A computer program is stored in the memory, and the processor is configured to run the computer program to execute the method for identifying a center steel bar according to any one of claims 1 to 6.

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

Images