Method and system for locating connection points of wire clamps based on artificial intelligence

Abstract

The present invention relates to the field of image processing, and discloses a method and system for realizing connection point positioning of a wire clamp based on artificial intelligence, wherein the method comprises: analyzing the connection point validity in a wire clamp connection point image, extracting a target wire clamp connection point image in the wire clamp connection point image; normalizing the target wire clamp connection point image to obtain a normalized connection point image, identifying the image features of the normalized connection point image, filtering the normalized connection point image to obtain a filtered connection point image; performing frequency wavelet transform on the filtered connection point image to obtain image frequency components, calculating the image local energy of the image frequency components, and extracting connection point texture features of the filtered connection point image; acquiring an image to be identified, extracting image texture features of the image to be identified, calculating the feature matching degree of connection point texture features and image texture features, and determining the wire clamp connection point of the image to be identified. The present invention can improve the positioning effect of the wire clamp connection point.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to a method and system for locating the connection point of a wire clamp based on artificial intelligence. Background Art

[0002] Wire clamp connection point positioning refers to a technology that accurately locates the wire clamp connection points of power transmission lines in power systems. Wire clamp connection point positioning can obtain the location information of wire clamp connection points in real time and accurately, which helps to improve the safe operation level of power systems, reduce fault risks and improve maintenance efficiency.

[0003] At present, the positioning of the wire clamp connection point is mainly carried out through wireless communication, which uses the wireless communication equipment on the wire clamp connection point to transmit signals for identification. When the wireless communication equipment at the connection point is damaged, this method cannot effectively transmit signals, resulting in poor positioning of the wire clamp connection point. Summary of the invention

[0004] The present invention provides a method and system for locating the connection point of a wire clamp based on artificial intelligence, the main purpose of which is to improve the positioning effect of the connection point of the wire clamp.

[0005] To achieve the above object, the present invention provides a method for locating the connection point of a wire clamp based on artificial intelligence, comprising:

[0006] Acquire a wire clamp connection point image, analyze the connection point validity in the wire clamp connection point image, and extract a target wire clamp connection point image in the wire clamp connection point image based on the connection point validity;

[0007] Normalizing the target wire clamp connection point image to obtain a normalized connection point image, identifying image features of the normalized connection point image, and determining a filtering algorithm for the normalized connection point image based on the image features;

[0008] Using the filtering algorithm to filter the normalized tie point image to obtain a filtered tie point image;

[0009] Constructing a wavelet basis function of the filtered tie point image, performing a frequency wavelet transform on the filtered tie point image through the wavelet basis function to obtain an image frequency component, calculating an image local energy of the image frequency component, and extracting a tie point texture feature of the filtered tie point image through the image local energy;

[0010] An image to be identified is acquired, image texture features of the image to be identified are extracted, a feature matching degree between the connection point texture features and the image texture features is calculated, and a wire clamp connection point of the image to be identified is determined through the feature matching degree.

[0011] Optionally, analyzing the validity of connection points in the wire clamp connection point image includes:

[0012] marking a connection point area of ​​the clamp connection point image;

[0013] Analyzing a tie point identifiability coefficient of the tie point region;

[0014] The validity of connection points in the wire clamp connection point image is analyzed based on the connection point identifiable coefficients.

[0015] Optionally, the step of normalizing the target wire clamp connection point image to obtain a normalized connection point image includes:

[0016] Dividing the target wire clamp connection point image into regional wire clamp connection point images;

[0017] Calculate the regional average value and the regional standard deviation of the regional clip connection point image respectively;

[0018] Determine a normalization function of pixels in a region corresponding to the region clip connection point image based on the region average value and the region standard deviation;

[0019] The regional line clip connection point image is normalized by using the normalization function to obtain the normalized connection point image.

[0020] Optionally, the filtering the normalized tie point image using the filtering algorithm to obtain a filtered tie point image includes:

[0021] determining filter coefficients of the normalized tie point image;

[0022] Based on the filtering coefficient, adjusting the filtering parameters of the filtering algorithm to obtain a target filtering function;

[0023] Based on the target filtering function, calculating pixel filtering values ​​of the normalized tie point image;

[0024] A filtered tie point image of the normalized tie point image is generated based on the pixel filter values.

[0025] Optionally, the calculating the pixel filtering value of the normalized tie point image based on the target filtering function comprises:

[0026] Based on the target filter function, the pixel filter value of the normalized tie point image is calculated using the following formula:

[0027] G(a,c)=conv2(Y,W)

[0028] Among them, G(a,c) represents the pixel filter value of the normalized tie point image, Y represents the normalized tie point image, W represents the target filter function of the normalized tie point image, conv2 represents the two-dimensional convolution operation, and (a,c) represents the pixel coordinates corresponding to the normalized tie point image.

[0029] Optionally, performing frequency wavelet transform on the filtered connection point image by using the wavelet basis function to obtain image frequency components includes:

[0030] determining a decomposition level of the filtered tie point image;

[0031] Through the decomposition level, the filter tie point image is subjected to discrete wavelet transformation using the wavelet basis function to obtain a discrete wavelet transformation image;

[0032] Extracting wavelet coefficients of the discrete wavelet transform image;

[0033] Based on the wavelet coefficients, image frequency components of the discrete wavelet transformed image are identified.

[0034] Optionally, calculating the image local energy of the image frequency components includes:

[0035] dividing the frequency components of the image into frequency size levels;

[0036] Determining a high frequency scale of the image frequency component based on the frequency size level;

[0037] extracting high-frequency components from the image frequency components based on the high-frequency frequency scale;

[0038] The local image energy of the high frequency component is calculated.

[0039] Optionally, calculating the local image energy of the high-frequency component includes:

[0040] Determining the scale wavelet coefficients of the high frequency scale corresponding to the high frequency component;

[0041] Based on the scaled wavelet coefficients, the image local energy of the high-frequency component is calculated using the following formula:

[0042] P(x,y)=∑|DWT(ω)(x,y,S)|2

[0043] Among them, P(x,y) represents the local energy of the image corresponding to the coordinate (x,y) of the high-frequency component, S represents the high-frequency scale corresponding to the high-frequency component, DWT(ω)(x,y,S) represents the wavelet coefficient of the high-frequency component at the coordinate (x,y) and the high-frequency scale S, DWT(ω) represents the wavelet coefficient matrix of the high-frequency component, and ω represents the high-frequency component.

[0044] Optionally, extracting the connection point texture features of the filtered connection point image by using the local energy of the image includes:

[0045] Identifying an energy maximum of local energy of the image;

[0046] Based on the energy maximum, marking the maximum value adjacent area of ​​the filtered tie point image;

[0047] Calculate the energy gradient direction of the area adjacent to the maximum value;

[0048] Based on the capability gradient direction, the connection point texture features of the filtered connection point image are extracted. In order to solve the above problem, the present invention also provides a connection point positioning system for a wire clamp based on artificial intelligence, the system comprising:

[0049] An image validity analysis model is used to obtain a wire clamp connection point image, analyze the connection point validity in the wire clamp connection point image, and extract a target wire clamp connection point image from the wire clamp connection point image based on the connection point validity;

[0050] An image normalization module, used to normalize the target wire clamp connection point image to obtain a normalized connection point image, identify image features of the normalized connection point image, and determine a filtering algorithm for the normalized connection point image based on the image features;

[0051] An image filtering processing module, used for filtering the normalized tie point image using the filtering algorithm to obtain a filtered tie point image;

[0052] A texture feature extraction module is used to construct a wavelet basis function of the filtered tie point image, perform frequency wavelet transform on the filtered tie point image through the wavelet basis function to obtain image frequency components, calculate image local energy of the image frequency components, and extract tie point texture features of the filtered tie point image through the image local energy;

[0053] The wire clamp connection point recognition module is used to obtain the image to be recognized, extract the image texture features of the image to be recognized, calculate the feature matching degree between the connection point texture features and the image texture features, and determine the wire clamp connection points of the image to be recognized through the feature matching degree.

[0054] The embodiment of the present invention can ensure good image quality by analyzing the validity of the connection points in the wire clamp connection point image, clearly display the appearance features of the wire clamp connection points, and thus ensure the data reliability of the subsequent image processing; the embodiment of the present invention can retain the image edge information by filtering the normalized connection point image using the filtering algorithm to obtain the filtered connection point image, thereby improving the effect of subsequent feature extraction; further, the embodiment of the present invention performs frequency wavelet transform on the filtered connection point image through the wavelet basis function to obtain the image frequency component, which can perform multi-scale analysis on the image and decompose the image into frequency domain information at different scales. This helps to better capture the local features and frequency information in the image, and is also beneficial for subsequent processing and analysis; further, the embodiment of the present invention can better analyze the frequency components in the image and understand the energy distribution at different frequencies by calculating the image local energy of the image frequency component. This helps to further analyze the image's texture, edges, noise and other features. Furthermore, the embodiment of the present invention can extract the detailed features of the wire clamp connection points by extracting the connection point texture features of the filtered connection point image through the local energy of the image, providing a data basis for the subsequent recognition of the wire clamp connection points of the image. Finally, the embodiment of the present invention can more accurately identify the target objects and scenes in the image by calculating the feature matching degree of the connection point texture features and the image texture features, thereby improving the recognition accuracy. Therefore, the method and system for locating the connection points of wire clamps based on artificial intelligence proposed in the present invention can improve the positioning effect of the wire clamp connection points. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 A schematic diagram of a flow chart of a method for locating a connection point of a wire clamp based on artificial intelligence provided by an embodiment of the present invention;

[0056] Figure 2 A functional module diagram of a connection point positioning system for a wire clamp based on artificial intelligence provided by an embodiment of the present invention;

[0057] Figure 3 A schematic diagram of the structure of an electronic device for realizing a connection point positioning system of a wire clamp based on artificial intelligence provided by an embodiment of the present invention

[0058] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0059] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0060] The embodiment of the present application provides a method for locating the connection point of a wire clamp based on artificial intelligence. The execution subject of the method for locating the connection point of a wire clamp based on artificial intelligence includes but is not limited to at least one of the electronic devices such as a server and a terminal that can be configured to execute the method provided by the embodiment of the present application. In other words, the method for locating the connection point of a wire clamp based on artificial intelligence can be executed by software or hardware installed on a terminal device or a server device, and the software can be a blockchain platform. The server includes but is not limited to: a single server, a server cluster, a cloud server or a cloud server cluster, etc. The server can be an independent server, or it can be a cloud server that provides cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, content delivery networks (Content Delivery Network, CDN), and basic cloud computing services such as big data and artificial intelligence platforms.

[0061] Reference Figure 1 FIG. 1 is a flow chart of a method for locating a connection point of a wire clamp based on artificial intelligence according to an embodiment of the present invention. In this embodiment, the method for locating a connection point of a wire clamp based on artificial intelligence includes:

[0062] S1. Acquire a wire clamp connection point image, analyze the connection point validity in the wire clamp connection point image, and extract a target wire clamp connection point image in the wire clamp connection point image based on the connection point validity.

[0063] In the embodiment of the present invention, the wire clamp connection point images refer to collected images of the wire clamp connection points, and these images may be derived from on-site detection or simulation experiments.

[0064] The embodiment of the present invention can ensure good image quality by analyzing the validity of the connection points in the wire clamp connection point image, clearly display the appearance features of the wire clamp connection points, and thus ensure the data reliability of subsequent image processing.

[0065] As an embodiment of the present invention, the analysis of the validity of connection points in the wire clamp connection point image includes: marking the connection point area of ​​the wire clamp connection point image; analyzing the connection point identifiable coefficients of the connection point area; and analyzing the validity of connection points in the wire clamp connection point image based on the connection point identifiable coefficients.

[0066] Among them, the connection point area refers to the image area containing the wire clamp connection points in the wire clamp connection point image, and the connection point identifiable coefficient refers to the degree to which the connection points in the connection point area can be completely identified, such as the degree of completeness, clarity, etc.

[0067] The embodiment of the present invention can screen out valid images by extracting target wire clamp connection point images from the wire clamp connection point images through the connection point validity, thereby improving the image processing efficiency and increasing the reliability of image information. The target wire clamp connection point image refers to an image in which the wire clamp connection points in the image have processing significance.

[0068] S2. Normalize the target wire clamp connection point image to obtain a normalized connection point image, identify image features of the normalized connection point image, and determine a filtering algorithm for the normalized connection point image based on the image features.

[0069] The embodiment of the present invention performs normalization processing on the target wire clamp connection point image to obtain a normalized connection point image, which is a process of converting an image into a unified standard form so as to compare and process different images. The purpose of normalization processing is to eliminate the problem of inconsistent image grayscale, thereby improving the accuracy and stability of the image processing algorithm. The normalized connection point image refers to the normalized image obtained by unifying the grayscale of the target wire clamp connection point image.

[0070] As an embodiment of the present invention, the target wire clamp connection point image is normalized to obtain a normalized connection point image, including: dividing the target wire clamp connection point image into regional wire clamp connection point images; respectively calculating the regional mean value and the regional standard deviation of the regional wire clamp connection point images; determining a normalization function of regional pixels corresponding to the regional wire clamp connection point image based on the regional mean value and the regional standard deviation; and normalizing the regional wire clamp connection point image by means of the normalization function to obtain the normalized connection point image.

[0071] Among them, the regional line clamp connection point image refers to the image after dividing the target line clamp connection point image into several small areas, the regional average value and the regional standard deviation refer to the average value and standard deviation of the pixel values ​​of each area of ​​the regional line clamp connection point image, and the normalization function refers to a function for normalizing the regional pixels. The normalization step of the normalization function is to subtract the regional average value from the pixel value corresponding to the regional pixel, and then divide it by the regional standard deviation.

[0072] Furthermore, the embodiment of the present invention can understand the noise level, pixel distribution and edge information in the image by identifying the image features of the normalized tie point image, wherein the image features refer to characteristic attributes of the normalized tie point image, such as image richness, image clarity and other attributes.

[0073] As an embodiment of the present invention, the identifying of image features of the normalized connection point image may be achieved by image scanning technology.

[0074] Furthermore, the embodiment of the present invention determines that the filtering algorithm of the normalized tie point image can obtain the best denoising effect through a suitable algorithm based on the image features, thereby improving the reliability of the later image information. The filtering algorithm refers to a function for filtering and denoising an image, such as mean filtering, median filtering, Gaussian filtering, bilateral filtering and other functions.

[0075] As an embodiment of the present invention, the filtering algorithm for determining the normalized tie point image based on the image features may be selected by mapping the image features and the filtering effect of the filtering algorithm.

[0076] S3. Filter the normalized tie point image using the filtering algorithm to obtain a filtered tie point image.

[0077] In the embodiment of the present invention, the normalized tie point image is filtered by using the filtering algorithm to obtain a filtered tie point image, which can retain image edge information, thereby improving the effect of later feature extraction. The filtered tie point image refers to an image obtained after filtering the normalized tie point image.

[0078] As an embodiment of the present invention, the filtering process of the normalized connection point image using the filtering algorithm to obtain a filtered connection point image includes: determining a filtering coefficient of the normalized connection point image; adjusting filtering parameters of the filtering algorithm based on the filtering coefficient to obtain a target filtering function; calculating pixel filtering values ​​of the normalized connection point image based on the target filtering function; and generating a filtered connection point image of the normalized connection point image based on the pixel filtering values.

[0079] Among them, the filtering coefficient refers to the degree to which the normalized connection point image needs to be filtered, the target filtering function refers to the function after parameter adjustment of the kernel size (determines the filtering range) and standard deviation (determines the filtering strength) of the filtering algorithm, and the pixel filtering value refers to the value of the image pixel after filtering the normalized connection point image.

[0080] Furthermore, in an optional embodiment of the present invention, the pixel filtering value of the normalized tie point image is calculated based on the target filtering function, including: based on the target filtering function, the pixel filtering value of the normalized tie point image is calculated using the following formula:

[0081] G(a,c)=conv2(Y,W)

[0082] Among them, G(a,c) represents the pixel filter value of the normalized tie point image, Y represents the normalized tie point image, W represents the target filter function of the normalized tie point image, conv2 represents the two-dimensional convolution operation, and (a,c) represents the pixel coordinates corresponding to the normalized tie point image.

[0083] S4. Construct a wavelet basis function of the filtered connection point image, perform frequency wavelet transform on the filtered connection point image through the wavelet basis function to obtain image frequency components, calculate the image local energy of the image frequency components, and extract connection point texture features of the filtered connection point image through the image local energy.

[0084] The embodiment of the present invention can realize feature extraction of the filtered connection point image by constructing a wavelet basis function of the filtered connection point image, thereby improving the recognition effect of the wire clamp connection point. The wavelet basis function refers to a function that performs wavelet transform on an image, such as Haar wavelet and Daubechies wavelet. The filtered connection point image can be determined by the features of the filtered connection point image.

[0085] Furthermore, the embodiment of the present invention performs a frequency wavelet transform on the filtered connection point image through the wavelet basis function to obtain the image frequency components, which can perform multi-scale analysis on the image and decompose the image into frequency domain information at different scales. This helps to better capture the local features and frequency information in the image, and is also beneficial for subsequent processing and analysis. Among them, the image frequency components refer to signal components of various frequencies contained in the image, such as DC components: DC components refer to signals with a frequency of 0 in the image, which usually reflect the average brightness or grayscale level of the image, low-frequency components: low-frequency components mainly include low-frequency signals in the image, such as slowly changing textures, backgrounds, etc. These components correspond to smooth areas of the image and affect the overall brightness, color and contrast of the image, and high-frequency components: high-frequency components mainly include high-frequency signals in the image, such as sharply changing edges, noise and other components.

[0086] As an embodiment of the present invention, the step of performing frequency wavelet transform on the filter connection point image by using the wavelet basis function to obtain the image frequency components includes: determining a decomposition level of the filter connection point image; performing discrete wavelet transform on the filter connection point image by using the wavelet basis function by using the decomposition level to obtain a discrete wavelet transform image;

[0087] Extracting wavelet coefficients of the discrete wavelet transform image; and identifying image frequency components of the discrete wavelet transform image based on the wavelet coefficients.

[0088] The decomposition level refers to the level of image decomposition, that is, the number of layers of wavelet decomposition. The higher the decomposition level, the more detailed the frequency components obtained. The discrete wavelet transform image refers to the decomposition of the filter connection point image into component images of different scales, directions and frequencies. The wavelet coefficient refers to the coefficient of each pixel point of the image at each scale during the wavelet transform process.

[0089] Furthermore, the embodiments of the present invention can better analyze the frequency components in the image and understand the energy distribution at different frequencies by calculating the image local energy of the image frequency components. This helps to further analyze the image features such as texture, edge and noise. The image local energy refers to the energy value of each pixel in the image, which reflects the strength and degree of change of the signal near the pixel.

[0090] As an embodiment of the present invention, the calculation of the image local energy of the image frequency component includes: dividing the frequency size levels of the image frequency component; based on the frequency size levels, determining the high-frequency frequency scale of the image frequency component; based on the high-frequency frequency scale, extracting the high-frequency component in the image frequency component; and calculating the image local energy of the high-frequency component.

[0091] Among them, the frequency size level refers to dividing the corresponding components of the image frequency components into different scales, for example, low-frequency components are divided into low-frequency level 1 and low-frequency level 2, and medium-frequency components are divided into medium-frequency level 1 and medium-frequency level 2, etc. The high-frequency frequency scale refers to the high-frequency scale to be extracted from the image frequency components, and the high-frequency component refers to the high-frequency part extracted from the image frequency components.

[0092] Furthermore, in an optional embodiment of the present invention, the calculation of the local image energy of the high-frequency component includes: determining the scaled wavelet coefficient of the high-frequency scale corresponding to the high-frequency component, and based on the scaled wavelet coefficient; calculating the local image energy of the high-frequency component using the following formula:

[0093] P(x,y)=∑|DWT(ω)(x,y,S)|2

[0094] Among them, P(x,y) represents the local energy of the image corresponding to the coordinate (x,y) of the high-frequency component, S represents the high-frequency scale corresponding to the high-frequency component, DWT(ω)(x,y,S) represents the wavelet coefficient of the high-frequency component at the coordinate (x,y) and the high-frequency scale S, DWT(ω) represents the wavelet coefficient matrix of the high-frequency component, and ω represents the high-frequency component.

[0095] Furthermore, the embodiment of the present invention can extract detailed features of the wire clamp connection points by extracting connection point texture features of the filtered connection point image through the local energy of the image, and provide data basis for the subsequent recognition of wire clamp connection points in the image. The connection point texture features refer to the local patterns that appear repeatedly in the image and their arrangement rules. These features are usually used to describe the characteristics of the surface of an object. Texture features can not only reflect the texture information of the surface of an object, but also reveal the essential properties of the object to a certain extent.

[0096] As an embodiment of the present invention, extracting the connection point texture features of the filtered connection point image through the local energy of the image includes: identifying the energy maximum of the local energy of the image; marking the maximum value adjacent area of ​​the filtered connection point image based on the energy maximum; calculating the energy gradient direction of the maximum value adjacent area; and extracting the connection point texture features of the filtered connection point image based on the energy gradient direction.

[0097] Among them, the energy maximum refers to the maximum energy value in the local energy of the image, the maximum value adjacent area refers to the image area adjacent to the energy maximum coordinates, and the energy gradient direction refers to the direction in which the energy distribution in the image changes with the spatial position.

[0098] S5. Acquire an image to be identified, extract image texture features of the image to be identified, calculate feature matching between the connection point texture features and the image texture features, and determine the wire clamp connection points of the image to be identified through the feature matching.

[0099] In the embodiment of the present invention, the image to be identified refers to an image that requires the identification of the connection points of the wire clamp.

[0100] It should be noted that the principle of extracting the texture features of the image to be identified is consistent with the principle of extracting the texture features of the above-mentioned wire clamp connection point image, which will not be further elaborated here.

[0101] Furthermore, the embodiment of the present invention can more accurately identify the target object and scene in the image by calculating the feature matching degree between the connection point texture feature and the image texture feature, thereby improving the recognition accuracy. The feature matching degree refers to the similarity between the connection point texture feature and the image texture feature. The feature matching degree between the connection point texture feature and the image texture feature can be calculated by a similarity function.

[0102] Furthermore, the embodiment of the present invention can accurately identify the wire clamp connection points of the image to be identified by determining the wire clamp connection points of the image to be identified through the feature matching degree. The wire clamp connection points refer to metal accessories used to connect transmission line conductors and electrical equipment in the power system. The wire clamp connection points of the image to be identified can be identified by analyzing a preset feature matching degree threshold.

[0103] The embodiment of the present invention can ensure good image quality by analyzing the validity of the connection points in the wire clamp connection point image, clearly display the appearance features of the wire clamp connection points, and thus ensure the data reliability of the subsequent image processing; the embodiment of the present invention can retain the image edge information by filtering the normalized connection point image using the filtering algorithm to obtain the filtered connection point image, thereby improving the effect of subsequent feature extraction; further, the embodiment of the present invention performs frequency wavelet transform on the filtered connection point image through the wavelet basis function to obtain the image frequency component, which can perform multi-scale analysis on the image and decompose the image into frequency domain information at different scales. This helps to better capture the local features and frequency information in the image, and is also beneficial for subsequent processing and analysis; further, the embodiment of the present invention can better analyze the frequency components in the image and understand the energy distribution at different frequencies by calculating the image local energy of the image frequency component. This helps to further analyze the image's texture, edges, noise and other features. Furthermore, the embodiment of the present invention can extract the detailed features of the wire clamp connection points by extracting the connection point texture features of the filtered connection point image through the local energy of the image, providing a data basis for the subsequent recognition of the wire clamp connection points of the image. Finally, the embodiment of the present invention can more accurately identify the target objects and scenes in the image by calculating the feature matching degree of the connection point texture features and the image texture features, thereby improving the recognition accuracy. Therefore, the method for locating the connection points of wire clamps based on artificial intelligence proposed in the present invention can improve the positioning effect of the wire clamp connection points.

[0104] like Figure 2 , is a functional module diagram of a connection point positioning system for a wire clamp based on artificial intelligence provided by an embodiment of the present invention.

[0105] The connection point positioning system 200 for implementing a wire clamp based on artificial intelligence of the present invention can be installed in an electronic device. According to the functions implemented, the connection point positioning system 200 for implementing a wire clamp based on artificial intelligence can include an image validity analysis model 201, an image normalization module 202, an image filtering processing module 203, a texture feature extraction module 204 and a wire clamp connection point identification module 205. The module of the present invention can also be referred to as a unit, which refers to a series of computer program segments that can be executed by an electronic device processor and can complete fixed functions, which are stored in the memory of the electronic device.

[0106] In this embodiment, the functions of each module / unit are as follows:

[0107] The image validity analysis model 201 is used to obtain a wire clamp connection point image, analyze the connection point validity in the wire clamp connection point image, and extract a target wire clamp connection point image from the wire clamp connection point image based on the connection point validity;

[0108] The image normalization module 202 is used to normalize the target wire clamp connection point image to obtain a normalized connection point image, identify image features of the normalized connection point image, and determine a filtering algorithm for the normalized connection point image based on the image features;

[0109] The image filtering processing module 203 is used to filter the normalized tie point image using the filtering algorithm to obtain a filtered tie point image;

[0110] The texture feature extraction module 204 is used to construct a wavelet basis function of the filtered tie point image, perform frequency wavelet transform on the filtered tie point image through the wavelet basis function to obtain image frequency components, calculate the image local energy of the image frequency components, and extract the tie point texture features of the filtered tie point image through the image local energy;

[0111] The wire clamp connection point recognition module 205 is used to obtain the image to be recognized, extract the image texture features of the image to be recognized, calculate the feature matching degree between the connection point texture features and the image texture features, and determine the wire clamp connection points of the image to be recognized through the feature matching degree.

[0112] In detail, the modules described in the artificial intelligence-based wire clamp connection point positioning system 200 described in the embodiment of the present invention adopt the same technical means as the artificial intelligence-based wire clamp connection point positioning method described in the accompanying drawings when used, and can produce the same technical effects, which will not be repeated here.

[0113] An embodiment of the present invention provides an electronic device for implementing a method for locating a connection point of a wire clamp based on artificial intelligence.

[0114] See also Figure 3 As shown, the electronic device may include a processor 30, a memory 31, a communication bus 32 and a communication interface 33, and may also include a computer program stored in the memory 31 and executable on the processor 30, such as a connection point positioning method program for a wire clamp based on artificial intelligence.

[0115] In some embodiments, the processor may be composed of an integrated circuit, for example, a single packaged integrated circuit, or a plurality of packaged integrated circuits with the same or different functions, including one or more central processing units (CPUs), microprocessors, digital processing chips, graphics processors, and combinations of various control chips. The processor is the control core (Control Unit) of the electronic device, which connects the various components of the entire electronic device using various interfaces and lines, and executes or executes programs or modules stored in the memory (for example, executing a connection point positioning program for a wire clamp based on artificial intelligence, etc.), and calls data stored in the memory to execute various functions of the electronic device and process data.

[0116] The memory includes at least one type of readable storage medium, and the readable storage medium includes flash memory, mobile hard disk, multimedia card, card-type memory (for example: SD or DX memory, etc.), magnetic memory, disk, optical disk, etc. In some embodiments, the memory can be an internal storage unit of an electronic device, such as a mobile hard disk of the electronic device. In other embodiments, the memory can also be an external storage device of an electronic device, such as a plug-in mobile hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the electronic device. Further, the memory can also include both an internal storage unit of the electronic device and an external storage device. The memory can not only be used to store application software and various types of data installed in the electronic device, such as the code of the connection point positioning program based on artificial intelligence to realize the wire clamp, but also can be used to temporarily store data that has been output or is to be output.

[0117] The communication bus may be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The bus may be divided into an address bus, a data bus, a control bus, etc. The bus is configured to realize connection and communication between the memory and at least one processor, etc.

[0118] The communication interface is used for communication between the above-mentioned electronic device and other devices, including a network interface and a user interface. Optionally, the network interface may include a wired interface and / or a wireless interface (such as a WI-FI interface, a Bluetooth interface, etc.), which is generally used to establish a communication connection between the electronic device and other electronic devices. The user interface may be a display (Display), an input unit (such as a keyboard (Keyboard)), and optionally, the user interface may also be a standard wired interface, a wireless interface. Optionally, in some embodiments, the display may be an LED display, a liquid crystal display, a touch-sensitive liquid crystal display, and an OLED (Organic Light-Emitting Diode, organic light-emitting diode) touch device, etc. Among them, the display may also be appropriately referred to as a display screen or a display unit, which is used to display information processed in the electronic device and to display a visual user interface.

[0119] For example, although not shown, the electronic device may also include a power source (such as a battery) for supplying power to each component. Preferably, the power source may be logically connected to the at least one processor through a power management system, so that the power management system can realize functions such as charging management, discharging management, and power consumption management. The power source may also include any components such as one or more DC or AC power sources, recharging systems, power failure detection circuits, power converters or inverters, and power status indicators. The electronic device may also include a variety of sensors, Bluetooth modules, Wi-Fi modules, etc., which will not be repeated here.

[0120] It should be understood that the embodiment is for illustration only and the scope of the patent application is not limited to this structure.

[0121] The connection point positioning program for the wire clamp based on artificial intelligence stored in the memory of the electronic device is a combination of multiple instructions. When running in the processor, it can achieve:

[0122] Acquire a wire clamp connection point image, analyze the connection point validity in the wire clamp connection point image, and extract a target wire clamp connection point image in the wire clamp connection point image based on the connection point validity;

[0123] Normalizing the target wire clamp connection point image to obtain a normalized connection point image, identifying image features of the normalized connection point image, and determining a filtering algorithm for the normalized connection point image based on the image features;

[0124] Using the filtering algorithm to filter the normalized tie point image to obtain a filtered tie point image;

[0125] Constructing a wavelet basis function of the filtered tie point image, performing a frequency wavelet transform on the filtered tie point image through the wavelet basis function to obtain an image frequency component, calculating an image local energy of the image frequency component, and extracting a tie point texture feature of the filtered tie point image through the image local energy;

[0126] An image to be identified is acquired, image texture features of the image to be identified are extracted, a feature matching degree between the connection point texture features and the image texture features is calculated, and a wire clamp connection point of the image to be identified is determined through the feature matching degree.

[0127] Specifically, the specific implementation method of the processor for the above instructions can refer to the description of the relevant steps in the corresponding embodiment of the accompanying drawings, which will not be repeated here.

[0128] Furthermore, if the module / unit integrated in the electronic device is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer-readable storage medium can be volatile or non-volatile. For example, the computer-readable medium may include: any entity or system capable of carrying the computer program code, a recording medium, a USB flash drive, a mobile hard disk, a magnetic disk, an optical disk, a computer memory, and a read-only memory (ROM).

[0129] The present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor of an electronic device, the computer program can implement:

[0130] Acquire a wire clamp connection point image, analyze the connection point validity in the wire clamp connection point image, and extract a target wire clamp connection point image in the wire clamp connection point image based on the connection point validity;

[0131] Normalizing the target wire clamp connection point image to obtain a normalized connection point image, identifying image features of the normalized connection point image, and determining a filtering algorithm for the normalized connection point image based on the image features;

[0132] Using the filtering algorithm to filter the normalized tie point image to obtain a filtered tie point image;

[0133] Constructing a wavelet basis function of the filtered tie point image, performing a frequency wavelet transform on the filtered tie point image through the wavelet basis function to obtain an image frequency component, calculating an image local energy of the image frequency component, and extracting a tie point texture feature of the filtered tie point image through the image local energy;

[0134] An image to be identified is acquired, image texture features of the image to be identified are extracted, a feature matching degree between the connection point texture features and the image texture features is calculated, and a wire clamp connection point of the image to be identified is determined through the feature matching degree.

[0135] In the several embodiments provided by the present invention, it should be understood that the disclosed devices, systems and methods can be implemented in other ways. For example, the system embodiments described above are only schematic, for example, the division of the modules is only a logical function division, and there may be other division methods in actual implementation.

[0136] The modules described as separate components may or may not be physically separated, and the components shown as modules 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 modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0137] In addition, each functional module in each embodiment of the present invention 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. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional modules.

[0138] It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and that the present invention can be implemented in other specific forms without departing from the spirit or essential characteristics of the present invention.

[0139] Therefore, no matter from which point of view, the embodiments should be regarded as illustrative and non-restrictive, and the scope of the present invention is limited by the appended claims rather than the above description, so it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any attached figure mark in the claims should not be regarded as limiting the claims involved.

[0140] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is the theory, method, technology and application system that uses digital computers or machines controlled by digital computers to simulate, extend and expand human intelligence, perceive the environment, acquire knowledge and use knowledge to obtain the best results.

[0141] In addition, it is clear that the word "comprising" does not exclude other units or steps, and the singular does not exclude the plural. Multiple units or systems stated in a system claim can also be implemented by one unit or system through software or hardware. The words first, second, etc. are used to indicate names, and do not indicate any particular order.

[0142] Finally, it should be noted that the above embodiments are only used to illustrate the technical solution of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope of the technical solution of the present invention.

Claims

1. A method for locating the connection point of a wire clamp based on artificial intelligence, characterized in that: The method comprises: Acquire a wire clamp connection point image, mark a connection point region of the wire clamp connection point image, analyze a connection point recognition coefficient of the connection point region, wherein the connection point recognition coefficient refers to the degree to which connection points in the connection point region can be completely recognized, analyze the connection point validity in the wire clamp connection point image based on the connection point recognition coefficient, and extract a target wire clamp connection point image from the wire clamp connection point image based on the connection point validity; Normalizing the target wire clamp connection point image to obtain a normalized connection point image, identifying image features of the normalized connection point image, and determining a filtering algorithm for the normalized connection point image based on the image features; Using the filtering algorithm to filter the normalized tie point image to obtain a filtered tie point image; Constructing a wavelet basis function of the filtered tie point image, performing a frequency wavelet transform on the filtered tie point image through the wavelet basis function to obtain an image frequency component, calculating an image local energy of the image frequency component, and extracting a tie point texture feature of the filtered tie point image through the image local energy; An image to be identified is acquired, image texture features of the image to be identified are extracted, a feature matching degree between the connection point texture features and the image texture features is calculated, and a wire clamp connection point of the image to be identified is determined through the feature matching degree.

2. The method for locating the connection point of a wire clamp based on artificial intelligence as claimed in claim 1, characterized in that: The step of normalizing the target wire clamp connection point image to obtain a normalized connection point image includes: Dividing the target wire clamp connection point image into regional wire clamp connection point images; Calculate the regional average value and the regional standard deviation of the regional clip connection point image respectively; Determine a normalization function of pixels in a region corresponding to the region clip connection point image based on the region average value and the region standard deviation; The regional line clip connection point image is normalized by using the normalization function to obtain the normalized connection point image.

3. The method for locating the connection point of a wire clamp based on artificial intelligence as claimed in claim 1, characterized in that: The filtering process of the normalized tie point image using the filtering algorithm to obtain a filtered tie point image includes: determining filter coefficients of the normalized tie point image; Based on the filtering coefficient, adjusting the filtering parameters of the filtering algorithm to obtain a target filtering function; Based on the target filtering function, calculating pixel filtering values ​​of the normalized tie point image; A filtered tie point image of the normalized tie point image is generated based on the pixel filter values.

4. The method for locating the connection point of a wire clamp based on artificial intelligence as claimed in claim 3, characterized in that: The calculating the pixel filtering value of the normalized tie point image based on the target filtering function comprises: Based on the target filter function, the pixel filter value of the normalized tie point image is calculated using the following formula: ； in, represents the pixel filter value of the normalized tie point image, represents the normalized connection point image, represents the target filter function of the normalized tie-point image, represents a two-dimensional convolution operation, Represents the pixel coordinates corresponding to the normalized connection point image.

5. The method for locating the connection point of a wire clamp based on artificial intelligence as claimed in claim 1, characterized in that: The step of performing frequency wavelet transform on the filtered connection point image by using the wavelet basis function to obtain the image frequency component comprises: determining a decomposition level of the filtered tie point image; Through the decomposition level, the filter tie point image is subjected to discrete wavelet transformation using the wavelet basis function to obtain a discrete wavelet transformation image; Extracting wavelet coefficients of the discrete wavelet transform image; Based on the wavelet coefficients, image frequency components of the discrete wavelet transformed image are identified.

6. The method for locating the connection point of a wire clamp based on artificial intelligence as claimed in claim 1, characterized in that: The calculating the image local energy of the image frequency component comprises: dividing the frequency components of the image into frequency size levels; Determining a high frequency scale of the image frequency component based on the frequency size level; extracting high-frequency components from the image frequency components based on the high-frequency frequency scale; The local image energy of the high frequency component is calculated.

7. The method for locating the connection point of a wire clamp based on artificial intelligence as claimed in claim 6, characterized in that: The calculating the local image energy of the high-frequency component comprises: Determining the scale wavelet coefficients of the high frequency scale corresponding to the high frequency component; Based on the scaled wavelet coefficients, the image local energy of the high-frequency component is calculated using the following formula: ； in, Indicates the coordinates corresponding to the high-frequency components The local energy of the image, Indicates that the high-frequency component corresponds to the high-frequency scale, Indicates that the high-frequency components are in the coordinate High frequency scale The wavelet coefficients of The wavelet coefficient matrix representing the high-frequency components, Indicates high-frequency components.

8. The method for locating the connection point of a wire clamp based on artificial intelligence as claimed in claim 1, characterized in that: The step of extracting the connection point texture features of the filtered connection point image by using the local energy of the image comprises: Identifying an energy maximum of local energy of the image; Based on the energy maximum, marking the maximum value adjacent area of ​​the filtered tie point image; Calculate the energy gradient direction of the area adjacent to the maximum value; Based on the energy gradient direction, connection point texture features of the filtered connection point image are extracted.

9. A connection point positioning system for a wire clamp based on artificial intelligence, characterized in that: The system is used to execute the method for locating the connection point of a wire clamp based on artificial intelligence as claimed in any one of claims 1 to 8, and comprises: An image validity analysis model is used to obtain a wire clamp connection point image, analyze the connection point validity in the wire clamp connection point image, and extract a target wire clamp connection point image from the wire clamp connection point image based on the connection point validity; An image normalization module, used to normalize the target wire clamp connection point image to obtain a normalized connection point image, identify image features of the normalized connection point image, and determine a filtering algorithm for the normalized connection point image based on the image features; An image filtering processing module, used for filtering the normalized tie point image using the filtering algorithm to obtain a filtered tie point image; A texture feature extraction module is used to construct a wavelet basis function of the filtered tie point image, perform frequency wavelet transform on the filtered tie point image through the wavelet basis function to obtain image frequency components, calculate image local energy of the image frequency components, and extract tie point texture features of the filtered tie point image through the image local energy; The wire clamp connection point recognition module is used to obtain the image to be recognized, extract the image texture features of the image to be recognized, calculate the feature matching degree between the connection point texture features and the image texture features, and determine the wire clamp connection points of the image to be recognized through the feature matching degree.

Images