Instrument data identification method, apparatus and device, and storage medium

Abstract

An instrument data identification method relates to the technical field of industrial automation. In the method, multi-dimensional image data and structural parameters of a to-be-detected instrument are collected, the multi-dimensional image data comprise point cloud data and image data, and the structural parameters comprise a measuring range, scale distribution and a display mode; performing deep layering processing on the multi-dimensional image data, and extracting instrument layer image data; performing enhancement processing on the instrument layer image data to obtain final image data; generating a three-dimensional model of the instrument to be detected based on the final image data and the structure parameters; key features of the three-dimensional model are extracted and matched with standard features in a preset instrument library, and a matching result is obtained; and according to the matching result, calling a detection model corresponding to the to-be-detected instrument to perform data identification on the to-be-detected instrument. According to the invention, the accuracy of instrument data identification is improved.

Description

Technical Field

[0001] The present application relates to the field of industrial automation technology, and in particular to an instrument data recognition method, device, equipment and storage medium. Background Art

[0002] With the deepening of industrial automation and digital transformation, the identification and collection of instrument data at industrial sites is becoming an important basis for production process monitoring and intelligent decision-making. In industrial production environments, a large number of various instrument equipment such as pressure gauges, flow meters, and thermometers are distributed. These instruments undertake the key task of real-time monitoring of production parameters. The accurate identification of their data directly affects the safety and controllability of the production process. Therefore, an instrument data identification method is urgently needed.

[0003] The existing technology mainly obtains the instrument's measurement data by acquiring instrument image data and using image processing methods to identify the image data.

[0004] However, due to the complex environment of industrial sites, interference factors such as reflections, stains, and blur often appear on the surface of instruments. Traditional single image processing methods are difficult to cope with these complex situations, which can easily lead to large deviations in recognition results, resulting in low accuracy in identifying instrument data. Summary of the Invention

[0005] The present application provides a meter data recognition method, device, equipment and storage medium, which have the effect of improving the accuracy of meter data recognition.

[0006] In a first aspect of the present application, a method for identifying instrument data is provided, comprising: collecting multidimensional image data and structural parameters of an instrument to be detected, the multidimensional image data comprising point cloud data and image data, the structural parameters comprising a measuring range, a scale distribution, and a display mode; performing deep layering processing on the multidimensional image data to extract instrument layer image data; performing enhancement processing on the instrument layer image data to obtain final image data; generating a three-dimensional model of the instrument to be detected based on the final image data and the structural parameters; extracting key features of the three-dimensional model and matching them with standard features in a preset instrument library to obtain a matching result; and based on the matching result, calling a detection model corresponding to the instrument to be detected to perform data identification on the instrument to be detected.

[0007] By adopting the above-mentioned technical solution, the present application obtains multidimensional image data by simultaneously collecting point cloud data and image data, and combines structural parameters such as range, scale distribution and display mode to provide rich input information for instrument identification. The multidimensional image data is deeply layered to extract instrument layer image data, effectively removing the influence of background and other interference layers. The extracted instrument layer image data is enhanced to solve the image quality problems caused by interference factors such as reflection, stains, and blur on the instrument surface in industrial field environments. Based on the processed high-quality image data and structural parameters, a three-dimensional model of the instrument to be inspected is generated, retaining the spatial structural characteristics of the instrument. By extracting the key features of the three-dimensional model and matching them with standard features in a preset instrument library, the instrument type is accurately identified. The corresponding detection model is called for data recognition based on the matching results, thereby achieving accurate identification of instrument data. This solution effectively solves the problem of low recognition accuracy of traditional single image processing methods in complex industrial environments through the technical means of multi-dimensional data acquisition, deep layered extraction, image enhancement processing, three-dimensional model construction and feature matching, and significantly improves the accuracy of instrument data recognition.

[0008] Optionally, the depth layering processing of the multidimensional image data to obtain instrument layer image data specifically includes: constructing a depth mapping matrix based on the multidimensional image data; performing layering processing on the multidimensional image data according to the depth distribution characteristics in the depth mapping matrix to obtain a preliminary layering result; denoising and repairing broken areas of each depth layer in the preliminary layering result to obtain an optimized layering result; extracting the feature set of each depth layer in the optimized layering result, calculating the similarity between the feature set of each depth layer and the standard feature set, and selecting the depth layer with the highest similarity as the instrument layer; converting the instrument layer into a two-dimensional image to obtain instrument layer image data.

[0009] By adopting the above-mentioned technical solution, the present application spatially models the image by constructing a depth mapping matrix. The rows and columns of the matrix correspond to the vertical and horizontal coordinates of the image, and the matrix elements record the depth values of the pixel points, thereby achieving an accurate description of the spatial structure of the image. The multidimensional image data is layered through the depth distribution characteristics in the depth mapping matrix, and an independent three-dimensional point cloud subset is generated as a depth layer through depth threshold segmentation. Each depth layer is denoised and fracture repaired for optimization to improve the tomography quality. The optimal instrument layer is selected by feature set similarity calculation and matching. Finally, the three-dimensional instrument layer is converted into two-dimensional image data, thereby achieving effective extraction of the instrument layer in a complex industrial environment.

[0010] Optionally, the multidimensional image data is layered according to the depth distribution characteristics in the depth mapping matrix to obtain a preliminary layering result, and the preliminary layering result is composed of at least one depth layer, and the depth layer is an independent three-dimensional point cloud subset generated by depth threshold segmentation, specifically including: according to a preset depth threshold and the depth value distribution characteristics in the depth mapping matrix, the data with depth values in the multidimensional image data in the same interval are divided into the same layer to obtain a preliminary hierarchical structure; based on the preliminary hierarchical structure, the depth difference of adjacent point cloud data in each layer is calculated, and each layer is subdivided based on the depth difference to obtain multiple candidate depth layers; based on a preset depth similarity judgment standard, the candidate depth layers are merged to obtain a preliminary layering result.

[0011] By adopting the above-mentioned technical solution, the present application divides the data with depth values in the same interval in the multidimensional image data into the same layer based on the depth value distribution characteristics and preset thresholds in the depth mapping matrix, realizes the preliminary stratification of scene data by setting multi-level thresholds, calculates the depth difference of adjacent point cloud data in each layer based on the preliminary hierarchical structure and performs inter-layer subdivision to obtain candidate depth layers with similar depth features, merges the candidate depth layers using the preset depth similarity judgment standard, realizes the refined processing of the depth layer, and realizes the accurate division and merging of different depth layers by combining depth threshold segmentation and depth difference calculation.

[0012] Optionally, the feature set of each depth layer in the optimized stratification result is extracted, the similarity between the feature set of each depth layer and the standard feature set is calculated, and the depth layer with the highest similarity is selected as the instrument layer, specifically including: extracting the feature set of each depth layer in the optimized stratification result, each feature set including geometric shape features and depth distribution features, and the depth distribution features are distribution features obtained by statistics of depth values; comparing each feature in each feature set with the corresponding feature in the standard feature set to determine the initial score corresponding to each feature; determining the similarity score of each feature set based on the initial score corresponding to each feature and the corresponding preset weight; and selecting the depth layer with the highest similarity score as the instrument layer.

[0013] By adopting the above-mentioned technical solution, the present application constructs a feature set including geometric shape features and depth distribution features, wherein the geometric shape features reflect the outer contour and internal structure information of the instrument, and the depth distribution features reflect the spatial distribution law of the instrument surface by performing statistical analysis on the depth values. The features in each feature set are compared with the standard feature set in multiple dimensions to obtain an initial score, and the scores of different features are weightedly calculated using preset weights to obtain a similarity score. The optimal instrument layer is selected based on the scoring results, and feature scoring is achieved through multi-dimensional comparison and weight calculation of features. The depth layer is comprehensively evaluated by multi-feature fusion to achieve accurate selection of the optimal instrument layer.

[0014] Optionally, the instrument layer image data is enhanced to obtain final image data, specifically including: performing illumination compensation on the instrument layer image data to obtain first image data; performing edge sharpening on the first image data to obtain second image data; and performing corresponding area enhancement on the second image data in combination with the scale distribution to obtain final image data.

[0015] By adopting the above-mentioned technical solution, the present application performs multi-stage enhancement processing on the instrument layer image data. First, the uneven illumination on the instrument surface is corrected by illumination compensation technology to obtain the first image data with balanced illumination. The first image data is subjected to edge sharpening processing to enhance the edge features of the instrument pointer and scale to obtain the second image data. Combined with the pre-acquired scale distribution information, the scale area is targetedly enhanced to obtain the final image data. Through the processing methods of illumination compensation, edge sharpening and area enhancement, the instrument layer image is fully optimized, providing high-quality image data for subsequent three-dimensional modeling and data recognition.

[0016] Optionally, generating a three-dimensional model of the instrument to be inspected based on the final image data and the structural parameters specifically includes: constructing an initial three-dimensional model based on the point cloud data; extracting the first texture feature in the final image data; constructing constraint conditions according to the measuring range and the display mode; aligning the initial three-dimensional model with the basic model with the highest matching degree in a preset instrument basic template library to obtain a registered three-dimensional model; optimizing the registered three-dimensional model in combination with the texture features and the constraint conditions to obtain a three-dimensional model.

[0017] By adopting the above-mentioned technical solution, this application constructs an initial three-dimensional model of the instrument based on high-quality point cloud data, extracts the texture features of the optimized image data as an important basis for model optimization, sets constraints for model optimization according to the measuring range and display mode of the instrument, and realizes standardization of the model by aligning it with the basic model in the preset template library. The alignment model is optimized and adjusted in combination with the texture features and constraints, thereby realizing accurate reconstruction of the three-dimensional structure of the instrument.

[0018] Optionally, the extracting of key features of the three-dimensional model and matching them with standard features in a preset instrument library to obtain a matching result specifically includes: extracting geometric features, second texture features and structural features of the three-dimensional model; using the geometric features and the structural features to match based on corresponding standard geometric features and standard structural features in a preset instrument library to obtain a first matching result; using the second texture features to match the corresponding standard texture features in the first matching result to obtain a matching result.

[0019] By adopting the above-mentioned technical solution, the present application performs multi-dimensional feature extraction on the three-dimensional model, and obtains the geometric features reflecting the appearance of the instrument, the texture features reflecting the surface information of the instrument, and the structural features reflecting the composition of the instrument. A two-stage matching method is adopted to first perform rough matching through geometric features and structural features to obtain preliminary results, and then combine texture features for precise matching to obtain the final matching results. Accurate identification of instrument types is achieved through multi-feature extraction and staged matching.

[0020] In a second aspect of the present application, a meter data identification system is provided, comprising: A multi-dimensional data acquisition module is used to acquire multi-dimensional image data and structural parameters of the instrument to be tested, wherein the multi-dimensional image data includes point cloud data and image data, and the structural parameters include measuring range, scale distribution and display mode; A depth layer processing module, configured to perform depth layer processing on the multi-dimensional image data and extract instrument layer image data; An image enhancement processing module is used to perform enhancement processing on the instrument layer image data to obtain final image data; A three-dimensional modeling generation module, configured to generate a three-dimensional model of the instrument to be inspected based on the final image data and the structural parameters; A feature matching analysis module is used to extract key features of the three-dimensional model and match them with standard features in a preset instrument library to obtain matching results; The intelligent detection calling module is used to call the detection model corresponding to the instrument to be detected to perform data recognition on the instrument to be detected according to the matching result.

[0021] By adopting the above-mentioned technical solution, the present application obtains multidimensional image data by simultaneously collecting point cloud data and image data, and combines structural parameters such as range, scale distribution and display mode to provide rich input information for instrument identification. The multidimensional image data is deeply layered to extract instrument layer image data, effectively removing the influence of background and other interference layers. The extracted instrument layer image data is enhanced to solve the image quality problems caused by interference factors such as reflection, stains, and blur on the instrument surface in industrial field environments. Based on the processed high-quality image data and structural parameters, a three-dimensional model of the instrument to be inspected is generated, retaining the spatial structural characteristics of the instrument. By extracting the key features of the three-dimensional model and matching them with standard features in a preset instrument library, the instrument type is accurately identified. The corresponding detection model is called for data recognition based on the matching results, thereby achieving accurate identification of instrument data. This solution effectively solves the problem of low recognition accuracy of traditional single image processing methods in complex industrial environments through the technical means of multi-dimensional data acquisition, deep layered extraction, image enhancement processing, three-dimensional model construction and feature matching, and significantly improves the accuracy of instrument data recognition.

[0022] In the third aspect of the present application, an electronic device is provided, including a processor, a memory, a user interface and a network interface, the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device performs any of the methods described above.

[0023] In a fourth aspect of the present application, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores instructions. When the instructions are executed, any one of the methods described above is executed. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 This is a schematic diagram of the architecture of an instrument data identification system disclosed in an embodiment of the present application; Figure 2 This is a flow chart of an instrument data identification method disclosed in an embodiment of the present application; Figure 3 yes Figure 2 A schematic flow chart of a sub-step of step S102; Figure 4 yes Figure 3 A schematic flow chart of a sub-step of step S202; Figure 5 yes Figure 3 A schematic flow chart of a sub-step of step S204; Figure 6 yes Figure 2 A schematic flow chart of a sub-step of step S103; Figure 7 yes Figure 2 A schematic flow chart of a sub-step of step S104; Figure 8 yes Figure 2 A schematic flow chart of a sub-step of step S105; Figure 9 This is a module diagram of an instrument data identification system provided in an embodiment of the present application; Figure 10 This is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application.

[0025] Explanation of the accompanying drawings: 21. Multi-dimensional data acquisition module; 22. Depth layering processing module; 23. Image enhancement processing module; 24. Three-dimensional modeling generation module; 25. Feature matching analysis module; 26. Intelligent detection calling module; 901. Processor; 902. Communication bus; 903. User interface; 904. Network interface; 905. Memory. DETAILED DESCRIPTION

[0026] In order to enable those skilled in the art to better understand the technical solutions in this specification, the technical solutions in the embodiments of this specification will be clearly and completely described below in conjunction with the drawings in the embodiments of this specification. Obviously, the described embodiments are only part of the embodiments of this application, not all of the embodiments.

[0027] In the description of the embodiments of this application, words such as "for example" or "for instance" are used to indicate examples, illustrations, or explanations. Any embodiment or design described as "for example" or "for instance" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "for example" or "for instance" is intended to present the relevant concepts in a concrete manner.

[0028] In the description of the embodiments of the present application, the term "multiple" means two or more. For example, multiple systems refer to two or more systems, and multiple screen terminals refer to two or more screen terminals. In addition, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as indicating or implying relative importance or implicitly indicating the indicated technical features. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized.

[0029] Figure 1 An exemplary system architecture 10 of a meter data recognition system is shown.

[0030] like Figure 1 As shown, system architecture 10 may include electronic device 11, network 12, and server 13. Network 12 is used to provide a medium for a communication link between electronic device 11 and server 13. Network 12 may include various connection types, such as wired or wireless communication links or fiber optic cables.

[0031] The operator can use the electronic device 11 to interact with the server 13 via the network 12 to receive or send data, etc. Various recognition applications can be installed on the electronic device 11, such as instrument data collection applications, instrument image processing applications, etc.

[0032] The electronic device 11 is hardware, and may be any electronic device with a display screen, including but not limited to a smart phone, a tablet computer, a portable detection terminal, and an industrial control computer.

[0033] The server 13 may be a background server that provides various identification services, such as a computing server that processes meter data collected by the electronic device 11. The background server may analyze the received data and feed back the processing results (identification results) to the electronic device.

[0034] The following describes the electronic equipment side in detail as an example.

[0035] This embodiment discloses a method for identifying instrument data. Figure 2 This is a flow chart of a method for identifying instrument data disclosed in an embodiment of the present application, such as Figure 2 As shown, including steps S101 to S106, the above steps are as follows: S101: Collect multi-dimensional image data and structural parameters of the instrument to be tested, where the multi-dimensional image data includes point cloud data and image data, and the structural parameters include measuring range, scale distribution, and display mode.

[0036] Among them, the instrument to be tested refers to the analog instrument equipment that needs to be tested, such as pressure gauges, thermometers and other measuring instruments with pointers and scales. Multi-dimensional image data refers to the digital representation data collected from multiple angles and directions of the instrument, which includes the point cloud data and image data of the instrument. The point cloud data represents the spatial position information of the instrument surface obtained by three-dimensional scanning, and is composed of a large number of discrete spatial coordinate points. Image data is used to represent the two-dimensional visible light information of the instrument surface, including color, texture and other features. Structural parameters refer to the basic working parameters of the instrument, among which the range represents the maximum and minimum value intervals that the instrument can measure, the scale distribution is used to represent the position and spacing pattern of the instrument scale lines, and the display mode represents the reading display form of the instrument, such as circle, sector, etc.

[0037] Specifically, the electronic device first starts the three-dimensional scanning module and the image acquisition module, and performs all-round data acquisition on the instrument to be tested. The three-dimensional scanning module emits a laser beam to scan the surface of the scanner, receives the reflected signal and converts it into point cloud data. At the same time, the image acquisition module completely records the appearance characteristics and spatial structure information of the instrument by capturing and collecting high-definition image data of the instrument surface. During the acquisition process, the range information of the instrument nameplate area is extracted through the collected image data, and the spacing and distribution characteristics between adjacent scales on the dial are analyzed in combination with the point cloud data to obtain the scale distribution law. The collected image data and point cloud data are matched with the typical characteristics of the preset pointer type, digital type, etc. to identify the display type, and these structural parameters are stored in the database. Through this acquisition process, the electronic device finally obtains multi-dimensional image data including point cloud data and image data, as well as structural parameters including range, scale distribution and display mode.

[0038] S102: Perform deep layering processing on the multi-dimensional image data to extract instrument layer image data.

[0039] The instrument layer image data is used to represent the two-dimensional imaging information of the corresponding depth layer of the instrument surface.

[0040] Specifically, the electronic device performs deep layering processing on the collected multi-dimensional image data based on spatial position relationships to remove background effects and accurately obtain instrument surface information. First, the spatial coordinate information of each data point in the point cloud data is used to obtain the distance of each point to the electronic device. Points with close distances are classified into the same layer, forming multiple position layers from near to far. After obtaining these position layers, the electronic device maps each point in the image to the corresponding position layer. Since the instrument surface forms a relatively complete plane in space, the position layer where the instrument surface is located can be found by identifying the density and continuity characteristics of each layer of points, and then the image information corresponding to this layer can be extracted to obtain the instrument layer image data.

[0041] Reference Figure 3 , Figure 3 This embodiment of the present application provides Figure 2 A schematic flow chart of a sub-step of step S102 includes steps S201 to S205, which are as follows: S201: Based on the multi-dimensional image data, a depth mapping matrix is constructed, where the rows of the depth mapping matrix are the vertical coordinates of the image, the columns are the horizontal coordinates of the image, and the matrix elements are the depth values of the image pixels.

[0042] Among them, the depth mapping matrix refers to a data structure that records the depth value of each position in the image in a two-dimensional table form. The vertical coordinate of the image represents the position of the image in the up and down directions, the horizontal coordinate of the image represents the position of the image in the left and right directions, and the depth value represents the distance from a certain position in the image to the electronic device.

[0043] Specifically, the electronic device needs to organize the multi-dimensional image data into a table form. First, a table is established based on the pixel value of the image data, and then the spatial position of each point in the point cloud data is mapped to a specific position in the image. The straight-line distance from this point to the electronic device is used as the depth value. If multiple points overlap at the same position in the image, the value of the closest point is selected to fill in the table. For positions without points in the table, the distance values of the eight positions around it are found, and these valid distance values are added up to find the average value and fill it in. After all positions are filled in, a complete depth mapping matrix is obtained.

[0044] S202: Based on the depth distribution characteristics in the depth mapping matrix, the multidimensional image data is layered to obtain a preliminary layered result, where the preliminary layered result consists of at least one depth layer, and each depth layer includes an independent three-dimensional point cloud subset generated by depth threshold segmentation.

[0045] Among them, the depth distribution feature represents the distribution law of the distance values in the table, the preliminary stratification result refers to the result obtained by the first stratification, the depth layer represents the layer where a group of data with similar distances are located, the depth threshold refers to the distance limit value used to distinguish different layers, and the 3D point cloud subset represents the collection of spatial position points in the same layer.

[0046] Specifically, the electronic device counts the number of times each distance value appears in the depth mapping matrix and generates a distance distribution histogram, identifies dense distance value areas representing the instrument surface from the histogram, sets the valley positions between these dense areas as depth thresholds, and then uses these depth thresholds to divide the multidimensional image data into several groups, each group of distance values corresponds to a depth layer, and at the same time assigns the point cloud data to the corresponding depth layer according to the distance value. If the distance value of a point falls within the range of a certain depth layer, the point belongs to the depth layer. After this processing, a preliminary stratification result is obtained, which contains at least one depth layer, and each depth layer has a set of three-dimensional point cloud subsets segmented by the depth threshold.

[0047] Reference Figure 4 , Figure 4 This embodiment of the present application provides Figure 3 A schematic flow chart of a sub-step of step S202 includes steps S301 to S303, which are as follows: S301: According to a preset depth threshold and the depth value distribution characteristics in the depth mapping matrix, data with depth values in the same interval in the multidimensional image data are divided into the same layer to obtain a preliminary hierarchical structure.

[0048] The preset depth threshold refers to a pre-set distance limit value for distinguishing different layers. The hierarchical structure refers to different data levels divided according to distance.

[0049] Specifically, the electronic device pre-sets a set of depth thresholds based on experience or actual application requirements. These depth thresholds divide the entire distance range into several intervals, then analyzes the distribution characteristics of the depth values in the depth mapping matrix, and counts the data distribution in each interval. Then, all data points in the multidimensional image data whose depth values fall within the same interval are classified into the same layer. In this way, all data points are assigned to different layers according to the interval position of their depth values, and finally a preliminary hierarchical structure containing multiple data layers is formed, and each layer contains all data points whose depth values are within the corresponding interval range.

[0050] S302: Based on the preliminary hierarchical structure, calculate the depth difference of adjacent point cloud data in each layer, subdivide each layer based on the depth difference, and obtain multiple candidate depth layers.

[0051] Among them, the candidate depth layer represents a finer data level obtained by subdivision.

[0052] Specifically, after obtaining the preliminary hierarchical structure, the electronic device needs to make a finer division of the data in each layer. First, it searches for spatially adjacent point cloud data pairs in each layer and calculates the depth difference between these adjacent data points. When it is found that the depth difference between certain adjacent points is significantly greater than the depth difference of other surrounding adjacent points, it means that these points may belong to different object surfaces, so they need to be divided into different layers. Through this depth difference-based subdivision processing, each original layer is further divided into multiple finer candidate depth layers.

[0053] S303: Based on a preset depth similarity judgment standard, the candidate depth layers are merged to obtain a preliminary layering result.

[0054] Among them, the preset deep similarity judgment standard represents the pre-set judgment rules for judging whether different levels are similar, and the preliminary stratification result represents the data stratification result obtained after merging.

[0055] Specifically, the electronic device pre-sets the depth similarity judgment standard according to the actual application requirements. This standard includes parameters such as the threshold range of the depth difference and the density distribution of data points within the layer. Then, the depth difference between adjacent candidate depth layers is calculated. When the difference between two candidate depth layers meets the preset similarity judgment standard, the two layers are merged into a new layer. In this way, all candidate depth layers that meet the similarity conditions are gradually merged, and finally a preliminary stratification result is obtained that can reflect the depth distribution characteristics of the scene without over-subdividing.

[0056] S203: Denoising and repairing the broken areas of each depth layer in the preliminary stratification result to obtain an optimized stratification result.

[0057] Among them, the preliminary stratification result refers to the data hierarchy result obtained by the first stratification, the depth layer refers to the layer where a group of data with similar distances are located, the broken area refers to the data area that should be continuous but is discontinuous, and the optimized stratification result refers to the more accurate stratification data obtained after denoising and repair.

[0058] Specifically, the electronic device performs denoising on the data within each depth layer in the preliminary stratification results. The standard deviation of the depth value differences between all adjacent pairs of points in the entire depth layer is calculated, and twice this standard deviation is set as a preset threshold for outlier detection. The average depth difference between each data point and its eight surrounding adjacent points is then calculated. If the difference between the depth value of a point and the average depth value of the surrounding points exceeds the preset threshold, the point is marked as an outlier. For marked outliers, the average depth value of the surrounding normal points can be replaced or directly deleted from the data set. The broken areas in the depth layer are then detected. These areas are usually manifested as discontinuous intervals on the surface of an object that should be continuous. For each detected broken area, the depth values of the valid data points at both ends of the broken area are determined. Then, based on the depth values of these two endpoints, the depth values of the missing points in the broken area are calculated using a linear interpolation method. That is, the average depth value of the two end points is calculated as the depth value of the middle position. The calculated depth value is filled into the corresponding position of the broken area, thereby reconnecting the broken areas that may belong to the same object surface and obtaining an optimized stratification result.

[0059] S204: extracting the feature set of each depth layer in the optimized stratification result, calculating the similarity between the feature set of each depth layer and the preset standard feature set, and selecting the depth layer with the highest similarity as the instrument layer.

[0060] Among them, the feature set represents a set of parameters used to describe the shape and distribution characteristics of each layer, the preset standard feature set represents the pre-set standard parameters used to determine whether it is an instrument layer, and the similarity represents the degree of closeness between the two sets of features.

[0061] Specifically, the electronic device identifies the number of data points within each small area to indicate point density, detects edges to determine whether the shape is circular or square, and calculates the depth difference between adjacent points to determine flatness. A standard feature set for the instrument layer is set based on experience or requirements. The absolute value of the difference between each layer's feature set and the standard feature set is calculated. The smaller the absolute value, the closer it is to the instrument layer, and the layer closest to it is selected as the instrument layer.

[0062] Reference Figure 5 , Figure 5 This embodiment of the present application provides Figure 3 A schematic flow chart of a sub-step of step S204 includes steps S401 to S404, which are as follows: S401: Extracting feature sets of each depth layer in the optimized stratification result, each feature set includes geometric shape features and depth distribution features, and the depth distribution features are distribution features obtained by statistics of depth values.

[0063] Among them, the geometric shape features represent the shape and edge features of the layer, the depth distribution features represent the distribution law of the depth values of the data points in the layer, and the feature set represents the collection of the geometric shape features and depth distribution features of a data layer.

[0064] Specifically, electronic devices acquire two types of features for each depth layer. One type is geometric shape features, which connect edge points to form a closed outline, determine its shape type, and calculate the distribution density by counting the number of points per unit area. The other type is depth distribution features, which calculate the overall depth by calculating the average depth of all points in the layer and the fluctuation amplitude by calculating the standard deviation of the depth values. These two types of features are combined to form the feature set for that layer. Each depth layer obtains a feature set that includes both geometric shape features and depth distribution features.

[0065] S402: Compare each feature in each feature set with the corresponding feature in the standard feature set to determine the initial score corresponding to each feature.

[0066] The standard feature set represents a combination of reference features obtained by pre-collecting multiple known instrument layers. The initial score represents the degree of closeness of a single feature to the standard feature.

[0067] Specifically, the electronic device overlaps the actual contour shape with the standard shape, and uses the proportion of the overlapped area to the total area as the shape score. The ratio of the actual point density divided by the standard density is used as the density score. For depth distribution features, the difference between the actual average depth and the standard depth is used as the depth score, and the difference between the actual depth fluctuation and the standard fluctuation is used as the fluctuation score. The scores obtained through these calculations are the initial scores corresponding to each feature, with higher scores indicating closer alignment with the standard feature.

[0068] S403: Determine the similarity score of each feature set based on the initial score corresponding to each feature and the corresponding preset weight.

[0069] The preset weight represents the importance of each feature determined through a large number of tests, and the similarity score represents the degree of match between the overall feature set and the standard feature set.

[0070] Specifically, the electronic device obtains the preset weight of each feature, such as the shape feature weight is 0.4, the density feature weight is 0.2, the depth feature weight is 0.3, and the fluctuation feature weight is 0.1; then the initial score of each feature is multiplied by the corresponding preset weight, such as the shape score multiplied by 0.4, the density score multiplied by 0.2, the depth score multiplied by 0.3, and the fluctuation score multiplied by 0.1; finally, all the weighted scores are added together to obtain the similarity score of the feature set. The higher the similarity score, the more likely the depth layer is to be the instrument layer.

[0071] S404: Select the depth layer with the highest similarity score as the instrument layer.

[0072] Specifically, the electronic device compares the similarity scores of all depth layers, finds the depth layer with the highest score, and determines it as the instrument layer.

[0073] S205: Convert the instrument layer into a two-dimensional image to obtain instrument layer image data.

[0074] Specifically, the electronic device identifies the horizontal and vertical ranges occupied by the instrument layer as the width and height of the converted image, then projects each point in the instrument layer from top to bottom to the corresponding position on the plane. Finally, the depth value of the point at each position is converted into a grayscale value between 0 and 255. In this way, a black and white image composed of these grayscale values is obtained, which is the instrument layer image data.

[0075] S103: Perform enhancement processing on the instrument layer image data to obtain final image data.

[0076] The final image data refers to clearer image data after enhancement.

[0077] Specifically, the electronic device adjusts the grayscale value of the entire image to the middle range to avoid being too dark or too bright, then adjusts the high grayscale value to be higher and the low grayscale value to be lower to expand the difference in grayscale value to make the contrast between the numbers and scales and the background more obvious, and finally strengthens the positions in the image where the grayscale value changes greatly to make the transition of these edge positions steeper, thereby obtaining final image data that is easier to recognize.

[0078] Reference Figure 6 , Figure 6 This embodiment of the present application provides Figure 2A schematic flow chart of a sub-step of step S103 includes steps S501 to S503, which are as follows: S501: Perform illumination compensation on the instrument layer image data to obtain first image data.

[0079] The first image data represents image data after illumination compensation.

[0080] Specifically, the electronic device calculates the average grayscale value of each area in the image, identifies areas where the grayscale values are significantly higher or lower than the overall average, and then adjusts these areas accordingly. For example, if the average grayscale value of a certain area is 180, which is much higher than the overall average of 100, the grayscale value of this area is lowered to close to 100. If the average grayscale value of a certain area is 30, which is much lower than the overall average of 100, the grayscale value of this area is raised to close to 100. Through such adjustments, the grayscale values of various areas of the image are closer together, resulting in more uniform first image data overall.

[0081] S502: Perform edge sharpening processing on the first image data to obtain second image data.

[0082] The second image data represents image data after edge sharpening.

[0083] Specifically, the electronic device identifies positions where grayscale values change dramatically in the image as edge positions, and then increases the grayscale value differences between adjacent pixels at these edge positions to make the edges clearer, thereby obtaining second image data with sharper edges.

[0084] S503: Performing corresponding area enhancement on the second image data in combination with the scale distribution to obtain final image data.

[0085] The final image data refers to the image data after all enhancements are completed.

[0086] Specifically, the electronic device determines the distribution pattern of scale lines and numbers based on the type of instrument. For example, the scales on a circular dial are distributed in a ring, and the scales on a straight strap are distributed linearly. Then, the contrast of the grayscale values in these scale areas is increased to make the grayscale value of the scale more different from the grayscale value of the background while maintaining the continuity of the scale lines. Finally, the final image data with clearer and easier-to-read scales and numbers is obtained.

[0087] S104: Generate a three-dimensional model of the instrument to be inspected based on the final image data and structural parameters.

[0088] Among them, the three-dimensional model represents the three-dimensional digital representation of the instrument.

[0089] Specifically, the electronic device establishes the dial structure and scale start and end positions based on the measuring range, then determines the layout of the scale lines and numbers on the dial according to the scale distribution pattern, and then establishes the pointer or digital display structure on the dial according to the display mode. Finally, the final image data is overlaid on the dial surface through texture mapping to obtain a complete three-dimensional model of the instrument to be tested.

[0090] Reference Figure 7 , Figure 7 This embodiment of the present application provides Figure 2 A schematic flow chart of a sub-step of step S104 includes steps S601 to S605, which are as follows: S601: Construct an initial 3D model based on point cloud data.

[0091] Specifically, the electronic device searches for points with similar positions in the spatial point cloud as adjacent points, then uses triangles to connect every three adjacent points to form a large number of triangular facets, and finally connects all the triangular facets into a whole and smoothes them to obtain an initial three-dimensional model with a smooth surface.

[0092] S602: Extracting a first texture feature from the final image data.

[0093] The first texture feature represents the surface detail feature in the image.

[0094] Specifically, the electronic device obtains the first texture feature by identifying areas in the image where grayscale value changes are similar and appear repeatedly. These areas may be patterns or lines on the surface of the instrument.

[0095] S603: Construct constraint conditions based on the measurement range and display mode.

[0096] Specifically, the electronic device determines the size limit of the dial and the range limit of the scale area according to the range, and then determines whether to follow the circular structure limit of the pointer dial or the rectangular structure limit of the digital dial according to the display mode, and finally obtains the constraint conditions.

[0097] S604: Align the initial three-dimensional model with the basic model with the highest matching degree in the preset instrument basic template library to obtain a registered three-dimensional model.

[0098] Specifically, the electronic device aligns the initial three-dimensional model with the model in the basic template library. First, the initial three-dimensional model is compared with all the models in the basic template library to find the most similar basic model, and then the position and orientation of the initial three-dimensional model are adjusted to make it have the highest degree of overlap with the selected basic model. Finally, a registered three-dimensional model that matches the standard model is obtained.

[0099] S605: Optimize the registered three-dimensional model by combining texture features and constraint conditions to obtain a three-dimensional model.

[0100] The three-dimensional model represents an optimized three-dimensional digital representation.

[0101] Specifically, the electronic device adds texture features to the surface of the registered three-dimensional model to give it realistic appearance details, and then adjusts the shape and size of the model according to the constraints to make it meet the requirements of the range and display mode, and finally obtains the three-dimensional model.

[0102] S105: Extract key features of the 3D model and match them with standard features in a preset instrument library to obtain matching results.

[0103] Among them, the key features represent the main feature parameters of the instrument, the preset instrument library represents the stored information of multiple standard instruments, the standard features represent the feature parameters recorded in the preset instrument library, and the matching results represent the comparison results of the features.

[0104] Specifically, the electronic device obtains characteristic parameters such as the shape and size of the dial, the distribution and spacing of the scales from the three-dimensional model, and combines these parameters into a set of characteristic data. The absolute value of each standard characteristic data in the preset instrument library is then subtracted from this set of data to obtain an error value. The similarity is then calculated based on the size of the error value. The smaller the error value, the higher the similarity. Finally, the similarity with each standard feature is obtained as the matching result.

[0105] Reference Figure 8 , Figure 8 This embodiment of the present application provides Figure 2 A schematic flow chart of a sub-step of step S105 includes steps S701 to S703, which are as follows: S701: Extracting geometric features, secondary texture features and structural features of the 3D model.

[0106] Geometric features represent the shape and size of an object, including basic dimensions such as length, width, and height, and shape features such as round or square. Secondary texture features represent the scale and indication information on the instrument surface, including scale line distribution, digital markings, and pointer position. Structural features represent fitting parameters such as connection area, fitting method, and gap size, obtained by counting the contact areas on the component surfaces.

[0107] Specifically, the electronic device first obtains the coordinates of all grid points on the surface of the three-dimensional model, calculates the distance between adjacent points to obtain the side length data, calculates the geometric features such as the dial diameter and the shell depth based on the side length data, and then calculates the height difference between each grid point and the surrounding adjacent points to obtain the surface morphological characteristics, finds the area with a larger height difference as the location of the concave and convex changes, and then analyzes the surface image to obtain the texture characteristics, marks the start and end coordinates of the scale lines, the center coordinates of the digital logo, and the rotation angle of the pointer, and finally counts the common surface areas between the components to obtain the structural characteristics, records the contact area of the dial and the shell, the installation gap, the positioning area of the pointer and the axis, the fitting gap and other assembly parameters, thereby completing the extraction of the three-dimensional model features.

[0108] S702: Use the geometric features and structural features to perform matching based on corresponding standard geometric features and standard structural features in a preset instrument library to obtain a first matching result.

[0109] Among them, the preset instrument library represents a data set that stores multiple standard instruments and their features. The standard geometric features represent the basic data such as the size value and shape parameters of each standard instrument in the instrument library. The standard structural features represent the assembly parameters, connection relationships and other assembly data of each standard instrument in the instrument library. The first matching result represents the standard instrument type with the smallest feature difference.

[0110] Specifically, the electronic device reads the feature data of all standard instruments in the preset instrument library, and calculates the feature difference between each standard instrument and the instrument to be identified. The calculation process includes calculating the size difference value using the geometric features such as the dial diameter and shell depth of the instrument to be identified and the standard geometric features, and calculating the assembly difference value using the structural features such as the contact area and fitting clearance of the instrument to be identified and the standard structural features. The geometric difference value and the structural difference value are then summed to obtain the total difference value, and finally the instrument type with the smallest total difference value is selected as the first matching result.

[0111] S703: Use the second texture feature to match the corresponding standard texture feature in the first matching result to obtain a matching result.

[0112] Specifically, the electronic device compares the texture features of the standard instrument in the first matching result, counts whether the number of scale lines of the instrument to be identified is the same and whether the distribution spacing is consistent, counts whether the number of digital logos is the same and whether the displayed content is consistent, and confirms whether the current angle of the pointer is within the standard movement range. If the matching degree of the above three features is higher than the preset threshold, it is determined to be the same model of instrument, thereby obtaining the final matching result.

[0113] S106: Based on the matching result, the detection model corresponding to the instrument to be detected is called to perform data recognition on the instrument to be detected.

[0114] Specifically, the electronic device determines the specific model of the instrument to be tested based on the matching results, and calls the detection model corresponding to the model from the model library. The detection model contains identification parameters such as the scale spacing ratio, numerical mapping relationship, pointer reading rules, etc. of this type of instrument. Then, based on the current pointer angle of the instrument to be tested, combined with the scale distribution and numerical mapping relationship, the angular position of the pointer is converted into the actual display value, thereby completing the identification of the instrument data.

[0115] This embodiment also discloses an instrument data recognition system 20, referring to Figure 9 , specifically including: A multi-dimensional data acquisition module 21 is used to acquire multi-dimensional image data and structural parameters of the instrument to be tested, wherein the multi-dimensional image data includes point cloud data and image data, and the structural parameters include measuring range, scale distribution and display mode; A depth layer processing module 22 is used to perform depth layer processing on the multi-dimensional image data to extract instrument layer image data; An image enhancement processing module 23 is used to perform enhancement processing on the instrument layer image data to obtain final image data; A three-dimensional modeling generation module 24 is used to generate a three-dimensional model of the instrument to be inspected based on the final image data and the structural parameters; A feature matching analysis module 25 is used to extract key features of the three-dimensional model and match them with standard features in a preset instrument library to obtain a matching result; The intelligent detection calling module 26 is used to call the detection model corresponding to the instrument to be detected to perform data recognition on the instrument to be detected according to the matching result.

[0116] Optionally, the depth layering processing module 22 is also used to construct a depth mapping matrix based on the multidimensional image data, wherein the rows of the depth mapping matrix are the coordinates in the vertical direction of the image, the columns are the coordinates in the horizontal direction of the image, and the matrix elements are the depth values of the image pixels; according to the depth distribution characteristics in the depth mapping matrix, the multidimensional image data is layered to obtain a preliminary layering result, and the preliminary layering result is composed of at least one depth layer, and each depth layer includes an independent three-dimensional point cloud subset generated by depth threshold segmentation; each depth layer in the preliminary layering result is subjected to denoising and broken area repair processing to obtain an optimized layering result; the feature set of each depth layer in the optimized layering result is extracted, the similarity between the feature set of each depth layer and the preset standard feature set is calculated, and the depth layer with the highest similarity is selected as the instrument layer; the instrument layer is converted into a two-dimensional image to obtain instrument layer image data.

[0117] Optionally, the depth layering processing module 22 is also used to divide the data with depth values in the multidimensional image data in the same interval into the same layer according to a preset depth threshold and the depth value distribution characteristics in the depth mapping matrix, so as to obtain a preliminary hierarchical structure; based on the preliminary hierarchical structure, calculate the depth difference of adjacent point cloud data in each layer, and subdivide each layer based on the depth difference to obtain multiple candidate depth layers; based on a preset depth similarity judgment standard, merge the candidate depth layers to obtain a preliminary layering result.

[0118] Optionally, the depth stratification processing module 22 is also used to extract a feature set of each depth layer in the optimized stratification result, each feature set including a geometric shape feature and a depth distribution feature, and the depth distribution feature is a distribution feature obtained by statistics of the depth value; each feature in each feature set is compared with the corresponding feature in the standard feature set to determine the initial score corresponding to each feature; based on the initial score corresponding to each feature and the corresponding preset weight, the similarity score of each feature set is determined; and the depth layer with the highest similarity score is selected as the instrument layer.

[0119] Optionally, the image enhancement processing module 23 is also used to perform illumination compensation on the instrument layer image data to obtain first image data; perform edge sharpening processing on the first image data to obtain second image data; and perform corresponding area enhancement on the second image data in combination with the scale distribution to obtain final image data.

[0120] Optionally, the three-dimensional modeling generation module 24 is also used to construct an initial three-dimensional model based on the point cloud data; extract the first texture feature in the final image data; construct constraint conditions according to the measuring range and the display mode; align the initial three-dimensional model with the basic model with the highest matching degree in the preset instrument basic template library to obtain a registered three-dimensional model; optimize the registered three-dimensional model in combination with the texture feature and the constraint conditions to obtain a three-dimensional model.

[0121] Optionally, the feature matching analysis module 25 is also used to extract the geometric features, second texture features and structural features of the three-dimensional model; use the geometric features and the structural features to match the corresponding standard geometric features and standard structural features in the preset instrument library to obtain a first matching result; use the second texture features to match the corresponding standard texture features in the first matching result to obtain a matching result.

[0122] It should be noted that the above embodiments provide devices that implement their functions using only the division of the above functional modules as examples. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the device and method embodiments provided in the above embodiments are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0123] This embodiment also discloses an electronic device 900, referring to Figure 10 The electronic device may include: at least one processor 901 , at least one communication bus 902 , a user interface 903 , a network interface 904 , and at least one memory 905 .

[0124] The communication bus 902 is used to implement the connection and communication between these components.

[0125] The user interface 903 may include a display screen (Display) and a camera (Camera). Optional user interfaces may also include a standard wired interface and a wireless interface.

[0126] The network interface 904 may optionally include a standard wired interface or a wireless interface (such as a WI-FI interface).

[0127] Processor 901 may include one or more processing cores. The processor utilizes various interfaces and circuits to connect various components within the server. It executes instructions, programs, code sets, or instruction sets stored in memory, and accesses data stored in memory to perform various server functions and process data. Optionally, the processor may be implemented using at least one of the following hardware forms: a digital signal processing (DSP), a field-programmable gate array (FPGA), or a programmable logic array (PLA). The processor may integrate one or a combination of a central processing unit (CPU), a graphics processing unit (GPU), and a modem. The CPU primarily processes the operating system, user interface, and application programs; the GPU is responsible for rendering and drawing content displayed on the display; and the modem handles wireless communications. It is understood that the modem may also be implemented as a separate chip, rather than integrated into the processor.

[0128] Memory 905 may include random access memory (RAM) or read-only memory (ROM). Optionally, the memory may include non-transitory computer-readable storage medium. The memory may be used to store instructions, programs, code, code sets, or instruction sets. The memory may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, sound playback function, image playback function, etc.), instructions for implementing each of the aforementioned method embodiments, etc.; the data storage area may store data related to each of the aforementioned method embodiments, etc. The memory may also optionally be at least one storage device located remotely from the aforementioned processor. As shown in the figure, the memory, as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an application program for a meter data recognition method.

[0129] exist Figure 10 In the electronic device shown, the user interface is mainly used to provide an input interface for the user and obtain data input by the user; and the processor can be used to call an application program storing a meter data recognition method in the memory. When executed by one or more processors, the electronic device executes one or more methods in the above embodiments.

[0130] It should be noted that for the aforementioned method embodiments, for simplicity of description, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required for this application.

[0131] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely schematic, such as the division of units, which is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some service interface, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0133] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0134] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0135] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of this application, or the portion that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the various embodiments of the method of this application. The aforementioned memory includes various media that can store program code, such as USB flash drives, mobile hard drives, magnetic disks, or optical disks.

[0136] The above is only an exemplary embodiment of the present disclosure and cannot be used to limit the scope of the present disclosure. That is, any equivalent changes and modifications made according to the teachings of the present disclosure are still within the scope of the present disclosure. After considering the disclosure of the specification, those skilled in the art will easily think of other embodiments of the present disclosure. This application is intended to cover any variations, uses or adaptive changes of the present disclosure, which follow the general principles of the present disclosure and include common knowledge or customary technical means in the technical field that are not recorded in the present disclosure. The description and examples are to be regarded as exemplary only, and the scope and spirit of the present disclosure are defined by the claims.

Claims

1. A method for identifying instrument data, characterized in that: The method comprises: Collecting multi-dimensional image data and structural parameters of the instrument to be tested, wherein the multi-dimensional image data includes point cloud data and image data, and the structural parameters include measuring range, scale distribution and display mode; Performing depth layering processing on the multi-dimensional image data to extract instrument layer image data; Performing enhancement processing on the instrument layer image data to obtain final image data; generating a three-dimensional model of the instrument to be inspected based on the final image data and the structural parameters; Extracting key features of the three-dimensional model and matching them with standard features in a preset instrument library to obtain matching results; According to the matching result, the detection model corresponding to the instrument to be detected is called to perform data recognition on the instrument to be detected.

2. The method according to claim 1, characterized in that The performing depth layering processing on the multi-dimensional image data to obtain instrument layer image data specifically includes: Based on the multidimensional image data, a depth mapping matrix is constructed, wherein the rows of the depth mapping matrix are the vertical coordinates of the image, the columns are the horizontal coordinates of the image, and the matrix elements are the depth values of the image pixels; performing layered processing on the multidimensional image data according to the depth distribution characteristics in the depth mapping matrix to obtain a preliminary layered result, wherein the preliminary layered result is composed of at least one depth layer, each of the depth layers including an independent three-dimensional point cloud subset generated by depth threshold segmentation; Performing denoising and broken area repair processing on each depth layer in the preliminary stratification result to obtain an optimized stratification result; Extracting the feature set of each depth layer in the optimized stratification result, calculating the similarity between the feature set of each depth layer and the preset standard feature set, and selecting the depth layer with the highest similarity as the instrument layer; The instrument layer is converted into a two-dimensional image to obtain instrument layer image data.

3. The method according to claim 2, characterized in that The multidimensional image data is subjected to layered processing according to the depth distribution characteristics in the depth mapping matrix to obtain a preliminary layered result, wherein the preliminary layered result is composed of at least one depth layer, and the depth layer is an independent three-dimensional point cloud subset generated by depth threshold segmentation, specifically including: According to a preset depth threshold and the depth value distribution characteristics in the depth mapping matrix, data with depth values in the multidimensional image data in the same interval are divided into the same layer to obtain a preliminary hierarchical structure; Based on the preliminary hierarchical structure, calculating the depth difference of adjacent point cloud data in each layer, and subdividing each layer based on the depth difference to obtain a plurality of candidate depth layers; Based on a preset depth similarity judgment standard, the candidate depth layers are merged to obtain a preliminary stratification result.

4. The method according to claim 2, characterized in that The extracting of the feature set of each depth layer in the optimized stratification result, calculating the similarity between the feature set of each depth layer and the standard feature set, and selecting the depth layer with the highest similarity as the instrument layer specifically includes: Extracting a feature set of each depth layer in the optimized stratification result, each feature set including a geometric shape feature and a depth distribution feature, wherein the depth distribution feature is a distribution feature obtained by statistics of depth values; Comparing each feature in each feature set with the corresponding feature in the standard feature set to determine an initial score corresponding to each feature; Determining a similarity score for each of the feature sets based on the initial score corresponding to each of the features and the corresponding preset weight; The depth layer with the highest similarity score is selected as the instrument layer.

5. The method according to claim 1, wherein The enhancing process of the instrument layer image data to obtain the final image data specifically includes: Performing illumination compensation on the instrument layer image data to obtain first image data; performing edge sharpening processing on the first image data to obtain second image data; The corresponding region of the second image data is enhanced in combination with the scale distribution to obtain final image data.

6. The method according to claim 1, characterized in that Generating a three-dimensional model of the instrument to be inspected based on the final image data and the structural parameters specifically includes: constructing an initial three-dimensional model based on the point cloud data; extracting a first texture feature from the final image data; Constructing constraint conditions according to the measuring range and the display mode; Registering the initial three-dimensional model with the basic model with the highest matching degree in a preset instrument basic template library to obtain a registered three-dimensional model; The registered three-dimensional model is optimized in combination with the texture features and the constraint conditions to obtain a three-dimensional model.

7. The method according to claim 1, characterized in that Extracting the key features of the three-dimensional model and matching them with the standard features in the preset instrument library to obtain a matching result specifically includes: Extracting geometric features, second texture features and structural features of the three-dimensional model; Using the geometric features and the structural features to match corresponding standard geometric features and standard structural features in a preset instrument library to obtain a first matching result; The second texture feature is matched with the corresponding standard texture feature in the first matching result to obtain a matching result.

8. An instrument data recognition system, characterized in that: include: A multi-dimensional data acquisition module is used to acquire multi-dimensional image data and structural parameters of the instrument to be tested, wherein the multi-dimensional image data includes point cloud data and image data, and the structural parameters include measuring range, scale distribution and display mode; A depth layer processing module, configured to perform depth layer processing on the multi-dimensional image data and extract instrument layer image data; An image enhancement processing module is used to perform enhancement processing on the instrument layer image data to obtain final image data; A three-dimensional modeling generation module, configured to generate a three-dimensional model of the instrument to be inspected based on the final image data and the structural parameters; A feature matching analysis module is used to extract key features of the three-dimensional model and match them with standard features in a preset instrument library to obtain matching results; The intelligent detection calling module is used to call the detection model corresponding to the instrument to be detected to perform data recognition on the instrument to be detected according to the matching result.

9. An electronic device, characterized in that: The electronic device comprises a processor, a memory, a user interface and a network interface, wherein the memory is used to store instructions, the user interface and the network interface are both used to communicate with other devices, and the processor is used to execute the instructions stored in the memory so that the electronic device executes the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores instructions, and when the instructions are executed, the method according to any one of claims 1 to 7 is executed.

Images