Method and system for intelligent analysis of instruments based on video images

Abstract

The application relates to a video image-based instrument intelligent analysis method and system. The method comprises the following steps: performing preprocessing on the basis of an instrument video image, the preprocessing comprising illumination contrast parameter adjustment, the illumination contrast parameter adjustment enhancing the visual effect and definition of the image. Then, an image segmentation operation is performed on the basis of the preprocessed instrument image, the image segmentation operation being used to accurately locate a feature region to be recognized and improve the accuracy of instrument key features. Furthermore, an instrument feature recognition model is used to extract instrument features from the instrument region segmentation image, when the instrument type is a pointer instrument, pointer positioning refinement and scale calibration are performed on the basis of the instrument key features, calibration data is obtained, and instrument reading calculation is performed on the basis of the calibration data to determine the instrument reading. The instrument data recognition mode combining the classical image processing technology and the convolutional neural network model features improves the accuracy of instrument data reading.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of instrument detection, and in particular to an instrument intelligent analysis method and system based on video images. BACKGROUND

[0002] In many fields such as industrial production, transportation, and environmental monitoring, instruments are key equipment parameter indicating tools. The accuracy and real-time performance of instrument readings are crucial for ensuring stable system operation, preventing safety accidents, and optimizing production efficiency. Traditional instrument readings rely on manual observation and recording, which is not only time-consuming and labor-intensive, but also prone to inaccurate data due to human factors, thereby affecting subsequent data analysis and decision-making.

[0003] With the rapid development of computer vision technology and deep learning algorithms, instrument intelligent analysis methods have emerged to achieve fast and accurate identification and recording of instrument readings through automation and intelligence. However, related instrument intelligent analysis methods are only applicable to specific types of instruments in simple scenarios, and the recognition accuracy needs to be improved when dealing with complex scenarios such as light changes, making it difficult to meet the demand for high-precision instrument data collection.

[0004] Therefore, how to improve the recognition accuracy of instruments is a problem that needs to be solved by those skilled in the art. SUMMARY

[0005] The purpose of the present application is to provide an instrument intelligent analysis method and system based on video images to solve at least one of the above technical problems.

[0006] The above invention purpose of the present application is realized by the following technical scheme:

[0007] In a first aspect, the present application provides an instrument intelligent analysis method based on video images, which adopts the following technical scheme:

[0008] An instrument intelligent analysis method based on video images, comprising:

[0009] Obtaining an instrument video image, pre-processing based on the instrument video image to obtain a pre-processed instrument image, wherein the pre-processing includes filtering and denoising, grayscale conversion, and illumination contrast parameter adjustment;

[0010] Performing image segmentation operation based on the pre-processed instrument image to obtain an instrument region segmentation map, wherein the instrument region segmentation map is used to partition different functional regions in the instrument;

[0011] obtain an instrument feature recognition model, perform instrument feature extraction on the instrument region segmentation image by using the instrument feature recognition model, and determine instrument key features, wherein the instrument key features include pointer position features and scale distribution features;

[0012] When the instrument type is a pointer instrument, perform pointer positioning refinement and scale calibration based on the instrument key features, obtain calibration data, and perform instrument reading calculation based on the calibration data to determine the instrument reading.

[0013] By adopting the above technical solution, the instrument video image is preprocessed to obtain a preprocessed instrument image. The preprocessing includes illumination contrast parameter adjustment. The illumination contrast parameter adjustment is performed on the instrument video image, so that the brightness and contrast of the processed instrument image reach a suitable range, and the visual effect and clarity of the image are enhanced. Then, image segmentation is performed based on the preprocessed instrument image to obtain an instrument region segmentation image. The image segmentation operation is used to accurately locate the feature region to be recognized, thereby improving the accuracy of the instrument key features. Furthermore, the instrument feature recognition model is used to perform instrument feature extraction on the instrument region segmentation image to determine the instrument key features. After that, pointer positioning refinement and scale calibration are performed based on the instrument key features to obtain calibration data, and instrument reading calculation is performed based on the calibration data to determine the instrument reading. The combination of the classical image processing technology and the convolutional neural network model feature extraction for data recognition improves the accuracy of instrument data reading.

[0014] In a preferred example, the application can be further configured to:

[0015] store the instrument reading into a data monitoring database, wherein the data monitoring database is used to store instrument readings corresponding to different nodes of each instrument;

[0016] extract an instrument reading sequence corresponding to a target instrument from the data monitoring database, wherein the target instrument is any instrument stored in the data monitoring database, and the instrument reading sequence is composed of a plurality of instrument readings arranged in time sequence;

[0017] perform reading prediction based on the instrument reading sequence to determine prediction data, and perform preventive evaluation based on the prediction data to obtain preventive maintenance information.

[0018] In a preferred example, the application can be further configured to:

[0019] acquire light information collected by a light sensor, wherein the light sensor is arranged at a preset position of the instrument and is configured to detect light intensity and light conditions around the instrument in real time;

[0020] perform working parameter analysis based on the light information, determine working parameters corresponding to the image acquisition device, and send the working parameters to the image acquisition device to control the image acquisition device to perform image acquisition according to the working parameters, wherein the working parameters include exposure time, shutter speed, white balance speed, and ISO value.

[0021] In a preferred example, the application can be further configured to, after acquiring the light information collected by the light sensor, further include:

[0022] perform light condition evaluation based on the light information, and determine a light condition evaluation result, wherein the light condition evaluation result includes meeting image acquisition requirements and not meeting image acquisition requirements;

[0023] when the light condition evaluation result is not meeting image acquisition requirements, perform light compensation analysis based on the light information, and determine a light compensation operation, wherein the light compensation operation includes increasing light sources and adjusting light direction.

[0024] In a preferred example, the application can be further configured to, after performing instrument reading calculation based on the calibration data to determine the instrument reading, further include:

[0025] acquire instrument environment data, perform environment interference analysis based on the instrument environment data, and determine an environment interference analysis result, wherein the environment interference analysis result includes existing interference and no interference;

[0026] when the environment interference analysis result is existing interference, determine a target sensor corresponding to the type of the instrument reading, acquire industrial data collected by the target sensor, and update the instrument reading based on the industrial data.

[0027] In a preferred example, the application can be further configured to, after performing pointer positioning refinement and scale calibration based on the instrument key features to obtain calibration data, include:

[0028] perform pointer positioning refinement on the pointer position feature in the instrument key features using an edge detection algorithm to determine a pointer tip position;

[0029] perform scale calibration on the scale distribution feature in the instrument key features using template matching and regression analysis to determine scale distribution information;

[0030] integrate the pointer tip position and the scale distribution information to obtain calibration data.

[0031] In a second aspect, the present application provides a video image-based instrument intelligent analysis system, which adopts the following technical solution:

[0032] A preprocessing module is configured to acquire an instrument video image, perform preprocessing based on the instrument video image, and obtain a preprocessed instrument image, wherein the preprocessing includes filtering and denoising, grayscale conversion, and illumination contrast parameter adjustment.

[0033] An image segmentation module is configured to perform an image segmentation operation based on the preprocessed instrument image, and obtain an instrument region segmentation map, wherein the instrument region segmentation map is used to partition different functional regions in the instrument.

[0034] A feature extraction module is configured to acquire an instrument feature recognition model, perform instrument feature extraction on the instrument region segmentation map by using the instrument feature recognition model, and determine instrument key features, wherein the instrument key features include pointer position features and scale distribution features.

[0035] A refinement and calibration module is configured to, when the instrument type is a pointer instrument, perform pointer positioning refinement and scale calibration based on the instrument key features, obtain calibration data, perform instrument reading calculation based on the calibration data, and determine instrument readings.

[0036] In a third aspect, the present application provides an electronic device, which adopts the following technical solution:

[0037] At least one processor;

[0038] A memory;

[0039] At least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one processor, and the at least one application program is configured to execute the above-mentioned video image-based instrument intelligent analysis method.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0041] A computer-readable storage medium having a computer program stored thereon, when the computer program is executed in a computer, the computer is caused to execute the above-mentioned video image-based instrument intelligent analysis method.

[0042] In summary, the present application has at least one of the following beneficial technical effects:

[0043] The instrument video image is preprocessed to obtain a preprocessed instrument image. The preprocessing includes adjusting the light contrast parameters, and adjusting the light contrast parameters of the instrument video image, so that the brightness and contrast of the processed instrument image reach a suitable range, thereby enhancing the visual effect and definition of the image. Then, an image segmentation operation is performed based on the preprocessed instrument image to obtain an instrument region segmentation image. The image segmentation operation is used to accurately locate the feature region to be recognized, thereby improving the accuracy of the instrument key features. Furthermore, an instrument feature recognition model is used to extract instrument features from the instrument region segmentation image to determine the instrument key features. After that, pointer positioning refinement and scale calibration are performed based on the instrument key features to obtain calibration data, and instrument reading calculation is performed based on the calibration data to determine the instrument reading. The data recognition is performed by combining the classical image processing technology and the convolutional neural network model feature extraction, thereby improving the accuracy of the instrument data reading.

[0044] The instrument reading sequence corresponding to the target instrument is extracted from the data monitoring database. Then, reading prediction is performed based on the instrument reading sequence to determine prediction data, and preventive evaluation is performed based on the prediction data to obtain preventive maintenance information. The instrument reading is usually closely related to the running state of the equipment. Therefore, performing the reading prediction and preventive evaluation operation helps to discover and handle potential problems in a timely manner, reduces the occurrence of equipment failure or accidents to a certain extent, and improves the reliability of the equipment. BRIEF DESCRIPTION OF DRAWINGS

[0045] Fig. 1 is a flowchart of an instrument intelligent analysis method based on a video image according to an embodiment of the present application;

[0046] Fig. 2 is a structural diagram of an instrument intelligent analysis system based on a video image according to an embodiment of the present application;

[0047] Fig. 3 is a structural diagram of an electronic device according to an embodiment of the present application. DETAILED DESCRIPTION

[0048] The following Figs. 1 to 3 The present application is further described in detail.

[0049] The present embodiment is only an explanation of the present application, and is not a limitation of the present application. Those skilled in the art can make modifications to the present embodiment without creative contribution after reading the present specification, but as long as the modifications are within the scope of the present application, they are protected by the patent law.

[0050] To make the purposes, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are some but not all of the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application. It should be noted that, in optional embodiments of the present application, the object information and other related data involved need to be authorized or agreed by the object when the embodiments of the present application are applied to specific products or technologies, and the collection, use, and processing of the related data need to comply with relevant laws, regulations, and standards of the country and region. That is, the data related to the object in the embodiments of the present application need to be obtained with the authorization and agreement of the object, the authorization and agreement of the relevant department, and the compliance with the relevant laws, regulations, and standards of the country and region. If the embodiments involve personal information, the consent of the individual is required for obtaining the personal information, and the separate consent of the information subject is required for obtaining sensitive information, and the embodiments also need to be implemented with the authorization and agreement of the object.

[0051] In addition, the term "and / or" in this paper is only a description of the association relationship between the associated objects, which means that there can be three relationships, for example, A and / or B can represent the following three cases: A exists alone, A and B exist together, and B exists alone. In addition, the character " / " in this paper generally represents an "or" relationship between the associated objects before and after it unless otherwise specified.

[0052] The embodiments of the present application will be described in further detail below with reference to the drawings of the specification.

[0053] The embodiments of the present application provide a kind of instrument intelligent analysis method based on video image, it is executed by electronic equipment, which can be server also can be terminal equipment, wherein, the server can be independent physical server, it can also be the server cluster or distributed system formed by multiple physical servers, it can also be the cloud server providing cloud computing service.Terminal equipment can be smart phone, tablet computer, notebook computer, desktop computer etc., but it is not limited to this, the terminal equipment and server can be connected directly or indirectly by wired or wireless communication mode, the embodiments of the present application do not limit here, such as Fig. 1 As shown in the figure, the method comprises steps S101, S102, S103 and S104, wherein:

[0054] Step S101: obtaining instrument video image, pre-processing based on instrument video image, to obtain pre-processed instrument image, wherein, pre-processing includes: filtering denoising, gray scale conversion and illumination contrast parameter adjustment.

[0055] For the embodiments of the present application, in order to solve the defect that the instrument intelligent analysis method in the related art cannot realize high-precision data reading under a complex light change scene, the light contrast parameters of the instrument video image are adjusted, so that the brightness and contrast of the processed instrument image reach a suitable range, and the visual effect and definition of the image are enhanced. After that, the image segmentation operation is performed on the preprocessed instrument image, so that when the instrument feature recognition model extracts the instrument features from the instrument region segmentation map, it can accurately locate the feature region to be recognized, and the accuracy of the instrument key features is improved. At the same time, the pointer positioning and refinement and scale calibration of the instrument key features extracted by the convolutional neural network model are performed by using the classical image processing technology, and the instrument data recognition method combining the two methods improves the accuracy of instrument data reading.

[0056] Specifically, a high-definition image acquisition device is deployed near the instrument, and preferably the image acquisition device is a high-performance camera. The deployment position should ensure that the camera can clearly capture the image of the instrument. Therefore, the image acquisition device can record the dial video of the instrument and ensure that the video quality is clear and stable. The electronic device is connected to the image acquisition device near the instrument through a wireless manner, so that the electronic device can obtain the instrument video image from the image acquisition device.

[0057] In order to improve the definition and quality of the instrument image and improve the efficiency of subsequent instrument data reading, the instrument video image is preprocessed to obtain a preprocessed instrument image, and the preprocessing includes but is not limited to filtering denoising, grayscale conversion and light contrast parameter adjustment. Through filtering denoising, various noises generated in the collection and transmission process of the instrument video image are effectively reduced or eliminated, the definition and quality of the image are improved, and more accurate input is provided for subsequent processing. Since a color image contains multiple color channels, the data amount is large and the processing is relatively complex, while a grayscale image only contains brightness information, the data amount is small and the processing speed is faster. Therefore, performing grayscale conversion can reduce the computational complexity of subsequent processing and improve the processing efficiency. At the same time, the light conditions of the instrument video image may vary due to the environment, resulting in uneven brightness and contrast of the image, which affects the visual effect of the image and the accuracy of subsequent processing to some extent. Therefore, by adjusting the light contrast parameters, the brightness and contrast of the image reach a suitable range, the visual effect and definition of the image are enhanced, and more accurate input is provided for subsequent processing.

[0058] Step S102: performing an image segmentation operation based on the preprocessed instrument image to obtain an instrument region segmentation map, wherein the instrument region segmentation map is used to partition different functional regions in the instrument.

[0059] For the embodiments of the present application, based on the pre-processed instrument image, an image segmentation method is selected, which includes but is not limited to: threshold-based image segmentation method, region-based image segmentation method, edge-based image segmentation method and machine learning-based image segmentation method. Different image segmentation methods have different characteristics, and the characteristics of the suitable instrument image will also be different, therefore, the electronic device pre-stores the correspondence between the instrument image characteristics and the image segmentation method, which is used to match the most suitable image segmentation method for the pre-processed instrument image. For example, the threshold-based image segmentation method is suitable for the case where the target and background gray values in the instrument image are obviously different; the region-based image segmentation method is suitable for the case where the target region and the background region in the instrument image have obvious differences in color, texture, etc.; the edge-based image segmentation method is suitable for the case where the edges between the target region and the background region in the instrument image are clear and obvious; the machine learning-based image segmentation method is suitable for the case where the instrument image is complex and the differences between the target region and the background region are not obvious.

[0060] Further, based on the selected image segmentation method, image segmentation operation is performed on the pre-processed instrument image to obtain an instrument region segmentation map, in which different functional regions are divided into different blocks, such as speedometer region, fuel gauge region, tachometer region, temperature gauge region, pressure gauge region, etc. By performing the image segmentation operation, not only can the feature region to be recognized be accurately located, and other irrelevant information be ignored, to reduce the computational amount of subsequent feature extraction and improve the accuracy of instrument key features; but also the complex instrument image can be decomposed into simpler sub-problems, reducing the complexity of subsequent instrument feature extraction.

[0061] Step S103: Obtain an instrument feature recognition model, use the instrument feature recognition model to perform instrument feature extraction on the instrument region segmentation map, and determine instrument key features, wherein the instrument key features include pointer position features and scale distribution features.

[0062] For the embodiments of the present application, the instrument feature recognition model is pre-stored in the electronic device, which is obtained by training a convolutional neural network model using a large number of training samples. The convolutional neural network model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and the like, to realize effective feature extraction of the instrument image. The training samples are instrument reading labels and corresponding instrument region segmentation maps. In the process of training the convolutional neural network model using the training samples, the parameters of the model need to be continuously optimized to improve its recognition ability of instrument key features. At the same time, the model needs to be evaluated regularly during the training process to check its recognition performance. If the performance is not good, the model needs to be further optimized, such as adjusting the network structure, increasing the training data, and the like. When the recognition performance meets the requirements, the trained model is used as the instrument feature recognition model.

[0063] Further, the instrument region segmentation map to be recognized is input into the instrument feature recognition model. The instrument feature recognition model extracts instrument features for each functional region block in the instrument region segmentation map, determines instrument key features, which include pointer position features and scale distribution features. The pointer position features are used to represent the specific position pointed by the pointer in the instrument, and the scale distribution features are used to represent the numerical range and accuracy of the scale on the instrument, and the like. Of course, for digital display type instruments, the instrument key features can also include display numbers and symbols. When the instrument type is a digital display type instrument, the complete instrument reading is obtained based on the combination of the display numbers and corresponding symbols in the instrument key features.

[0064] Step S104: When the instrument type is a pointer type instrument, the pointer positioning refinement and scale calibration are performed based on the instrument key features, to obtain calibration data, and the instrument reading is calculated based on the calibration data to determine the instrument reading.

[0065] For the embodiments of the present application, in the actual instrument feature extraction process, the instrument image may be affected by factors such as illumination change, noise interference, and shooting angle, which may cause certain errors in the pointer position and scale distribution extracted by the instrument feature recognition model, and further affect the accuracy of the subsequent instrument reading. In order to further improve the accuracy of instrument reading recognition, the pointer positioning refinement and scale calibration are performed based on the instrument key features to obtain calibration data, that is, the image processing methods such as edge detection and morphological processing are used to refine the pointer position, and the methods such as template matching and regression analysis are used for scale calibration, so that the calibration data can meet the requirements of high precision and robustness in actual application. Further, based on the pointer tip position and scale distribution information in the calibration data, the angle of the pointer tip compared with a certain reference point (for example, the zero scale point of the scale disc of the instrument) is calculated, and then the calculated pointer angle is converted into the corresponding instrument reading according to the scale range and accuracy in the scale distribution information of the instrument.

[0066] It can be seen that in the embodiments of the present application, the instrument video image is preprocessed to obtain a preprocessed instrument image, the preprocessing includes illumination contrast parameter adjustment, and the illumination contrast parameter adjustment is performed on the instrument video image, so that the brightness and contrast of the processed instrument image reach a suitable range, and the visual effect and clarity of the image are enhanced. Then, an image segmentation operation is performed based on the preprocessed instrument image to obtain an instrument region segmentation map, and the image segmentation operation is used to accurately locate the feature region to be identified, and improve the accuracy of the instrument key features. Further, the instrument feature recognition model is used to extract the instrument features from the instrument region segmentation map to determine the instrument key features, and then the pointer positioning refinement and scale calibration are performed based on the instrument key features to obtain calibration data, and the instrument reading is calculated based on the calibration data to determine the instrument reading. The data recognition is performed by combining the classical image processing technology and the convolutional neural network model feature extraction, and the instrument data recognition mode combining the two modes improves the accuracy of instrument data reading.

[0067] Further, in order to timely discover and handle potential problems, reduce the occurrence of equipment failure or accident, and improve the reliability of the equipment, in the embodiments of the present application, after the instrument reading is calculated based on the calibration data to determine the instrument reading, the following steps are further included:

[0068] The instrument reading is stored in a data monitoring database, wherein the data monitoring database is used to store the instrument readings corresponding to different nodes of each instrument;

[0069] The instrument reading sequence corresponding to a target instrument is extracted from the data monitoring database, wherein the target instrument is any one of the instruments stored in the data monitoring database, and the instrument reading sequence is composed of a plurality of instrument readings arranged in time sequence;

[0070] Based on the meter reading sequence, reading prediction is performed, prediction data is determined, and based on the prediction data, preventive evaluation is performed to obtain preventive maintenance information.

[0071] For the embodiments of the present application, the meter reading is usually closely related to the running state of the equipment. By storing the meter reading into the data monitoring database, centralized management of the data is achieved, which not only helps subsequent data analysis and processing, but also facilitates historical data tracing and querying. Therefore, the meter reading is format-converted to convert the meter reading into a format suitable for storage, such as a number, a string, or a specific data structure, and necessary metadata, such as a timestamp, a meter ID, a reading type, etc., is added for subsequent data querying and analysis. Further, from the data monitoring database, a meter reading sequence corresponding to a target meter is extracted, the target meter being any meter stored in the data monitoring database, the meter reading sequence consisting of a plurality of meter readings arranged in chronological order, the meter reading sequence being capable of reflecting the change trend of the readings in the target meter. Then, based on the meter reading sequence, reading prediction is performed, prediction data is determined, and based on the prediction data, preventive evaluation is performed to obtain preventive maintenance information. The meter reading is usually closely related to the running state of the equipment, and therefore, performing reading prediction and preventive evaluation operation helps to discover and handle potential problems in a timely manner, reduces the occurrence of equipment failure or accident to a certain extent, and thus improves the reliability of the equipment.

[0072] There are various specific implementation manners for the reading prediction, and the embodiments of the present application are not limited again. In an implementable manner, the instrument reading sequence is analyzed to identify its long-term trend (for example, linear growth, exponential growth, etc.), and the identified trend is used to predict future readings; it is checked whether the instrument reading sequence has periodic changes (for example, daily, weekly, monthly periodic fluctuations), and the future instrument readings are predicted according to the periodic law. There are various specific implementation manners for the preventive evaluation, and the embodiments of the present application are not limited again. In an implementable manner, the electronic device stores evaluation standards corresponding to various types of instruments respectively. The evaluation standards are corresponding standards formulated according to the types, purposes and working environments of the instruments, and the standards include but are not limited to: reading range, change rate, abnormal mode, etc. Then, according to the evaluation standards corresponding to the instruments, the reading threshold is determined, which is used to judge whether the predicted reading is within the normal range and whether preventive maintenance measures need to be taken. Further, the predicted data is compared and analyzed with the set reading threshold to judge whether the instrument reading is likely to exceed the normal range or appear abnormal. When it is analyzed and determined that the instrument reading is likely to exceed the normal range, the preventive maintenance information is determined based on the instrument abnormal reading dimension, wherein the preventive maintenance information includes but is not limited to: maintenance time, maintenance content, required materials, maintenance personnel. The maintenance content can be the maintenance of the instrument or the maintenance of the instrument monitored equipment. The specific maintenance object can be selected according to the actual situation, and the embodiments of the present application are not limited again.

[0073] It can be seen that in the embodiments of the present application, the instrument reading sequence corresponding to the target instrument is extracted from the data monitoring database. Then, the reading prediction is performed based on the instrument reading sequence, the predicted data is determined, and the preventive evaluation is performed based on the predicted data to obtain the preventive maintenance information. The instrument reading is usually closely related to the running state of the equipment. Therefore, performing the reading prediction and the preventive evaluation operation helps to discover and handle potential problems in time, reduces the occurrence of equipment failure or accident to a certain extent, and improves the reliability of the equipment.

[0074] Further, in order to ensure that clear instrument images can be collected under various complex lighting environments and improve the identification accuracy of subsequent instrument readings, in the embodiments of the present application, before acquiring the instrument video image, the following steps are further included:

[0075] Acquiring light information collected by a light sensor, wherein the light sensor is deployed at a preset position of the instrument and is used to detect the light intensity and lighting conditions of the environment around the instrument in real time;

[0076] The working parameters are analyzed based on the illumination information, the working parameters corresponding to the image acquisition device are determined, and the working parameters are sent to the image acquisition device to control the image acquisition device to acquire images according to the working parameters, wherein the working parameters include an exposure time, a shutter speed, a white balance speed, and an ISO value.

[0077] For the embodiments of the present application, the instrument can be in various complex illumination conditions. In order to ensure that a clear instrument image can be acquired under various complex illumination environments, the working parameters of the image acquisition device are dynamically adjusted based on the illumination conditions of the environment where the instrument is located, which significantly reduces problems such as image blur, overexposure, or underexposure caused by light problems, thereby improving the recognition accuracy of subsequent instrument reading.

[0078] Specifically, a light sensor is pre-deployed at a preset position of the instrument. Preferably, a high-precision and high-sensitivity light sensor is selected. Such a sensor usually has a sensitive light-sensitive acquisition device inside and is equipped with components such as a light filter and a cosine corrector to ensure the accuracy of measurement. The preset position should be able to fully reflect the light intensity and illumination conditions of the environment around the instrument. The electronic device and the light sensor are connected through wireless transmission. Therefore, the illumination information is obtained from the light sensor through wireless transmission. The illumination information includes but is not limited to illumination intensity, illumination color, light direction, and light intensity change.

[0079] Furthermore, the electronic device pre-stores a mapping relationship between the illumination information and the working parameters of the image acquisition device. The mapping relationship is the best working parameter setting determined by a large number of illumination information and working parameter combinations through testing and analysis. Of course, machine learning, deep learning, and other algorithms can be used to optimize the mapping relationship to improve the accuracy and efficiency of working parameter analysis. Then, the working parameters are analyzed using the illumination information and the mapping relationship to determine the working parameters corresponding to the image acquisition device. The working parameters are the parameters that can most clearly highlight the instrument video captured by the image acquisition device under the current illumination information. Finally, the working parameters are sent to the image acquisition device to control the image acquisition device to acquire images according to the working parameters.

[0080] As can be seen, in the embodiments of the present application, in order to ensure that a clear instrument image can be acquired under various complex illumination environments, the illumination information collected by the light sensor is obtained, the working parameters are analyzed based on the illumination information, the working parameters corresponding to the image acquisition device are determined, and the working parameters are sent to the image acquisition device to control the image acquisition device to acquire images according to the working parameters. The working parameters of the image acquisition device are dynamically adjusted, which significantly reduces problems such as image blur, overexposure, or underexposure caused by light problems, thereby improving the recognition accuracy of subsequent instrument reading.

[0081] Further, in order to enable the image acquisition device to work under the best lighting condition and improve the image acquisition quality, in the embodiment of the present application, after the lighting information collected by the light sensor is acquired, the following steps are further included:

[0082] perform lighting condition evaluation based on the lighting information to determine a lighting condition evaluation result, wherein the lighting condition evaluation result includes: meeting the image acquisition requirement and not meeting the image acquisition requirement;

[0083] when the lighting condition evaluation result is not meeting the image acquisition requirement, perform light compensation analysis based on the lighting information to determine a light compensation operation, wherein the light compensation operation includes: increasing the light source and adjusting the light direction.

[0084] For the embodiment of the present application, in the actual working environment, not all lighting conditions meet the image acquisition requirement, and insufficient lighting or too strong light will cause image blur, color distortion and other problems, affecting the quality of the instrument video image and causing errors in the instrument reading. Therefore, in order to improve the image acquisition quality, perform lighting condition evaluation and automatically perform light compensation operation when the image acquisition requirement is not met, so that the image acquisition device can work under the best lighting condition.

[0085] Specifically, the pre-stored lighting condition evaluation standard in the electronic device is acquired, which is set according to the technical specifications and application requirements of the image acquisition device, including but not limited to: the range of lighting intensity, the appropriate value of color temperature, the limitation of light direction, etc. Further, multi-dimensional analysis is performed based on the lighting information, and the multi-dimensional analysis result is matched with the lighting condition evaluation standard, wherein the multi-dimensional analysis includes but is not limited to: lighting intensity distribution analysis, color temperature change analysis, and light direction stability analysis. When the multi-dimensional analysis result matches the lighting condition evaluation standard, it is determined that the lighting condition evaluation result meets the image acquisition requirement, otherwise, it is determined that the lighting condition evaluation result does not meet the image acquisition requirement.

[0086] When the lighting condition evaluation result meets the image acquisition requirement, the remaining operations do not need to be performed; when the lighting condition evaluation result does not meet the image acquisition requirement, light compensation analysis is performed based on the lighting information to determine a light compensation operation, which includes: increasing the light source and adjusting the light direction. For light compensation analysis, key parameter evaluation is performed based on the lighting information and the lighting condition evaluation standard to determine the gap between the current lighting condition and the standard. If the lighting intensity is insufficient, it is determined that the light compensation operation is to increase the light source; if the light direction is not appropriate, it is determined that the light compensation operation is to adjust the light direction, i.e., the position of the light source can be adjusted, a light board can be used to guide the light, etc.

[0087] It can be seen that, in the embodiment of the present application, the illumination condition is evaluated based on the illumination information to determine the illumination condition evaluation result. In order to improve the image acquisition quality, when the illumination condition evaluation result does not meet the image acquisition requirement, the light supplement analysis is performed based on the illumination information to determine the light supplement operation, so that the image acquisition device can work under the best illumination condition.

[0088] Further, in order to improve the accuracy and reliability of the instrument reading, in the embodiment of the present application, after the instrument reading is calculated based on the calibration data, the instrument reading includes:

[0089] The instrument environment data is acquired, and the environmental interference analysis is performed based on the instrument environment data to determine the environmental interference analysis result, wherein the environmental interference analysis result includes: interference exists and no interference;

[0090] When the environmental interference analysis result is interference exists, the corresponding target sensor is determined based on the type of the instrument reading, and the industrial data collected by the target sensor is acquired, and the instrument reading is updated based on the industrial data.

[0091] For the embodiment of the present application, since the instrument reading may be affected by various factors, in one case, the instrument zero drift caused by temperature change, the instrument deformation caused by pressure change, etc.; in another case, in some industrial or scientific environment, the instrument may be under extreme temperature, pressure or other physical conditions; under these conditions, only through the video image to read the instrument will cause the reading to appear deviation or instability, thereby affecting the accuracy and reliability of the data. Therefore, when the instrument is in the environment which has interference to the reading, the video image and the sensor acquisition are combined to read the instrument value, so as to improve the accuracy and reliability of the instrument reading.

[0092] Specifically, a plurality of environmental sensors are deployed in the relevant environment where the instrument is located, including but not limited to: temperature sensor, pressure sensor, humidity sensor, etc., to monitor the environmental change in real time. The environmental sensor collects environmental data in real time and transmits it to the electronic device through a wireless way. Then, according to the characteristics and working environment of the instrument, an environmental interference identification model is established, which should be able to automatically judge whether there is a factor that interferes with the instrument reading based on the instrument environment data, that is, the interference threshold of each type of environmental parameter is set in the interference identification model. Further, the environmental interference identification model is used to analyze the environmental interference of the instrument environment data to determine the environmental interference analysis result, which includes: interference exists and no interference, that is, when at least one environmental data in the instrument environment data exceeds the interference threshold, it is determined that interference exists; otherwise, it is determined that no interference exists.

[0093] Further, when the environmental interference analysis result is that there is interference, a target sensor is determined based on the type of the instrument reading, and industrial data collected by the target sensor is acquired, and the instrument reading is updated based on the industrial data. For example, when the instrument reading is temperature, a high-precision temperature sensor is selected as the target sensor, and the industrial data collected by the target sensor is used to update the instrument reading, that is, the industrial data collected by the high-precision and accurate sensor is used to update the reading with deviation, thereby improving the accuracy and reliability of the instrument reading.

[0094] It can be seen that in the embodiment of the present application, instrument environment data is acquired, environmental interference analysis is performed based on the instrument environment data, and an environmental interference analysis result is determined. When the environmental interference analysis result is that there is interference, a target sensor is determined based on the type of the instrument reading, and industrial data collected by the target sensor is acquired, and the instrument reading is updated based on the industrial data. When the instrument is in an environment with interference to the reading, a combination of video images and sensor collection is used to read the instrument value, so as to improve the accuracy and reliability of the instrument reading.

[0095] Further, in order to reduce the positioning error caused by image blur or noise interference and improve the quality and reliability of the industrial data, in the embodiment of the present application, pointer positioning refinement and scale calibration are performed based on the instrument key features to obtain calibration data, including:

[0096] The pointer position feature in the instrument key feature is subjected to pointer positioning refinement by using an edge detection algorithm, and the position of the pointer tip is determined;

[0097] The scale distribution feature in the instrument key feature is subjected to scale calibration by using template matching and regression analysis, and the scale distribution information is determined;

[0098] The calibration data is obtained by comprehensively considering the position of the pointer tip and the scale distribution information.

[0099] For the embodiment of the present application, in the process of instrument feature extraction by using the convolutional neural network, the instrument image may be affected by factors such as light change, noise interference, and shooting angle, which may cause a certain error in the pointer position and scale distribution extracted by the instrument feature recognition model, and further affect the accuracy of the subsequent instrument reading. In order to further improve the accuracy of instrument reading recognition, pointer positioning refinement and scale calibration are performed based on the instrument key features to obtain calibration data, and the pointer positioning refinement and scale calibration are used to reduce the positioning error caused by image blur or noise interference.

[0100] Specifically, the edge detection algorithm is used to perform pointer positioning refinement on the pointer position feature in the key feature of the instrument, to determine the position of the pointer tip, that is, the edge detection algorithm is used to accurately identify the edge information of the pointer, and the profile of the pointer is further refined through morphological processing (such as erosion, dilation, thinning, etc.), so that the position of the pointer tip is more accurately determined. At the same time, for the case that the instrument scale is regular and stable, the scale distribution feature in the instrument image is matched with the preset template through the template matching algorithm, so that the scale distribution information is quickly identified; for the instrument with irregular or changing scale distribution, a regression analysis statistical method can be used to fit the scale distribution information according to the known scale point position information. Finally, the calibration data is obtained by comprehensively considering the pointer tip position and the scale distribution information. The pointer positioning refinement and scale calibration operation are performed, which improves the quality and reliability of the industrial data, and provides a strong guarantee for the monitoring and optimization of the production process.

[0101] It can be seen that, in the embodiment of the present application, the edge detection algorithm is used to perform pointer positioning refinement on the pointer position feature in the key feature of the instrument, to determine the position of the pointer tip. At the same time, the template matching and regression analysis are used to perform scale calibration on the scale distribution feature in the key feature of the instrument, to determine the scale distribution information. Finally, the calibration data is obtained by comprehensively considering the pointer tip position and the scale distribution information. The pointer positioning refinement and scale calibration are used to reduce the positioning error caused by image blur or noise interference, and improve the quality and reliability of the industrial data.

[0102] The above embodiment introduces an instrument intelligent analysis method based on video images from the perspective of method flow. The following embodiment introduces an instrument intelligent analysis system based on video images from the perspective of virtual modules or virtual units. For details, see the following embodiment.

[0103] The embodiment of the present application provides an instrument intelligent analysis system based on video images, as shown in Fig. 2 The instrument intelligent analysis system based on video images can specifically include:

[0104] The preprocessing module 210 is configured to acquire an instrument video image, and perform preprocessing based on the instrument video image to obtain a preprocessed instrument image. The preprocessing includes filtering and denoising, gray scale conversion, and illumination contrast parameter adjustment.

[0105] The image segmentation module 220 is configured to perform image segmentation operation based on the preprocessed instrument image to obtain an instrument region segmentation map. The instrument region segmentation map is used to partition different functional regions in the instrument.

[0106] The feature extraction module 230 is configured to acquire an instrument feature recognition model, perform instrument feature extraction on the instrument region segmentation image by using the instrument feature recognition model, and determine instrument key features, wherein the instrument key features include a pointer position feature and a scale distribution feature.

[0107] The calibration module 240 is configured to, when the instrument type is a pointer instrument, perform pointer positioning refinement and scale calibration based on the instrument key features, obtain calibration data, and perform instrument reading calculation based on the calibration data to determine the instrument reading.

[0108] For the embodiment of the present application, the instrument video image is preprocessed to obtain a preprocessed instrument image. The preprocessing includes illumination contrast parameter adjustment. The illumination contrast parameter adjustment is performed on the instrument video image, so that the brightness and contrast of the processed instrument image reach a suitable range, and the visual effect and definition of the image are enhanced. Then, an image segmentation operation is performed based on the preprocessed instrument image to obtain an instrument region segmentation image. The image segmentation operation is used to accurately locate the feature region to be recognized, and improve the accuracy of the instrument key features. Furthermore, the instrument feature recognition model is used to perform instrument feature extraction on the instrument region segmentation image to determine the instrument key features. After that, the pointer positioning refinement and the scale calibration are performed based on the instrument key features to obtain calibration data, and the instrument reading calculation is performed based on the calibration data to determine the instrument reading. The data recognition is performed by combining the classical image processing technology and the convolutional neural network model feature extraction. The instrument data recognition mode combining the two modes improves the accuracy of the instrument data reading.

[0109] In a possible implementation of the embodiment of the present application, the instrument intelligent analysis system based on a video image further includes:

[0110] The reading prediction module is configured to store the instrument reading into a data monitoring database, wherein the data monitoring database is configured to store the instrument readings corresponding to different nodes of each instrument;

[0111] The instrument reading sequence corresponding to the target instrument is extracted from the data monitoring database, wherein the target instrument is any one of the instruments stored in the data monitoring database, and the instrument reading sequence is composed of a plurality of instrument readings arranged in time sequence;

[0112] The reading prediction is performed based on the instrument reading sequence, the prediction data is determined, and the preventive evaluation is performed based on the prediction data to obtain the preventive maintenance information.

[0113] In a possible implementation of the embodiment of the present application, the instrument intelligent analysis system based on a video image further includes:

[0114] The illumination analysis module is configured to acquire illumination information collected by the light sensor, wherein the light sensor is arranged at a preset position of the instrument and is configured to detect light intensity and illumination conditions of an environment around the instrument in real time.

[0115] The working parameter analysis is performed based on the illumination information, and working parameters corresponding to the image acquisition device are determined and sent to the image acquisition device to control the image acquisition device to acquire images according to the working parameters, wherein the working parameters include an exposure time, a shutter speed, a white balance speed, and an ISO value.

[0116] In an embodiment of the present application, the instrument intelligent analysis system based on video images further includes:

[0117] The illumination evaluation module is configured to evaluate illumination conditions based on the illumination information and determine an illumination condition evaluation result, wherein the illumination condition evaluation result includes satisfaction of image acquisition requirements and non-satisfaction of image acquisition requirements.

[0118] When the illumination condition evaluation result is non-satisfaction of image acquisition requirements, light compensation analysis is performed based on the illumination information, and light compensation operations are determined, wherein the light compensation operations include increasing light sources and adjusting light directions.

[0119] In an embodiment of the present application, the instrument intelligent analysis system based on video images further includes:

[0120] The data updating module is configured to acquire instrument environment data, perform environment interference analysis based on the instrument environment data, and determine an environment interference analysis result, wherein the environment interference analysis result includes existence of interference and non-existence of interference.

[0121] When the environment interference analysis result is existence of interference, a target sensor corresponding to a type of instrument reading is determined, industrial data collected by the target sensor is acquired, and the instrument reading is updated based on the industrial data.

[0122] In an embodiment of the present application, when the calibration data is obtained by performing pointer positioning refinement and scale calibration based on the instrument key features, the refinement calibration module 240 is configured to:

[0123] The pointer position feature in the instrument key features is refined by using an edge detection algorithm to determine a pointer tip position.

[0124] The scale distribution feature in the instrument key features is calibrated by using template matching and regression analysis to determine scale distribution information.

[0125] The calibration data is obtained by comprehensively considering the pointer tip position and the scale distribution information.

[0126] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the above-described video image-based instrument intelligent analysis system can refer to the corresponding process in the foregoing method embodiments, and will not be described here.

[0127] An electronic device is provided in the embodiments of the present application, such as Fig. 3 as shown in the figure, Fig. 3 The electronic device 300 shown in the figure includes a processor 301 and a memory 303. Wherein, the processor 301 and the memory 303 are connected, such as connected through a bus 302. Optionally, the electronic device 300 can also include a transceiver 304. It should be noted that the transceiver 304 is not limited to one in actual application, and the structure of the electronic device 300 does not constitute a limitation on the embodiments of the present application.

[0128] The processor 301 can be a CPU (Central Processing Unit, central processor), a general-purpose processor, a DSP (Digital Signal Processor, data signal processor), an ASIC (Application Specific Integrated Circuit, application specific integrated circuit), an FPGA (Field Programmable Gate Array, field programmable gate array) or other programmable logic devices, transistor logic devices, hardware components or any combination thereof. It can realize or execute various exemplary logical blocks, modules and circuits described in combination with the disclosure content of the present application. The processor 301 can also be a combination of computing functions, such as one or more microprocessor combinations, combinations of DSP and microprocessor, etc.

[0129] The bus 302 can include a channel for transmitting information between the above-mentioned components. The bus 302 can be a PCI (Peripheral Component Interconnect, peripheral component interconnect) bus or an EISA (Extended Industry Standard Architecture, extended industry standard architecture) bus, etc. The bus 302 can be divided into an address bus, a data bus, a control bus, etc. For the convenience of representation, Fig. 3 In the figure, only one thick line is used to represent, but it does not mean that there is only one bus or one type of bus.

[0130] The memory 303 can be a ROM (Read Only Memory) or other type of static storage device that can store static information and instructions, a RAM (Random Access Memory) or other type of dynamic storage device that can store information and instructions, an EEPROM (Electrically Erasable Programmable Read Only Memory), a CD-ROM (Compact Disc Read Only Memory) or other optical disk storage, a magnetic disk storage medium or other magnetic storage device, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer, but is not limited thereto.

[0131] The memory 303 is configured to store application program codes for implementing the solutions of the present application, and the processor 301 is configured to control the execution of the application program codes. The processor 301 is configured to execute the application program codes stored in the memory 303 to implement the content shown in the foregoing method embodiments.

[0132] The electronic device includes, but is not limited to, a mobile terminal such as a mobile phone, a notebook computer, a digital broadcast receiver, a PDA (Personal Digital Assistant), a PAD (Tablet Personal Computer), a PMP (Portable Multimedia Player), a car terminal (for example, a car navigation terminal), and the like, and a fixed terminal such as a digital TV, a desktop computer, and the like. It can also be a server or the like. Fig. 3 The electronic device shown is only an example, and should not bring any limitation to the functions and use range of the embodiments of the present application.

[0133] The embodiments of the present application provide a computer readable storage medium, and the computer readable storage medium stores a computer program. When the computer program is run on a computer, the computer can execute the corresponding content in the foregoing method embodiments.

[0134] The embodiment of the application provides a computer program product, which comprises a computer program, and the computer program is executed by a processor to realize the method in any of the above embodiments. Compared with the related art, the embodiment of the application performs preprocessing on the instrument video image to obtain a preprocessed instrument image, the preprocessing comprises illumination contrast parameter adjustment, and the illumination contrast parameter adjustment is performed on the instrument video image, so that the brightness and contrast of the processed instrument image reach a proper range, and the visual effect and definition of the image are enhanced. Then, an image segmentation operation is performed on the preprocessed instrument image to obtain an instrument region segmentation graph, and the image segmentation operation is used to accurately locate a feature region to be recognized, and the accuracy of the instrument key feature is improved. Furthermore, an instrument feature recognition model is used to extract an instrument feature from the instrument region segmentation graph, to determine the instrument key feature, and after that, pointer positioning refinement and scale calibration are performed based on the instrument key feature to obtain calibration data, and instrument reading calculation is performed based on the calibration data to determine the instrument reading. The data recognition is performed by combining the classical image processing technology and the convolutional neural network model feature extraction, the instrument data recognition mode combining the two modes improves the accuracy of instrument data reading.

[0135] It should be understood that, although each step in the flowchart of the accompanying drawings is displayed in sequence according to the indication of the arrow, these steps are not necessarily executed in sequence according to the indication of the arrow. Unless otherwise specified herein, the execution of these steps is not strictly limited in sequence, and they can be executed in other sequences. Moreover, at least part of the steps in the flowchart of the accompanying drawings can comprise multiple sub-steps or multiple stages, and these sub-steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution sequence is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0136] The above is only part of the embodiments of the application, and it should be pointed out that, for those skilled in the art, without departing from the principles of the application, a number of improvements and refinements can be made, and these improvements and refinements should be regarded as the protection scope of the application.

Claims

1. A method for intelligent analysis of instruments based on video images, characterized in that, The method comprises the following steps: acquiring an instrument video image, preprocessing based on the instrument video image to obtain a preprocessed instrument image, wherein the preprocessing comprises filtering denoising, grayscale conversion and illumination contrast parameter adjustment; performing image segmentation operation based on the preprocessed instrument image to obtain an instrument region segmentation map, wherein the instrument region segmentation map is used to divide different functional regions in the instrument, and the functional regions include a speedometer region, a fuel gauge region, a tachometer region, a temperature gauge region and a pressure gauge region; acquiring an instrument feature recognition model, using the instrument feature recognition model to extract instrument features from the instrument region segmentation map, and determining instrument key features, wherein the instrument key features include pointer position features and scale distribution features; when the instrument type is a pointer instrument, performing pointer positioning refinement and scale calibration based on the instrument key features to obtain calibration data, and performing instrument reading calculation based on the calibration data to determine the instrument reading; before the step of acquiring the instrument video image, the method further comprises the following steps: acquiring illumination information collected by a light sensor, wherein the light sensor is arranged at a preset position of the instrument and is used to detect the light intensity and illumination conditions of the environment around the instrument in real time; performing working parameter analysis based on the illumination information to determine the working parameters corresponding to the image acquisition device, and sending the working parameters to the image acquisition device to control the image acquisition device to perform image acquisition according to the working parameters, wherein the working parameters include exposure time, shutter speed, white balance speed and ISO value; after the step of acquiring the illumination information collected by the light sensor, the method further comprises the following steps: performing illumination condition evaluation based on the illumination information to determine an illumination condition evaluation result, wherein the illumination condition evaluation result includes meeting the image acquisition requirement and not meeting the image acquisition requirement; when the illumination condition evaluation result is the not meeting the image acquisition requirement, performing light supplement analysis based on the illumination information to determine a light supplement operation, wherein the light supplement operation includes increasing light sources and adjusting light direction; the illumination condition evaluation includes the range of illumination intensity, the suitable value of color temperature and the limitation of light direction; after the step of performing instrument reading calculation based on the calibration data to determine the instrument reading, the method further comprises the following steps: acquiring instrument environment data, performing environment interference analysis based on the instrument environment data to determine an environment interference analysis result, wherein the environment interference analysis result includes existing interference and no interference; when the environment interference analysis result is the existing interference, determining a corresponding target sensor based on the type of the instrument reading, acquiring industrial data collected by the target sensor, and updating the instrument reading based on the industrial data.

2. The method of claim 1, wherein, after the step of performing instrument reading calculation based on the calibration data to determine the instrument reading, the method further comprises the following steps: storing the instrument reading into a data monitoring database, wherein the data monitoring database is used to store the instrument readings corresponding to different nodes of each instrument respectively; From the data monitoring database, the instrument reading sequence corresponding to the target instrument is extracted, wherein the target instrument is any one instrument stored in the data monitoring database, and the instrument reading sequence is composed of a plurality of instrument readings arranged in time sequence; Based on the instrument reading sequence, reading prediction is performed, prediction data is determined, and preventive evaluation is performed based on the prediction data to obtain preventive maintenance information.

3. The method of claim 1, wherein, The calibration data is obtained by refining the pointer positioning based on the instrument key features and calibrating the scale. The pointer positioning refinement is performed on the pointer position feature in the instrument key features by using an edge detection algorithm to determine the pointer tip position; The scale calibration is performed on the scale distribution feature in the instrument key features by using template matching and regression analysis to determine the scale distribution information; The calibration data is obtained by integrating the pointer tip position and the scale distribution information.

4. A video image-based meter intelligence analysis system, characterized by comprising: The system performs the intelligent analysis method of the instrument based on the video image as claimed in claim 1, and the system comprises: A preprocessing module is configured to acquire an instrument video image, perform preprocessing based on the instrument video image, and obtain a preprocessed instrument image, wherein the preprocessing includes filtering and denoising, grayscale conversion, and illumination contrast parameter adjustment; An image segmentation module is configured to perform image segmentation on the preprocessed instrument image to obtain an instrument region segmentation map, wherein the instrument region segmentation map is used to divide different functional regions in the instrument; A feature extraction module is configured to acquire an instrument feature recognition model, extract instrument features from the instrument region segmentation map by using the instrument feature recognition model, and determine instrument key features, wherein the instrument key features include pointer position features and scale distribution features; A refinement and calibration module is configured to refine the pointer positioning and calibrate the scale based on the instrument key features when the instrument type is a pointer instrument to obtain calibration data, and perform instrument reading calculation based on the calibration data to determine the instrument reading; An illumination analysis module is configured to acquire illumination information collected by a light sensor, wherein the light sensor is arranged at a preset position of the instrument panel to detect the light intensity and illumination conditions of the environment around the instrument panel in real time; Based on the illumination information, the working parameters of the image acquisition device are determined, and the working parameters are sent to the image acquisition device to control the image acquisition device to perform image acquisition according to the working parameters, wherein the working parameters include exposure time, shutter speed, white balance speed, and ISO value; An illumination evaluation module is configured to evaluate the illumination conditions based on the illumination information to determine the illumination condition evaluation result, wherein the illumination condition evaluation result includes meeting the image acquisition requirements and not meeting the image acquisition requirements; When the illumination condition evaluation result is not meeting the image acquisition requirements, the light compensation analysis is performed based on the illumination information to determine the light compensation operation, wherein the light compensation operation includes increasing the light source and adjusting the light direction. It comprises:

5. An electronic device, comprising: At least one processor; Memory; At least one application program, wherein the at least one application program is stored in the memory and is configured to be executed by the at least one ​ The processor executes the at least one application program configured to perform the video image-based instrument intelligence analysis method of any one of claims 1-3.

6. A computer readable storage medium characterized by A computer program product, comprising a computer readable medium having stored thereon the computer program, the computer program, when executed in a computer, causing the computer to perform the video image-based instrument intelligence analysis method of any one of claims 1-3.

Images