Dust detection method based on image processing and related equipment

Abstract

The embodiment of the invention provides a dust detection method and device based on image processing, and the method comprises the steps: obtaining dust data in a current region, and the dust data comprises dust image data and dust concentration data; processing the dust image data and the dust concentration data through a trained dust feature analysis model to obtain dust feature data in the current area; and integrating and outputting the dust feature data through a visualization module, and generating a visual dust feature report. By means of the method, the scheme that image data and concentration data are combined to obtain accurate dust characteristic data is achieved, and the real-time performance, accuracy and stability of dust detection in a certain area are improved by conducting comprehensive analysis on the current dust concentration and images in the certain area.

Description

Technical Field

[0001] The present invention relates to the field of environmental detection, and in particular to a dust detection method, device, electronic equipment and storage medium based on image processing. Background Art

[0002] In the field of environmental monitoring and air quality assessment, dust detection and analysis are key links. Dust not only affects air quality, but may also have a significant impact on human health and the industrial production environment. Therefore, accurately monitoring and evaluating the dust content in the air has become an important task for environmental protection and health supervision.

[0003] The current dust detection method cannot combine image data and dust concentration data to determine the current state of the dust, resulting in low dust detection accuracy and stability. Summary of the invention

[0004] The embodiment of the present invention provides a dust detection method based on image processing to solve the problem that the existing dust detection method cannot combine image data and data corresponding to dust concentration to determine the current state of dust, thereby resulting in low dust detection accuracy and stability.

[0005] In a first aspect, an embodiment of the present invention provides a dust detection method based on image processing, the method comprising the following steps: Acquire dust data in the current area, wherein the dust data includes dust image data and dust concentration data; The dust image data and dust concentration data are processed by a trained dust feature analysis model to obtain dust feature data in the current area; The dust characteristic data are integrated and outputted through a visualization module to generate a visualized dust characteristic report.

[0006] Optionally, obtaining dust data in the current area includes: The dust in the current area is collected within a certain period of time by a preset concentration sensor to obtain corresponding dust concentration data; The dust in the current area is photographed within a certain period of time by a preset optical camera to obtain corresponding dust image data.

[0007] Optionally, the dust in the current area is photographed within a certain period of time by a preset optical camera to obtain corresponding dust image data, including: Performing image enhancement preprocessing on the first image data obtained by shooting to obtain second image data; The second image data is subjected to feature labeling preprocessing to obtain the corresponding dust image data, wherein the dust image data contains corresponding dust features.

[0008] Optionally, the dust image data and dust concentration data are processed by a trained dust feature analysis model to obtain dust feature data in the current area, including: Calculate the similarity between the dust features corresponding to the dust image data and the dust concentration data to determine the overlapping part of the dust image data and the dust concentration data; Based on the overlapping part, dust characteristic data in the current area is determined, and the dust characteristic data includes current concentration, concentration trend and corresponding early warning scheme.

[0009] Optionally, before the dust image data and dust concentration data are processed by the trained dust feature analysis model to obtain dust feature data in the current area, the method further includes: Obtaining a dust feature analysis model to be trained and a training dust sample set, wherein the training dust sample set includes dust concentration, a dust picture corresponding to the dust concentration, and a dust concentration label corresponding to the dust picture; Based on the dust concentration, the dust image corresponding to the dust concentration, and the dust concentration label corresponding to the dust image, the dust feature analysis model to be trained is iteratively trained, and a trained dust feature analysis model is obtained after the iterative training is completed.

[0010] Optionally, the dust feature analysis model to be trained is iteratively trained based on the dust concentration, the dust image corresponding to the dust concentration, and the dust concentration label corresponding to the dust image, and a trained dust feature analysis model is obtained after the iterative training is completed. The method also includes: The dust image corresponding to the latest dust concentration is used as the latest training sample to replace the current training set; The dust feature analysis model to be trained is iteratively trained using the latest training samples to obtain a trained dust feature analysis model.

[0011] Optionally, the dust characteristic data is integrated and outputted through a visualization module to generate a visualized dust characteristic report, including: Based on the dust characteristic data, determining a curve graph of each characteristic data in the layered characteristic data; Based on the curve graph, a trend graph of each characteristic data is obtained; According to the trend chart and curve chart, a corresponding early warning strategy is generated, and a visual report is generated for display.

[0012] In a second aspect, an embodiment of the present invention further provides a dust detection device based on image processing, and the dust detection device based on image processing includes: An acquisition module, used to acquire dust data in the current area, wherein the dust data includes dust image data and dust concentration data; A processing module, used to process the dust image data and dust concentration data through a trained dust feature analysis model to obtain dust feature data in a current area; The generation module is used to integrate and output the dust characteristic data through the visualization module to generate a visualized dust characteristic report.

[0013] In a third aspect, an embodiment of the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the dust detection method based on image processing provided in an embodiment of the present invention are implemented.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the steps of the dust detection method based on image processing provided in the embodiment of the invention are implemented.

[0015] In an embodiment of the present invention, dust data in the current area is obtained, and the dust data includes dust image data and dust concentration data; the dust image data and dust concentration data are processed by a trained dust feature analysis model to obtain dust feature data in the current area; the dust feature data is integrated and output by a visualization module to generate a visualized dust feature report. Through the above method, a solution is implemented to combine image data with concentration data to obtain accurate dust feature data. By comprehensively analyzing the current dust concentration and image in a certain area, the real-time, accuracy and stability of dust detection in the area are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a flow chart of a dust detection method based on image processing provided by an embodiment of the present invention; Figure 2is a structural schematic diagram of a dust detection method and device based on image processing provided in an embodiment of the present invention; Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0019] The terms "first", "second", etc. in the specification and claims of the present application are used to distinguish similar objects, and are not used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable under appropriate circumstances, so that the embodiments of the present application can be implemented in an order other than those illustrated or described here, and the objects distinguished by "first", "second", etc. are generally of one type, and the number of objects is not limited. For example, the first object can be one or more. In addition, "and / or" in the specification and claims represents at least one of the connected objects, and the character " / " generally indicates that the objects associated with each other are in an "or" relationship. like Figure 1 As shown, Figure 1 : is a flow chart of a dust detection method based on image processing provided by an embodiment of the present invention, the dust detection method based on image processing comprises the steps of: S101, obtaining dust data in the current area.

[0020] In an embodiment of the present invention, the above-mentioned dust detection method based on image processing can be applied to a dust detection device based on image processing. The above-mentioned dust detection device based on image processing has functions such as dust data processing, dust data transmission and reception, and dust data storage, and can be constructed based on a server or a server cluster. The above-mentioned server or server cluster can be an electronic device with dust data processing capabilities.

[0021] The dust data may include but are not limited to dust image data and dust concentration data. Specifically, the dust image data may be obtained by real-time photographing the dust portion in the current area with a high-resolution camera. Generally speaking, the area may be determined based on the maximum dust capture capability of the camera, which may be determined based on the clarity of the dust image captured in the largest area, i.e., the clearer the dust image captured is in a larger area, the stronger the maximum dust capture capability is.

[0022] It should be noted that the above-mentioned high-resolution camera is also equipped with a light source system, which uses a light source with a wavelength and intensity matching the ambient light in the current environment, so that the camera can clearly capture images of dust particles in the air under various ambient lighting conditions.

[0023] The dust concentration data may be a specific value obtained by obtaining and calculating the number of dust particles in a certain area through a preset concentration sensor. The dust concentration data may indicate the distribution degree of dust particles in the current area.

[0024] S102: Process the dust image data and dust concentration data through the trained dust feature analysis model to obtain dust feature data in the current area.

[0025] In an embodiment of the present invention, the above-mentioned trained dust feature analysis model may include but is not limited to any deep learning model that can combine dust image data and dust concentration data for comprehensive analysis and processing to output dust feature data in the current area, such as BERT (Bidirectional Encoder Representations from Transformers), CLIP (Contrastive Language–Image Pre-training) and MMBT (Multimodal Bitransformer) and other deep learning models.

[0026] The above-mentioned dust feature data can be obtained by processing the dust image data and dust concentration data through the above-mentioned trained dust feature analysis model, which is a comprehensive information that can be used to describe the detailed characteristics of the dust, including but not limited to the size, shape, distribution of dust particles, and other characteristics related to the current environmental concentration.

[0027] In a possible embodiment, the dust image data and dust concentration data are input into the trained dust feature analysis model. The model calculates and outputs accurate dust feature data by calculating the size, shape and distribution of dust particles in the image in combination with the dust concentration data. It can be understood that the output data may include but is not limited to dust concentration, distribution trend and potential risk level. These data are integrated through a visualization module to generate an easy-to-understand dust feature report, providing a basis for environmental monitoring and health risk assessment.

[0028] S103. Integrate and output the dust characteristic data through a visualization module to generate a visualized dust characteristic report.

[0029] In an embodiment of the present invention, the visualization module may display the output dust characteristic data in the intelligent terminal for the user to view, and may generate a characteristic report integrating the corresponding data.

[0030] In a possible embodiment, the concentration, form, distribution and trend data of dust are converted into intuitive graphics and charts through the above-mentioned visualization module, and the dust conditions in the area are displayed in real time through the intelligent terminal. It can be understood that early warnings and protective measures corresponding to the dust status can also be generated so that users can quickly understand the current air quality conditions and respond.

[0031] In the embodiment of the present invention, dust data in the current area is obtained, and the dust data includes dust image data and dust concentration data; the dust image data and dust concentration data are processed by a trained dust feature analysis model to obtain dust feature data in the current area; the dust feature data is integrated and output by a visualization module to generate a visualized dust feature report. Through the above method, a solution of combining image data with concentration data to obtain accurate dust feature data is realized, and by comprehensively analyzing the current dust concentration and image in a certain area, the real-time, accuracy and stability of dust detection in the area are improved.

[0032] Optionally, the step of obtaining dust data in the current area also includes: collecting dust in the current area within a certain period of time through a preset concentration sensor to obtain corresponding dust concentration data; photographing the dust in the current area within a certain period of time through a preset optical camera to obtain corresponding dust image data.

[0033] In an embodiment of the present invention, the preset concentration sensor may include but is not limited to any sensor that can set a regional range and collect dust within the regional range. Specifically, after collecting dust in the current area, the preset concentration sensor may calculate the dust concentration data in the current area by using the set regional range and the number of collected dust particles.

[0034] The preset optical camera can be a high-resolution camera device specifically used to capture images of dust particles in the air in real time. The position, shooting frequency and image quality of the camera can be determined according to the maximum dust capture capacity to ensure that clear dust image data can be stably collected under different lighting and environmental conditions. Generally speaking, the preset optical camera is also equipped with a suitable filter and fill light to reduce ambient light interference, improve shooting effects, and make dust particles easier to be identified and processed by subsequent image processing and analysis algorithms.

[0035] Optionally, in the step of photographing the dust in the current area within a certain period of time by a preset optical camera to obtain corresponding dust image data, it also includes performing image enhancement preprocessing on the first image data obtained by the photographing to obtain second image data; performing feature marking preprocessing on the second image data to obtain corresponding dust image data, and the dust image data contains corresponding dust features.

[0036] In an embodiment of the present invention, the above-mentioned image enhancement preprocessing may include but is not limited to operations such as denoising, contrast enhancement, and edge detection. Specifically, a filtering algorithm (such as Gaussian filtering) may be used to remove noise in the image, histogram equalization may be used to enhance the contrast of the image, and a Canny edge detection algorithm may be used to extract edge information of dust particles in the image.

[0037] More specifically, the above-mentioned denoising process can utilize filters (such as Gaussian filters, median filters, etc.) to denoise the image so as to reduce the impact of noise in the image on subsequent processing; the above-mentioned image enhancement can enhance the contrast and clarity of the image through histogram equalization, contrast enhancement and other technologies, so as to better observe and analyze the dust particles in the image; the above-mentioned edge detection can utilize edge detection algorithms (such as Sobel, Canny, etc.) to detect edge information in the image, so as to locate and extract the contour and shape characteristics of the dust particles.

[0038] The above-mentioned feature marker preprocessing can extract characteristic information such as shape, size, distribution, etc. of dust particles through morphological processing, contour extraction and other technologies, which can be used for subsequent dust concentration analysis and identification.

[0039] The dust particles in the image can also be separated from the background by segmentation algorithms (such as threshold segmentation, region growing, etc.) for segmentation processing, so as to perform subsequent feature extraction and analysis.

[0040] In one possible embodiment, key features such as shape, size and distribution of dust particles are accurately identified and extracted from the collected dust image through morphological processing and contour extraction technology, and segmentation processing such as threshold segmentation and region growing algorithm is used to further separate the dust particles in the image from the background, making the features of the dust particles more obvious and easier to analyze.

[0041] This processing method significantly improves the usability of data, making the analysis and identification of dust concentrations more accurate and effective.

[0042] Optionally, in the step of processing the dust image data and dust concentration data through a trained dust feature analysis model to obtain the dust feature data in the current area, it also includes calculating the similarity between the dust features corresponding to the dust image data and the dust concentration data to determine the overlapping part of the dust image data and the dust concentration data; based on the overlapping part, determine the dust feature data in the current area.

[0043] In an embodiment of the present invention, the above-mentioned phase velocity calculation can be calculated based on the corresponding dust concentration data in the dust features and the collected dust concentration data. Specifically, the concentration data obtained by the sensor can be calculated by similarity with these image features, such as using cosine similarity or correlation coefficient to determine the overlapping part between the image data and the concentration data.

[0044] Through the above method, the actual state of dust can be accurately monitored and analyzed, which improves the accuracy and reliability of dust concentration measurement. This data fusion technology not only enhances the effectiveness of monitoring data, but also provides a more scientific and real-time basis for dust management, and improves the overall performance and responsiveness of the environmental monitoring system.

[0045] The above-mentioned dust characteristic data may include but are not limited to parameters such as current concentration, concentration trend and corresponding early warning plan. Specifically, since the forms and characteristics of different dusts in different areas are different, for example, since the dust particles are large, the calculation method for concentration calculation may also change. Therefore, different types of dust can be determined based on the different dust characteristic data detected.

[0046] In a possible embodiment, by calculating the similarity between the dust features in the image data and the collected dust features, an overlapping portion is determined in the image data, and features are extracted from the image data of the overlapping portion to determine dust feature data of the corresponding type of dust.

[0047] Optionally, before the step of processing the dust image data and the dust concentration data through the trained dust feature analysis model to obtain the dust feature data in the current area, it also includes obtaining the dust feature analysis model to be trained and the training dust sample set; based on the dust concentration, the dust picture corresponding to the dust concentration, and the dust concentration label corresponding to the dust picture, the dust feature analysis model to be trained is iteratively trained, and the trained dust feature analysis model is obtained after the iterative training is completed.

[0048] In an embodiment of the present invention, the above-mentioned dust feature analysis model to be trained may include but is not limited to any deep learning model that cannot combine dust image data and dust concentration data for comprehensive analysis and processing, and outputs dust feature data in the current area, such as BERT (Bidirectional Encoder Representations from Transformers), CLIP (Contrastive Language–Image Pre-training) and MMBT (Multimodal Bitransformer) and other deep learning models. Specifically, since the dust image data between different types of dust and dust are similar, before the deep learning model is trained, outputting dust image data and dust concentration data to the dust feature analysis model to be trained may output dust feature data that deviates from the actual results.

[0049] The training dust sample set may include, but is not limited to, dust concentrations, dust images corresponding to the dust concentrations, and dust concentration labels corresponding to the dust images.

[0050] The dust image corresponding to the dust concentration may be collected image information of different types of dust at different concentrations.

[0051] The dust concentration labels may be specific and accurate concentration data of different types of dust under different image information stored in the database.

[0052] In a possible embodiment, the dust feature analysis model to be trained is iteratively trained using the above-mentioned dust concentration, the dust picture corresponding to the dust concentration, and the dust concentration label corresponding to the dust picture. Specifically, the above-mentioned dust concentration and the dust picture corresponding to the dust concentration are input into the above-mentioned dust feature analysis model to be trained, and the parameters of the model are adjusted with the goal of being infinitely close to the dust concentration label corresponding to the above-mentioned dust picture. When the similarity between the output dust feature data and the dust concentration label corresponding to the dust picture is within a preset similarity threshold, the model training is completed and a trained dust feature analysis model is obtained.

[0053] Optionally, in the step of iteratively training the dust feature analysis model to be trained based on the dust concentration, the dust image corresponding to the dust concentration, and the dust concentration label corresponding to the dust image, and obtaining the trained dust feature analysis model after the iterative training is completed, it also includes taking the dust image corresponding to the latest acquired dust concentration as the latest training sample to replace the current training set; iteratively training the dust feature analysis model to be trained using the latest training sample to obtain the trained dust feature analysis model.

[0054] In the embodiment of the present invention, a training threshold test may be performed on the training sample to determine whether the current training sample meets the training content of the dust feature analysis model to be trained according to a preset training threshold.

[0055] In a possible embodiment, if the detected error exceeds a preset training threshold or the determination coefficient does not reach the threshold, an updated training sample and a corresponding optimized image preprocessing algorithm, such as denoising, contrast enhancement, edge detection, etc., will be obtained from the database to ensure the quality and clarity of the input image and the corresponding training sample can meet the cleanliness and quality issues. An adaptive filtering algorithm is used to dynamically adjust the preprocessing parameters according to different environmental conditions to improve the preprocessing effect, and then the deep learning model is retrained.

[0056] Optionally, in the step of integrating and outputting the dust characteristic data through a visualization module to generate a visual dust characteristic report, the step includes determining a curve graph of each characteristic data in the layered characteristic data based on the dust characteristic data; obtaining a trend graph of each characteristic data based on the curve graph; generating a corresponding early warning strategy based on the trend graph and the curve graph, and generating a visualization report for display.

[0057] In an embodiment of the present invention, dust characteristic data, such as the size, shape and concentration of dust, are collected and analyzed, and processed by a trained dust characteristic analysis model. Curve graphs of various characteristics are drawn in the layered characteristic data, and trend graphs of dust characteristics are generated using these curve graphs, so as to display the dust behavior and pattern that changes over time in the smart terminal. Based on these data and graphs, an early warning strategy is automatically formulated. For example, when the dust concentration is monitored to exceed the safety threshold, the management personnel are immediately notified to take action. The above method not only helps the monitoring team track historical changes in dust levels, but also predicts future trend changes. All data and charts are displayed in an intuitive visual report, which improves decision-making efficiency and response speed, ensures environmental safety and personnel health protection, and improves the efficiency of dust detection.

[0058] In a possible embodiment, after the user enters the dust detection system through ID detection, the user can manage the alarm operation through a computer and set the alarm thresholds of different detection areas according to specific needs. Specifically, it can support dynamic adjustment of the alarm thresholds to ensure that the dust detection system can flexibly respond to changes in dust concentration in different environments.

[0059] More specifically, when the dust concentration exceeds the preset threshold, the system will send an alarm to the user through pop-up windows, sound prompts, red warning signs, etc. The user can click the alarm prompt to view detailed information, such as alarm time, detection area, concentration value, etc. The user can also view all historical alarm records in the alarm log, handle alarms and add notes (such as handling measures, results, etc.).

[0060] In another possible embodiment, the user can also adjust the parameters of the image processing module (such as filter parameters, edge detection parameters, etc.) to optimize the image processing effect, support saving and restoring the default parameter configuration, and facilitate users to quickly adjust the settings in different environments.

[0061] More specifically, the dust detection system can also provide a management interface for deep learning models, where users can upload, update, and switch model files, and view detailed model information (such as training parameters, version number, etc.).

[0062] like Figure 2 As shown, the embodiment of the present invention further provides a dust detection device 200 based on image processing, and the dust detection device based on image processing includes: An acquisition module 201 is used to acquire dust data in a current area, wherein the dust data includes dust image data and dust concentration data; The processing module 202 is used to process the dust image data and the dust concentration data through the trained dust feature analysis model to obtain dust feature data in the current area; The generation module 203 is used to integrate and output the dust characteristic data through a visualization module to generate a visualized dust characteristic report.

[0063] Optionally, the acquisition module 201 includes: The first acquisition submodule is used to collect dust in the current area within a certain period of time through a preset concentration sensor to obtain corresponding dust concentration data; The second acquisition submodule is used to photograph the dust in the current area within a certain period of time through a preset optical camera to obtain corresponding dust image data.

[0064] Optionally, the second acquisition submodule further includes: A first preprocessing unit, configured to perform image enhancement preprocessing on the first image data obtained by shooting to obtain second image data; The second preprocessing unit is used to perform feature labeling preprocessing on the second image data to obtain the corresponding dust image data, wherein the dust image data contains corresponding dust features.

[0065] Optionally, the processing module 202 includes: A first calculation submodule is used to perform similarity calculation between the dust features corresponding to the dust image data and the dust concentration data to determine the overlapping part of the dust image data and the dust concentration data; The second calculation submodule is used to determine dust characteristic data in the current area based on the overlapping part, and the dust characteristic data includes current concentration, concentration trend and corresponding early warning plan.

[0066] Optionally, the above device further includes: A first training module is used to obtain a dust feature analysis model to be trained and a training dust sample set, wherein the training dust sample set includes dust concentration, dust pictures corresponding to the dust concentration, and dust concentration labels corresponding to the dust pictures; The second training module is used to iteratively train the dust feature analysis model to be trained based on the dust concentration, the dust image corresponding to the dust concentration, and the dust concentration label corresponding to the dust image, and obtain the trained dust feature analysis model after the iterative training is completed.

[0067] Optionally, the second training module further includes: The first training submodule is used to use the dust image corresponding to the latest dust concentration as the latest training sample to replace the current training set; The second training submodule is used to iteratively train the dust feature analysis model to be trained using the latest training samples to obtain a trained dust feature analysis model.

[0068] Optionally, the generation module 203 includes: A first determination submodule, configured to determine a curve graph of each characteristic data in the layered characteristic data based on the dust characteristic data; A second determination submodule is used to obtain a trend graph of each characteristic data based on the curve graph; The third determination submodule is used to generate a corresponding early warning strategy according to the trend chart and the curve chart, and generate a visual report for display.

[0069] like Figure 3 As shown, an embodiment of the present invention further provides an electronic device 300, including a processor, and the processor can execute any one of the above-mentioned dust detection methods based on image processing.

[0070] Specifically, it includes a processor 301 and a memory 302, and a computer program for executing a dust detection method based on image processing, which is stored in the memory 302 and can be run on the processor 301, wherein: The processor 301 runs the computer program of the dust detection method based on image processing stored in the memory 302, and performs the following steps: Acquire dust data in the current area, wherein the dust data includes dust image data and dust concentration data; The dust image data and dust concentration data are processed by a trained dust feature analysis model to obtain dust feature data in the current area; The dust characteristic data are integrated and outputted through a visualization module to generate a visualized dust characteristic report.

[0071] Optionally, the processor 301 executes the step of obtaining dust data in the current area, including: The dust in the current area is collected within a certain period of time by a preset concentration sensor to obtain corresponding dust concentration data; The dust in the current area is photographed within a certain period of time by a preset optical camera to obtain corresponding dust image data.

[0072] Optionally, the processor 301 executes the step of photographing the dust in the current area within a certain period of time by using a preset optical camera to obtain corresponding dust image data, including: Performing image enhancement preprocessing on the first image data obtained by shooting to obtain second image data; The second image data is subjected to feature labeling preprocessing to obtain the corresponding dust image data, wherein the dust image data contains corresponding dust features.

[0073] Optionally, the processor 301 executes the trained dust feature analysis model to process the dust image data and the dust concentration data to obtain dust feature data in the current area, including: Calculate the similarity between the dust features corresponding to the dust image data and the dust concentration data to determine the overlapping part of the dust image data and the dust concentration data; Based on the overlapping part, dust characteristic data in the current area is determined, and the dust characteristic data includes current concentration, concentration trend and corresponding early warning scheme.

[0074] Optionally, before the processor 301 executes the trained dust feature analysis model to process the dust image data and the dust concentration data to obtain the dust feature data in the current area, the method further includes: Obtaining a dust feature analysis model to be trained and a training dust sample set, wherein the training dust sample set includes dust concentration, a dust picture corresponding to the dust concentration, and a dust concentration label corresponding to the dust picture; Based on the dust concentration, the dust image corresponding to the dust concentration, and the dust concentration label corresponding to the dust image, the dust feature analysis model to be trained is iteratively trained, and a trained dust feature analysis model is obtained after the iterative training is completed.

[0075] Optionally, the processor 301 further executes the iterative training of the dust feature analysis model to be trained based on the dust concentration, the dust picture corresponding to the dust concentration, and the dust concentration label corresponding to the dust picture, and obtains the trained dust feature analysis model after the iterative training is completed. The method also includes: The dust image corresponding to the latest dust concentration is used as the latest training sample to replace the current training set; The dust feature analysis model to be trained is iteratively trained using the latest training samples to obtain a trained dust feature analysis model.

[0076] Optionally, the processor 301 further performs the step of integrating and outputting the dust characteristic data through a visualization module to generate a visualized dust characteristic report, including: Based on the dust characteristic data, determining a curve graph of each characteristic data in the layered characteristic data; Based on the curve graph, a trend graph of each characteristic data is obtained; According to the trend chart and curve chart, a corresponding early warning strategy is generated, and a visual report is generated for display.

[0077] An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the dust detection method based on image processing provided by the embodiment of the present invention or the various processes of the dust detection method based on image processing on the application side can be implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0078] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0079] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A dust detection method based on image processing, characterized in that: include: Acquire dust data in the current area, wherein the dust data includes dust image data and dust concentration data; The dust image data and dust concentration data are processed by a trained dust feature analysis model to obtain dust feature data in the current area; The dust characteristic data are integrated and outputted through a visualization module to generate a visualized dust characteristic report.

2. The dust detection method based on image processing as claimed in claim 1, characterized in that: The obtaining of dust data in the current area includes: The dust in the current area is collected within a certain period of time by a preset concentration sensor to obtain corresponding dust concentration data; The dust in the current area is photographed within a certain period of time by a preset optical camera to obtain corresponding dust image data.

3. The dust detection method based on image processing as claimed in claim 1, characterized in that: The dust in the current area is photographed by a preset optical camera within a certain period of time to obtain corresponding dust image data, including: Performing image enhancement preprocessing on the first image data obtained by shooting to obtain second image data; The second image data is subjected to feature labeling preprocessing to obtain the corresponding dust image data, wherein the dust image data contains corresponding dust features.

4. The dust detection method based on image processing as claimed in claim 1, characterized in that: The dust image data and dust concentration data are processed by the trained dust feature analysis model to obtain dust feature data in the current area, including: Calculate the similarity between the dust features corresponding to the dust image data and the dust concentration data to determine the overlapping part of the dust image data and the dust concentration data; Based on the overlapping part, dust characteristic data in the current area is determined, and the dust characteristic data includes current concentration, concentration trend and corresponding early warning scheme.

5. The dust detection method based on image processing as claimed in claim 1, characterized in that: Before the dust image data and dust concentration data are processed by the trained dust feature analysis model to obtain dust feature data in the current area, the method further includes: Obtaining a dust feature analysis model to be trained and a training dust sample set, wherein the training dust sample set includes dust concentration, a dust picture corresponding to the dust concentration, and a dust concentration label corresponding to the dust picture; Based on the dust concentration, the dust image corresponding to the dust concentration, and the dust concentration label corresponding to the dust image, the dust feature analysis model to be trained is iteratively trained, and a trained dust feature analysis model is obtained after the iterative training is completed.

6. The dust detection method based on image processing as claimed in claim 5, characterized in that: The method further comprises: iteratively training the dust feature analysis model to be trained based on the dust concentration, the dust image corresponding to the dust concentration, and the dust concentration label corresponding to the dust image, and obtaining a trained dust feature analysis model after the iterative training is completed. The dust image corresponding to the latest dust concentration is used as the latest training sample to replace the current training set; The dust feature analysis model to be trained is iteratively trained using the latest training samples to obtain a trained dust feature analysis model.

7. The dust detection method based on image processing as claimed in claim 1, characterized in that: The dust characteristic data is integrated and outputted through the visualization module to generate a visualized dust characteristic report, including: Based on the dust characteristic data, determining a curve graph of each characteristic data in the layered characteristic data; Based on the curve graph, a trend graph of each characteristic data is obtained; According to the trend chart and curve chart, a corresponding early warning strategy is generated, and a visual report is generated for display.

8. A dust detection device based on image processing, characterized in that: include: An acquisition module, used to acquire dust data in the current area, wherein the dust data includes dust image data and dust concentration data; A processing module, used to process the dust image data and dust concentration data through a trained dust feature analysis model to obtain dust feature data in the current area; The generation module is used to integrate and output the dust characteristic data through the visualization module to generate a visualized dust characteristic report.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the dust detection method based on image processing as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the dust detection method based on image processing according to any one of claims 1 to 7 are implemented.

Images