Image-based appearance assessment method and system for bridge pier detection

Abstract

This invention relates to the field of bridge inspection and evaluation technology, and discloses an image-based method and system for appearance evaluation of bridge piers. The method includes: an image acquisition module for acquiring image information of the bridge piers from all directions; an image preprocessing module, containing code units for functions such as grayscale conversion, noise reduction, and image enhancement; a feature extraction module for extracting geometric and texture features; an evaluation index determination and classification module responsible for determining appearance evaluation indicators based on the extracted features and classifying them; this module can also generate an evaluation report; and a data display and storage module for displaying the evaluation report and storing the acquired image data. This invention can significantly save measurement time and further improve the accuracy and efficiency of inspection.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge detection and evaluation, and in particular to an image-based appearance evaluation method and system for bridge pier detection. Background Art

[0002] With the continuous development of transportation infrastructure, bridges, as important transportation hubs, have attracted much attention for their safety and reliability. As one of the main load-bearing components of bridges, the appearance of bridge piers directly affects the overall performance and service life of the bridge.

[0003] The traditional method of visual inspection of bridge piers mainly relies on manual visual observation and simple measuring tools, such as calipers, crack width meters, etc. This method has the following disadvantages: Low efficiency: Manual inspection requires a lot of manpower and time, especially for large bridges or a large number of piers, the inspection work often takes a long time. Limited accuracy: Manual inspection is easily affected by factors such as the experience, subjective judgment and fatigue of the inspectors, resulting in inconsistency and low accuracy of the inspection results. Difficult data management: Data records for manual inspections are usually in paper forms or simple electronic documents, which are inconvenient to manage and query data, and it is difficult to conduct long-term data analysis and trend prediction.

[0004] Therefore, it is necessary to design an image-based appearance evaluation method and system for bridge pier inspection to solve the problems of low detection efficiency, limited detection accuracy and difficult data management in traditional bridge pier appearance inspection methods. Summary of the invention

[0005] In view of this, the present invention proposes an image-based appearance evaluation method and system for bridge pier detection, aiming to solve the problems of low detection efficiency, limited detection accuracy and difficult data management in traditional bridge pier appearance detection methods.

[0006] In one aspect, the present invention provides an image-based appearance assessment system for bridge pier detection, comprising:

[0007] The image acquisition module is used to take all-round images of the bridge pier surface and record the environmental parameters during the shooting;

[0008] The image preprocessing module is used to perform grayscale processing and image enhancement on the captured image;

[0009] The geometric feature extraction module is used to extract the geometric features of bridge piers;

[0010] The texture feature extraction module is used to extract the texture features of the bridge piers;

[0011] An evaluation index determination and classification module is used to evaluate and classify the characteristics of the extracted bridge piers. The evaluation indexes include the damage degree and the surface flatness. For the damage degree, the detection items include crack width, crack length, crack depth, crack distribution density, honeycombing and pitting area, honeycombing and pitting depth, spalling area and spalling depth.

[0012] Record the safety status data as Si, where i = 1, 2, …, 8.

[0013] The safety status data Si is the detection value of the i-th item to be detected, including: crack width S1, crack length S2, crack depth S3, crack distribution density S4, honeycombing and pitting area S5, honeycombing and pitting depth S6, spalling area S7 and spalling depth S8.

[0014] Preset an outlier determination threshold X, where X > 0.

[0015] If Si < X, then it is judged that the quality of the detected bridge pier meets the standard.

[0016] If Si ≥ X, then it is judged that the quality of the detected bridge pier does not meet the standard.

[0017] For the surface flatness, the point cloud data of the pier is obtained through 3D reconstruction technology, the height difference between each point is measured, the normal height value is set as h0, and the height difference between each point is recorded as Δh.

[0018] If Δh < h0, then it is judged that the surface flatness of the pier meets the standard.

[0019] If Δh ≥ h0, then it is judged that the surface flatness of the pier does not meet the standard.

[0020] Set the safety detection evaluation levels according to the bell-shaped Gbellmf membership function. The first preset safety detection evaluation level, the second preset safety detection evaluation level and the third preset safety evaluation level are set in descending order. The detection values in the normal state of each detection item are divided into detection evaluation levels, and an evaluation report is generated.

[0021] A data display and storage module is used to display the evaluation report and store the collected image data.

[0022] Furthermore, the image acquisition module sets the exposure time according to the collected environmental parameters. If the natural light is sufficient, a shorter exposure time is set. If the natural light is dim, the exposure time needs to be appropriately delayed.

[0023] Furthermore, the grayscale processing converts the color image into a grayscale image. Each pixel is represented by a grayscale value, forming a grayscale component image in the original image, which is used to reduce the data volume.

[0024] Furthermore, after obtaining the grayscale component image in the original image, the CPLD processor performs grayscale value correction on the pixel points of the grayscale component image according to the relative light and dark relationship between the pixel points of the grayscale component image and the pixel points in the grayscale component image after Gaussian smoothing, and synthesizes the grayscale component image after grayscale value correction to obtain an enhanced image.

[0025] Furthermore, in the geometric feature extraction, a combination of multiple edge detection algorithms is used to extract the pier column contour; in the texture feature extraction process, the grayscale co-occurrence matrix and local binary pattern are used, and the wavelet transform texture analysis method is introduced. The wavelet transform can decompose the image at different scales and directions, thereby extracting richer texture information.

[0026] Furthermore, for the bell-shaped Gbel lmf membership function Determine the values ​​of parameters a, b, and c based on the characteristics of each test item and engineering experience;

[0027] If the membership function value y is close to 1, the corresponding detection value range is divided into the first level, which is usually the range where the detection value has little impact on the structural safety;

[0028] If the membership function value is in the middle range, the corresponding test value is classified into the second level, which means that the test value has begun to have some minor impact on the structural safety, but is still within the acceptable range;

[0029] If the membership function value y is close to 0, the corresponding detection value range is divided into the third level, which means that the detection value has begun to affect the structural safety and repair measures need to be taken.

[0030] Furthermore, the data display and storage module uses a visual interface to display the evaluation report, through which the test results, image data and safety detection evaluation level can be easily viewed. At the same time, the stored image data can be backed up and stored for a long time to provide historical data support for subsequent detection and analysis.

[0031] Furthermore, the system continuously accumulates and analyzes test data to establish a database of the appearance of bridge piers. Through statistical analysis of large amounts of data, the patterns and trends of changes in the appearance of piers can be discovered, providing a scientific basis for preventive maintenance and management of bridges.

[0032] Compared with the prior art, the present invention has the following beneficial effects:

[0033] 1. Used for image acquisition, it can quickly and comprehensively photograph the surface of bridge piers without manual climbing, greatly saving detection time;

[0034] 2. Since environmental factors such as lighting conditions and weather conditions will affect the clarity of the image and the accuracy of feature extraction, by recording these parameters, a more accurate evaluation of the detection results can be made;

[0035] 3. The automated processing flow of the system reduces the need for professional technicians and reduces human resource costs. At the same time, digital test results are easy to store and manage, reducing the cost of paper records and file management;

[0036] 4. Setting the safety inspection evaluation level according to the bell-shaped Gbel lmf membership function can scientifically divide the detection values ​​of each inspection item in the normal state, provide an accurate assessment of the safety status of the pier. The evaluation report includes the results and evaluation levels of various inspection indicators, providing a scientific basis for the maintenance and management of the bridge.

[0037] On the other hand, the present invention provides an appearance assessment method for bridge pier detection in an image, which is characterized by comprising the following steps:

[0038] S100: used to take all-round images of the bridge pier surface and record the environmental parameters during shooting;

[0039] S200: grayscale processing and image enhancement of the captured image;

[0040] S300: Extracting geometric features and texture features of bridge piers;

[0041] S300: Evaluate the crack width, crack length, crack depth, crack distribution density, honeycomb and pitting area, honeycomb and pitting depth, spalling area and spalling depth, and surface flatness of bridge piers;

[0042] S400: setting a first preset safety detection evaluation level, a second preset safety detection evaluation level and a third preset safety evaluation level in order from large to small, and dividing the detection values ​​of the normal state of each detection item into detection evaluation levels;

[0043] S500: Displaying an evaluation report and storing the acquired image data.

[0044] It is understandable that the above-mentioned image-based appearance assessment method and system for bridge pier detection have the same beneficial effects, which will not be described in detail here. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Various other advantages and benefits will become apparent to those of ordinary skill in the art by reading the detailed description of the preferred embodiments below. The accompanying drawings are only for the purpose of illustrating the preferred embodiments and are not to be considered as limiting the present invention. Moreover, the same reference symbols are used throughout the accompanying drawings to represent the same components. In the accompanying drawings:

[0046] Figure 1 A functional block diagram of an appearance assessment system for bridge pier detection based on an image provided by an embodiment of the present invention;

[0047] Figure 2 A flowchart of a method for appearance assessment of bridge pier detection in an image provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] Various exemplary embodiments of the present application will now be described in detail with reference to the accompanying drawings. It should be noted that unless otherwise specifically stated, the relative arrangement of components and steps, numerical expressions and numerical values ​​set forth in these embodiments do not limit the scope of the present application.

[0049] At the same time, it should be understood that for the convenience of description, the sizes of the various parts shown in the drawings are not drawn according to the actual proportional relationship.

[0050] The following description of at least one exemplary embodiment is merely illustrative in nature and is not intended to limit the present application, its application, or uses.

[0051] Technologies, methods, and equipment known to ordinary technicians in the relevant art may not be discussed in detail, but where appropriate, the technologies, methods, and equipment should be considered as part of the specification.

[0052] It should be noted that like reference numerals and letters refer to similar items in the following figures, and therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0053] In addition, the technical solutions between the various embodiments of the present application can be combined with each other, but it must be based on the fact that ordinary technicians in the field can implement it. When the combination of technical solutions is contradictory or cannot be implemented, it should be deemed that such combination of technical solutions does not exist and is not within the scope of protection required by this application.

[0054] It should be noted that all directional indications in the embodiments of the present application (such as up, down, left, right, front, back, etc.) are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture (as shown in the accompanying drawings). If the specific posture changes, the directional indication will also change accordingly.

[0055] Combine the following Figure 1 and Figure 2 Describe an appearance evaluation method and system for image - based bridge pier detection according to an exemplary embodiment of the present application. It should be noted that the following application scenarios are only shown for the convenience of understanding the spirit and principle of the present application, and the embodiments of the present application are not limited in this regard. On the contrary, the embodiments of the present application can be applied to any applicable scenario.

[0056] Refer to Figure 1 , in some embodiments of the present application, an appearance evaluation system for image - based bridge pier detection includes:

[0057] An image acquisition module, which is used to take all - around images of the surface of the bridge pier and record the environmental parameters during shooting;

[0058] An image pre - processing module, which performs grayscale processing and image enhancement on the captured images;

[0059] A feature extraction module, including geometric feature extraction and texture feature extraction;

[0060] An evaluation index determination and classification module, the evaluation indexes include the damage degree and surface flatness; for the damage degree, the detection items include crack width, crack length, crack depth, crack distribution density, honeycomb and pitted surface area, honeycomb and pitted surface depth, spalling area and spalling depth;

[0061] Record the safety status data as Si, i = 1, 2,..., 8;

[0062] The safety status data Si is the detection value of the i - th item to be detected, including: crack width S1, crack length S2, crack depth S3, crack distribution density S4, honeycomb and pitted surface area S5, honeycomb and pitted surface depth S6, spalling area S7 and spalling depth S8;

[0063] Preset an outlier determination threshold X, X > 0;

[0064] If Si < X, then it is judged that the quality of the detected bridge pier meets the standard;

[0065] If Si ≥ X, then it is judged that the quality of the detected bridge pier does not meet the standard;

[0066] For the surface flatness, obtain the point cloud data of the pier through 3D reconstruction technology, measure the height difference between each point, set the normal height value as h0, and record the height difference between each point as Δh;

[0067] If Δh < h0, then it is judged that the surface flatness of the pier meets the standard;

[0068] If Δh ≥ h0, then it is judged that the surface flatness of the pier does not meet the standard;

[0069] The safety detection evaluation level is set according to the bell-shaped Gbel lmf membership function, and the first preset safety detection evaluation level, the second preset safety detection evaluation level and the third preset safety evaluation level are set in order from large to small, and the detection values ​​of the normal state of each detection item are divided into detection evaluation levels, and an evaluation report is generated;

[0070] The data display and storage module is used to display the evaluation report and store the collected image data.

[0071] Specifically, it is used to capture all-round images of the surface of bridge piers, record the environmental parameters during shooting, perform grayscale processing and image enhancement on the captured images, extract the geometric features and texture features of the bridge piers, evaluate the crack width, crack length, crack depth, crack distribution density, honeycomb and pitting area, honeycomb and pitting depth, spalling area and spalling depth and surface flatness of the bridge piers, set the first preset safety detection evaluation level, the second preset safety detection evaluation level and the third preset safety evaluation level in descending order, divide the detection values ​​of the normal state of each of the detection items into detection evaluation levels, display the evaluation report, and store the collected image data.

[0072] It can be understood that the image acquisition can be used to quickly and comprehensively photograph the surface of the bridge pier without manual climbing, which greatly saves the detection time; since environmental factors such as lighting conditions and weather conditions will affect the clarity of the image and the accuracy of feature extraction, by recording these parameters, the detection results can be evaluated more accurately; the automated processing flow of the system reduces the demand for professional technicians and reduces human resource costs. At the same time, the digital detection results are easy to store and manage, reducing the cost of paper records and archive management; according to the bell-shaped Gbel lmf membership function, the safety detection evaluation level can be set, and the detection values ​​of the normal state of each detection item can be scientifically divided, providing an accurate evaluation of the safety status of the pier. The evaluation report contains the results and evaluation levels of various detection indicators, providing a scientific basis for the maintenance and management of the bridge.

[0073] Specifically, the image acquisition module sets the exposure time according to the collected environmental parameters. If there is sufficient natural light, a shorter exposure time is set; if the natural light is dim, the exposure time needs to be appropriately delayed.

[0074] It is understandable that in natural light conditions, if there is sufficient light, a shorter exposure time can be set to avoid overexposure of the image. In a darker environment, the exposure time needs to be appropriately extended, but care should be taken to avoid noise or blur in the image due to too long an exposure time. Generally speaking, the appropriate exposure time can be determined by test shooting based on factors such as the light intensity at the scene and the sensitivity of the camera.

[0075] Specifically, grayscale processing converts a color image into a grayscale image, where each pixel is represented by a grayscale value, forming a grayscale component image in the original image to reduce the amount of data.

[0076] Specifically, color images usually contain three channels: red (R), green (G), and blue (B), each of which has a corresponding pixel value, and the amount of data is relatively large. After converting a color image to a grayscale image, each pixel only needs to be represented by a grayscale value, which greatly reduces the amount of data. This helps to improve the efficiency of subsequent image processing and analysis, and speed up the running speed of feature extraction and evaluation algorithms.

[0077] It is understandable that some key features of the bridge pier surface, such as cracks, peeling and other defects, can also be clearly presented in the grayscale image. Through grayscale processing, the interference of color information is removed, and the shape and texture features that are closely related to appearance evaluation can be more focused, making subsequent analysis more accurate and convenient.

[0078] Specifically, after obtaining the grayscale component image in the original image, the CPLD processor performs grayscale value correction on the pixels of the grayscale component image according to the relative light and dark relationship between the pixels of the grayscale component image and the pixels in the grayscale component image after Gaussian smoothing, and synthesizes the grayscale component images that have undergone grayscale value correction to obtain an enhanced image.

[0079] Specifically, in the extraction of geometric features, a combination of multiple edge detection algorithms is used to extract the pier contour; in the process of texture feature extraction, grayscale co-occurrence matrix and local binary pattern are used, and the wavelet transform texture analysis method is also introduced. The wavelet transform can decompose the image at different scales and directions, thereby extracting richer texture information.

[0080] It is understandable that the combination of multiple edge detection algorithms can better cope with these different environmental conditions. When the lighting conditions are poor, one algorithm may misjudge due to its high sensitivity to grayscale changes, but another algorithm may still detect the edge relatively accurately in this case. By combining multiple algorithms, it can ensure that the pier contour can be extracted relatively stably and accurately in various complex environments, providing a reliable foundation for subsequent contour-based geometric feature analysis.

[0081] Specifically, for the bell-shaped Gbel lmf membership function Determine the values ​​of parameters a, b, and c based on the characteristics of each test item and engineering experience;

[0082] If the membership function value y is close to 1, the corresponding detection value range is divided into the first level, which is usually the range where the detection value has little impact on the structural safety;

[0083] If the membership function value is in the middle range, the corresponding test value is classified into the second level, which means that the test value has begun to have some minor impact on the structural safety, but is still within the acceptable range;

[0084] If the membership function value y is close to 0, the corresponding detection value range is divided into the third level, which means that the detection value has begun to affect the structural safety and repair measures need to be taken.

[0085] It is understandable that after the initial classification, the classification results need to be verified in combination with the actual engineering situation and previous test data. If it is found that the classification level does not match the actual safety status of the structure, for example, a pier is judged to be in a medium state according to the classification level, but actual on-site observations show that it has a greater safety hazard, it is necessary to adjust the parameters a, b, c of the membership function or the level boundary value.

[0086] Through continuous verification and optimization, the grade classification can more accurately reflect the actual safety status of bridge piers and provide a reliable basis for subsequent maintenance and management.

[0087] Specifically, the data display and storage module uses a visual interface to display the assessment report, through which the test results, image data and safety test evaluation levels can be easily viewed. At the same time, the stored image data can be backed up and preserved for a long time, providing historical data support for subsequent testing and analysis.

[0088] It is understandable that, based on the intuitive display, relevant personnel can make targeted decisions in a short period of time. For example, for piers with serious damage, they can decide to immediately carry out repair work; for piers with good safety conditions but slight changes in certain indicators, they can arrange subsequent regular monitoring plans, etc., thereby improving decision-making efficiency and ensuring the safe operation of the bridge.

[0089] Specifically, based on these historical image data, the system continuously accumulates and analyzes detection data to establish a database of the appearance conditions of bridge piers. Through statistical analysis of large amounts of data, the laws and trends of changes in the appearance of piers can be discovered, providing a scientific basis for preventive maintenance and management of bridges.

[0090] Reference Figure 2 In some embodiments of the present application, the appearance assessment method for bridge pier detection in an image is characterized by comprising the following steps:

[0091] S100: used to take all-round images of the bridge pier surface and record the environmental parameters during shooting;

[0092] S200: grayscale processing and image enhancement of the captured image;

[0093] S300: Extracting geometric features and texture features of bridge piers;

[0094] S300: Evaluate the crack width, crack length, crack depth, crack distribution density, honeycomb and pitting area, honeycomb and pitting depth, spalling area and spalling depth, and surface flatness of bridge piers;

[0095] S400: setting a first preset safety detection evaluation level, a second preset safety detection evaluation level and a third preset safety evaluation level in order from large to small, and dividing the detection values ​​of the normal state of each detection item into detection evaluation levels;

[0096] S500: Displaying an evaluation report and storing the acquired image data.

[0097] It is understandable that the above-mentioned image-based appearance assessment method and system for bridge pier detection have the same beneficial effects, which will not be described in detail here.

[0098] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. An image-based appearance assessment system for bridge pier detection, characterized in that: Including: The image acquisition module is used to take all-round images of the surface of the bridge pier column and record the environmental parameters at the time of shooting; The image preprocessing module is used to perform grayscale processing and image enhancement on the captured images; The geometric feature extraction module is used to extract the geometric features of the bridge pier column; The texture feature extraction module is used to extract the texture features of the bridge pier column; The evaluation index determination and classification module is used to evaluate and classify the features of the bridge pier column after extraction. The evaluation indexes include the damage degree and the surface flatness; for the damage degree, the detection items include crack width, crack length, crack depth, crack distribution density, honeycomb and pitted surface area, honeycomb and pitted surface depth, spalling area and spalling depth; Denote the safety state data as Si, where i = 1, 2,..., 8; The safety state data Si is the detection value of the i-th item to be detected, including: crack width S1, crack length S2, crack depth S3, crack distribution density S4, honeycomb and pitted surface area S5, honeycomb and pitted surface depth S6, spalling area S7 and spalling depth S8; Preset an outlier determination threshold X, where X > 0; If Si < X, it is judged that the quality of the detected bridge pier column meets the standard; If Si ≥ X, it is judged that the quality of the detected bridge pier column does not meet the standard; For the surface flatness, the point cloud data of the pier column is obtained through 3D reconstruction technology, the height difference between each point is measured, the normal height value is set as h0, and the height difference between each point is denoted as Δh; If Δh < h0, it is judged that the surface flatness of the pier column meets the standard; If Δh ≥ h0, it is judged that the surface flatness of the pier column does not meet the standard; Set the safety detection evaluation grades according to the bell-shaped Gbell lmf membership function. The first preset safety detection evaluation grade, the second preset safety detection evaluation grade and the third preset safety evaluation grade are set in descending order. The detection values in the normal state of each detection item are divided into detection evaluation grades, and an evaluation report is generated; The data display and storage module is used to display the evaluation report and store the collected image data.

2. The appearance evaluation system for bridge pier detection based on an image according to claim 1, characterized in that: The image acquisition module sets the exposure time according to the collected environmental parameters. If the natural light is sufficient, a shorter exposure time is set; if the natural light is dim, the exposure time needs to be appropriately delayed.

3. The appearance evaluation system for bridge pier detection based on an image according to claim 1, characterized in that: The grayscale processing converts the color image into a grayscale image, and each pixel is represented by a grayscale value to form a grayscale component image in the original image, which is used to reduce the data volume.

4. The appearance evaluation system for bridge pier detection based on an image according to claim 1, characterized in that: After obtaining the grayscale component image in the original image, through the CPLD processor, according to the relative brightness relationship between the pixel points of the grayscale component image and the pixel points of the grayscale component image after Gaussian smoothing, the pixel points of the grayscale component image are corrected for grayscale values, and the grayscale component image after grayscale value correction is synthesized to obtain an enhanced image.

5. The appearance evaluation system for bridge pier detection based on an image according to claim 1, characterized in that: In the geometric feature extraction, a combination of multiple edge detection algorithms is used to extract the pier column contour; in the texture feature extraction process, grayscale co-occurrence matrix and local binary pattern are used, and a wavelet transform texture analysis method is introduced. The wavelet transform can decompose the image at different scales and directions, thereby extracting richer texture information.

6. The appearance evaluation system for bridge pier detection based on an image according to claim 1, characterized in that: For the bell-shaped Gbel lmf membership function Determine the values ​​of parameters a, b, and c based on the characteristics of each test item and engineering experience; If the membership function value y is close to 1, the corresponding detection value range is divided into the first level, which is usually the range where the detection value has little impact on the structural safety; If the membership function value is in the middle range, the corresponding test value is classified into the second level, which means that the test value has begun to have some minor impact on the structural safety, but is still within the acceptable range; If the membership function value y is close to 0, the corresponding detection value range is divided into the third level, which means that the detection value has begun to affect the structural safety and repair measures need to be taken.

7. The appearance evaluation system for bridge pier detection based on an image according to claim 1, characterized in that: The data display and storage module uses a visual interface to display the evaluation report, through which various test results, image data and safety test evaluation levels can be easily viewed. At the same time, the stored image data can be backed up and stored for a long time to provide historical data support for subsequent testing and analysis.

8. The appearance evaluation system for bridge pier detection based on an image according to claim 1, characterized in that: The system continuously accumulates and analyzes test data to establish a database of the appearance of bridge piers. Through statistical analysis of large amounts of data, the patterns and trends of changes in the appearance of piers can be discovered, providing a scientific basis for preventive maintenance and management of bridges.

9. An image-based appearance assessment method for bridge pier detection, characterized in that: The following steps are involved: S100: used to take all-round images of the bridge pier surface and record the environmental parameters during shooting; S200: grayscale processing and image enhancement of the captured image; S300: Extracting geometric features and texture features of bridge piers; S300: Evaluate the crack width, crack length, crack depth, crack distribution density, honeycomb and pitting area, honeycomb and pitting depth, spalling area and spalling depth, and surface flatness of bridge piers; S400: setting a first preset safety detection evaluation level, a second preset safety detection evaluation level and a third preset safety evaluation level in order from large to small, and dividing the detection values ​​of the normal state of each detection item into detection evaluation levels; S500: Displaying an evaluation report and storing the acquired image data.

Images