Evaluation method and system for high support frame structure

Abstract

The invention discloses an evaluation method and system for a high support frame structure, and relates to the technical field of support frames, and the method comprises the steps: collecting a support frame image of a to-be-evaluated high support frame, carrying out the image segmentation, and obtaining a plurality of frame region images; performing horizontal deviation analysis and vertical deviation analysis on the plurality of frame area images to obtain a plurality of horizontal deviation degrees and a plurality of vertical deviation degrees; based on the multiple horizontal deviation degrees and the multiple vertical deviation degrees, the horizontal compliance degree and the vertical compliance degree of the high supporting frame are obtained through analysis; calculating the compliance of the high support frame according to the horizontal compliance and the vertical compliance, and performing correction calculation according to the height of the high support frame to obtain a corrected compliance; and based on the correction compliance, evaluating to obtain the safety level of the high support frame. According to the invention, the technical problem of inaccurate safety quality evaluation of the high support frame in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of support frames, and in particular to an evaluation method and system for a high support frame structure. Background Art

[0002] The support frame is a structure that supports the main body of the building during the construction process. For example, it is used to support steel bars, plates, and precast cement panels to provide stable support for the construction of the building. The support frame needs to have a stable support capacity to ensure the quality of construction and support. As the height of the building increases, a higher support frame is needed for support. A higher support frame has the risk of unstable support. The existing technology requires an assessment of the stability and safety of the support frame, which is generally conducted by relevant technical personnel, and there are inaccurate technical problems. Summary of the invention

[0003] The present application provides a method and system for evaluating a high support frame structure, which are used to solve the technical problem of inaccurate safety evaluation of high support frames in the prior art.

[0004] In view of the above problems, the present application provides a method and system for evaluating a high support frame structure.

[0005] In a first aspect of the present application, a method for evaluating a high support frame structure is provided, the method comprising:

[0006] Acquire an image of a high support frame to be evaluated to obtain a support frame image;

[0007] Performing image segmentation on the support frame image to obtain a plurality of frame area images;

[0008] Performing horizontal deviation analysis and vertical deviation analysis on the multiple frame area images to obtain multiple horizontal deviation degrees and multiple vertical deviation degrees;

[0009] Based on the multiple horizontal deviations and the multiple vertical deviations, analyzing and obtaining the horizontal compliance and the vertical compliance of the high support frame;

[0010] The compliance of the high support frame is calculated according to the horizontal compliance and the vertical compliance, and a correction calculation is performed according to the height of the high support frame to obtain a corrected compliance;

[0011] Based on the revised compliance, the safety level of the high support frame is evaluated.

[0012] A second aspect of the present application provides an evaluation system for a high support frame structure, the system comprising:

[0013] A support frame image acquisition module, used to acquire an image of a high support frame to be evaluated, and obtain a support frame image;

[0014] An image segmentation module, used to perform image segmentation on the support frame image to obtain a plurality of frame area images;

[0015] A horizontal and vertical deviation analysis module, used for performing horizontal deviation analysis and vertical deviation analysis on the multiple frame area images to obtain multiple horizontal deviation degrees and multiple vertical deviation degrees;

[0016] A compliance analysis module, configured to analyze and obtain the horizontal compliance and vertical compliance of the high support frame based on the multiple horizontal deviations and the multiple vertical deviations;

[0017] A compliance correction module, used to calculate the compliance of the high support frame according to the horizontal compliance and the vertical compliance, and perform correction calculation according to the height of the high support frame to obtain a corrected compliance;

[0018] A safety assessment module is used to assess and obtain a safety level of the high support frame based on the revised compliance.

[0019] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0020] The present application acquires images of a high support frame to be evaluated, performs image segmentation on the support frame images, obtains multiple frame area images, performs horizontal deviation analysis and vertical deviation analysis on the multiple frame area images, obtains multiple horizontal deviations and multiple vertical deviations, and then analyzes and obtains the horizontal compliance and vertical compliance of the high support frame, calculates the compliance of the high support frame based on the horizontal compliance and vertical compliance, and performs correction calculation based on the height of the high support frame to obtain the corrected compliance, and finally evaluates and obtains the safety level of the high support frame. The embodiment of the present application acquires images of the high support frame through image processing technology, performs image segmentation, analyzes the horizontal deviation and vertical deviation of the images in multiple frame areas respectively, and then analyzes the compliance of the support frame to perform safety assessment, thereby realizing automated support frame safety assessment and achieving the technical effect of improving the accuracy and reliability of support frame safety assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. 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 creative work.

[0022] Figure 1 A schematic diagram of a flow chart of an evaluation method for a high support frame structure provided in an embodiment of the present application;

[0023] Figure 2 A schematic diagram of the structure of an evaluation system for a high support frame structure provided in an embodiment of the present application.

[0024] Explanation of the reference numerals: support frame image acquisition module 11 , image segmentation module 12 , horizontal and vertical deviation analysis module 13 , compliance analysis module 14 , compliance correction module 15 , safety assessment module 16 . DETAILED DESCRIPTION

[0025] The present application provides a method and system for evaluating a high support frame structure, which is used to solve the technical problem of inaccurate safety evaluation of high support frames in the prior art.

[0026] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0027] It should be noted that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or server that includes a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or modules that are not explicitly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] like Figure 1 As shown, the present application provides a method for evaluating a high support frame structure, wherein the method comprises:

[0030] S100: Acquire an image of a high support frame to be evaluated to obtain a support frame image;

[0031] In the embodiment of the present application, the high support frame to be evaluated is a relatively high support frame that has been built, for example, a support frame that has been built in a building and is waiting for construction, and a safety analysis of the high support frame is required.

[0032] An image of the high support frame is acquired to obtain a support frame image. Exemplarily, the image of the high support frame is acquired in the center direction directly in front of the high support frame to avoid image distortion affecting the accuracy of subsequent image processing.

[0033] Optionally, images of multiple parts of the high support frame may be collected separately, and image fusion may be performed to obtain an image of the high support frame.

[0034] S200: performing image segmentation on the support frame image to obtain a plurality of frame region images;

[0035] In the embodiment of the present application, the high support frame is generally constructed by connecting multiple horizontal and vertical support tubes to form multiple rectangular areas as multiple frame areas. By analyzing the stability of the support frame in multiple frame areas respectively, the overall safety of the high support frame can be analyzed.

[0036] In the embodiment of the present application, the image of the support frame is segmented into a plurality of frame region images of a plurality of frame regions, so as to analyze the quality of the support frame respectively.

[0037] The image of the support frame may be segmented based on any image segmentation means in the prior art to obtain a plurality of frame area images.

[0038] Step S200 in the method provided in the embodiment of the present application includes:

[0039] Based on multiple sample high support frames, a sample support frame image set is acquired;

[0040] Performing image segmentation on each sample support frame image in the sample support frame image set to obtain a plurality of sample frame region image sets;

[0041] Using the sample support frame image set and multiple sample frame region image sets, construct a support frame image segmentor;

[0042] The support frame image segmentor is used to perform image segmentation on the support frame image to obtain the multiple frame area images.

[0043] Step S200 in the method provided in the embodiment of the present application includes:

[0044] Based on multiple sample high support frames, a sample support frame image set is acquired;

[0045] Performing image segmentation on each sample support frame image in the sample support frame image set to obtain a plurality of sample frame region image sets;

[0046] Using the sample support frame image set and multiple sample frame region image sets, construct a support frame image segmentor;

[0047] The support frame image segmentor is used to perform image segmentation on the support frame image to obtain the multiple frame area images.

[0048] In the embodiment of the present application, based on the historical data of the support frame construction, multiple other high support frames are obtained as multiple sample high support frames for collecting sample data. The support frame images of the multiple sample high support frames are collected to obtain a sample support frame image set.

[0049] Based on manual image segmentation and annotation, each sample support frame image in the sample support frame image set is segmented, specifically, each sample support frame image is segmented into multiple rectangular frame area images as a sample frame area image set, and multiple sample frame area image sets are obtained. Each sample frame area image set includes sample frame area images of multiple frame areas of a sample high support frame.

[0050] The sample support frame image set and multiple sample frame region image sets are used to construct a support frame image segmentor for segmenting the support frame image into multiple frame region images. Exemplarily, the support frame image segmentor is constructed based on machine learning.

[0051] Based on the constructed support frame image segmentor, the support frame image of the current high support frame is input into the support frame image segmentor for image segmentation, and the image is segmented into multiple frame area images to obtain multiple frame area images.

[0052] In an embodiment of the present application, the sample support frame image set and multiple sample frame region image sets are used to construct a support frame image segmentor, including:

[0053] Based on semantic segmentation, construct an encoding unit and a decoding unit in the support frame image segmentor;

[0054] The sample support frame image set and multiple sample frame region image sets are used to train the encoding unit and the decoding unit until convergence requirements are met, thereby obtaining a support frame image segmentor.

[0055] In an embodiment of the present application, based on semantic segmentation in machine learning, an encoding unit and a decoding unit are constructed in the support frame image segmentor, wherein the encoding unit and the decoding unit are the encoder and the decoder in semantic segmentation, respectively including multiple layers of convolutional layers, pooling layers and fully connected layers, as well as multiple layers of deconvolutional layers, depooling layers and fully connected layers, which can extract feature information in the image, classify it into a category of pre-identified frame areas according to the feature information, and then classify all pixels in the support frame image into categories of multiple frame areas to complete image segmentation.

[0056] The sample support frame image set and multiple sample frame area image sets are used to perform supervised training on the encoding unit and the decoding unit. During the training process, the network parameters are adjusted and updated according to the deviation between the actual output and the sample data until the convergence requirements are met, for example, the accuracy rate is greater than or equal to 85%, thereby obtaining a trained support frame image segmentor.

[0057] The embodiment of the present application constructs a support frame image segmentor for segmenting the support frame image based on semantic segmentation, and intelligently and automatically segments the support frame image, thereby facilitating the evaluation of the support frame in multiple frame areas, thereby improving the evaluation accuracy.

[0058] S300: performing horizontal deviation analysis and vertical deviation analysis on the multiple frame area images to obtain multiple horizontal deviation degrees and multiple vertical deviation degrees;

[0059] In the embodiment of the present application, based on the multiple frame area images obtained by segmentation, horizontal deviation analysis and vertical deviation analysis are performed respectively, specifically analyzing the deviation of the support tube in the bracket frame from the horizontal direction or the vertical direction in each frame area image. Exemplarily, the support tube is, for example, a steel tube, and the deviation is, for example, a deviation angle.

[0060] Due to installation errors or other factors, the support tube may deviate to a certain extent. The deviation of the support tube will cause the stability and safety of the high support frame to decrease. Therefore, the high support frame is evaluated based on the analysis of the deviation.

[0061] In the embodiments of the present application, machine vision and other means are used to automatically and intelligently perform horizontal deviation analysis and vertical deviation analysis on multiple frame area images to improve analysis accuracy and efficiency.

[0062] Step S300 in the method provided in the embodiment of the present application includes:

[0063] Acquire a sample frame area image set, and perform horizontal deviation and vertical deviation evaluation to obtain a sample horizontal deviation degree set and a sample vertical deviation degree set;

[0064] Based on a convolutional neural network, a horizontal deviation analyzer is constructed according to the sample frame area image set and the sample horizontal deviation degree set;

[0065] Based on the convolutional neural network, a vertical deviation analyzer is constructed according to the sample frame area image set and the sample vertical deviation degree set, and a frame deviation analysis model is obtained by combining the horizontal deviation analyzer;

[0066] The multiple frame area images are input into the frame deviation analysis model to obtain the multiple horizontal deviations and the multiple vertical deviations.

[0067] Among them, based on other sample high support frames built in historical time and based on the methods in the aforementioned content, a set of sample frame area images is collected and acquired, and in each sample frame area image, the horizontal deviation and vertical deviation of the support tubes in the horizontal and vertical directions are evaluated to obtain the sample horizontal deviation set and the sample vertical deviation set as the construction data for intelligent horizontal deviation and vertical deviation.

[0068] Based on the convolutional neural network, the network structure of the horizontal deviation analyzer is constructed with the frame area image as input and the horizontal deviation as output. Then, the horizontal deviation analyzer is trained and updated according to the sample frame area image set and the sample horizontal deviation set as training data until the convergence requirements are met.

[0069] Similarly, based on the convolutional neural network, the frame area image is used as input and the vertical deviation is used as output to construct a network structure of the vertical deviation analyzer. Then, the vertical deviation analyzer is trained and updated based on the sample frame area image set and the sample vertical deviation set as training data until the convergence requirements are met.

[0070] Based on the constructed horizontal deviation analyzer and vertical deviation analyzer, a frame deviation analysis model for performing horizontal and vertical deviation analysis of a support frame according to a frame area image is obtained.

[0071] Based on the constructed frame deviation analysis model, multiple frame area images obtained by segmenting the current image are input into the frame deviation analysis model, specifically into the horizontal deviation analyzer and the vertical deviation analyzer, respectively, to perform horizontal and vertical deviation analysis to obtain multiple horizontal deviation degrees and multiple vertical deviation degrees.

[0072] In the embodiment of the present application, horizontal and vertical analysis is performed based on multiple frame area images obtained by image segmentation based on machine learning to analyze the offset problems existing in the high support frame structure, improve the accuracy of the analysis of the stability and safety of the high support frame, and improve efficiency.

[0073] S400: Analyze and obtain the horizontal compliance and vertical compliance of the high support frame based on the multiple horizontal deviations and the multiple vertical deviations;

[0074] In the embodiment of the present application, the horizontal compliance and vertical compliance of the high support frame are analyzed and obtained according to the multiple horizontal deviations and the multiple vertical deviations. The horizontal compliance and the vertical compliance are specifically information on the degree to which the support frame meets the preset requirements in the horizontal direction and the vertical direction, for example, percentage information. The smaller the multiple horizontal deviations and the multiple vertical deviations, the greater the horizontal compliance and the vertical compliance, and the more the structure of the high support frame meets the requirements.

[0075] Step S400 in the method provided in the embodiment of the present application includes:

[0076] Based on the positions of the plurality of frame region images in the support frame image, a plurality of frame region weights are allocated and obtained, wherein a frame region image with a higher position has a greater frame region weight;

[0077] Using the multiple frame area weights, weighted calculation is performed on the multiple horizontal deviations and the multiple vertical deviations to obtain a comprehensive horizontal deviation and a comprehensive vertical deviation;

[0078] According to the comprehensive horizontal deviation and the comprehensive vertical deviation, the horizontal compliance and the vertical compliance are calculated and obtained.

[0079] In the embodiment of the present application, frame areas at different positions have different effects on the stability of the high support frame, and the stability of the higher frame area has a greater effect on the overall stability of the high support frame. According to the positions of multiple frame area images in the support frame image, multiple frame area weights are allocated and obtained, wherein the frame area weight of the frame area image at a higher position is greater. Exemplarily, multiple frame area weights can be allocated and calculated based on the height distance of multiple frame areas.

[0080] The multiple frame area weights are used to perform weighted calculation on the multiple horizontal deviations and the multiple vertical deviations to obtain the overall comprehensive horizontal deviation and comprehensive vertical deviation of the high support frame.

[0081] Based on the comprehensive horizontal deviation and the comprehensive vertical deviation, the horizontal compliance and the vertical compliance are calculated. For example, based on the deviation angles within the comprehensive horizontal deviation and the comprehensive vertical deviation, the ratio to 90 degrees is calculated as the deviation percentage, and 1 minus the deviation percentage is used as the comprehensive horizontal deviation and the comprehensive vertical deviation.

[0082] The embodiment of the present application performs weighted calculation on multiple horizontal deviations and multiple vertical deviations of multiple frame areas according to the heights of the frame areas formed at different positions of the high support frame, and calculates the horizontal compliance and vertical compliance of the entire high support frame, combined with the characteristics of the high support frame having a high ceiling, to improve the reliability of the overall safety assessment of the high support frame.

[0083] S500: Calculating the compliance of the high support frame according to the horizontal compliance and the vertical compliance, and performing correction calculation according to the height of the high support frame to obtain a corrected compliance;

[0084] In the embodiment of the present application, a weighted calculation is performed based on the horizontal compliance and the vertical compliance to obtain the overall compliance of the high support frame and obtain the compliance.

[0085] Furthermore, the higher the support frame is, the greater the probability of the hidden danger of unstable support and the greater the impact after an accident occurs. Therefore, the embodiment of the present application corrects the compliance according to the height of the high support frame, so that the compliance is affected by the height of the high support frame and is more accurate.

[0086] Step S500 in the method provided in the embodiment of the present application includes:

[0087] Acquiring height information of the high support frame;

[0088] Obtain the average height information of multiple sample high support frames;

[0089] The compliance is corrected and calculated based on the height information and the average height information to obtain a corrected compliance.

[0090] The height information of the high support frame is obtained. Furthermore, the sample height information of other multiple sample high support frames is obtained, and the mean is calculated to obtain the average height information.

[0091] According to the height information and the average height information, the compliance is corrected and calculated to obtain a corrected compliance. Exemplarily, according to the inverse of the ratio of the height information to the average height information, the compliance is multiplied and corrected, so that the compliance of a high support frame with a height greater than the average height information is smaller, which is more in line with the actual situation of the high support frame quality assessment and more accurate.

[0092] S600: Based on the modified compliance, evaluate and obtain the safety level of the high support frame.

[0093] In the embodiment of the present application, based on the revised compliance, a safety assessment of the current high support frame is performed, and the safety level is specifically assessed to reflect the quality level of the high support frame.

[0094] S600 in the method provided in the embodiment of the present application includes:

[0095] Obtain a sample correction compliance set, and obtain a sample security level set;

[0096] Using the sample correction compliance set and the sample safety level set, based on a decision tree, a safety assessment decision maker is constructed;

[0097] The security assessment decision maker is used to assess and decide on the revised compliance to obtain the security level.

[0098] Among them, for multiple sample high support frames, compliance analysis, calculation and correction are performed based on the method in the above content to obtain a sample correction compliance set. And the multiple sample high support frames are evaluated and labeled for safety level to obtain a sample safety level set. The evaluation of the sample safety level can be obtained based on relevant industry standards or engineer evaluation. Exemplarily, the sample safety level can be 10 levels from 1 to 10, which is positively correlated with the size of the sample correction compliance.

[0099] The sample modified compliance set and the sample security level set are used as construction data, and a security assessment decision maker is constructed based on a decision tree. The modified compliance is used as decision data, and the security level is used as the decision result for construction. Exemplarily, the sample modified compliance set is used to construct a multi-layer decision node, each layer of decision node includes a modified compliance, and the modified compliance of the input decision node is discriminated and classified, and through multi-layer classification, the security level corresponding to the input modified compliance is obtained.

[0100] Based on the constructed safety assessment decision maker, the current revised compliance is input to make an assessment decision, obtain the safety level, and complete the safety quality assessment of the high support frame.

[0101] In summary, the embodiments of the present application have at least the following technical effects:

[0102] The embodiment of the present application acquires an image of a high support frame to be evaluated, performs image segmentation on the image of the support frame, obtains multiple frame area images, performs horizontal deviation analysis and vertical deviation analysis on the multiple frame area images, obtains multiple horizontal deviations and multiple vertical deviations, and then analyzes and obtains the horizontal compliance and vertical compliance of the high support frame, calculates the compliance of the high support frame based on the horizontal compliance and vertical compliance, and performs correction calculation based on the height of the high support frame to obtain the corrected compliance, and finally evaluates and obtains the safety level of the high support frame. The embodiment of the present application acquires an image of the high support frame through image processing technology, performs image segmentation, analyzes the horizontal deviation and vertical deviation of the images in multiple frame areas respectively, and then analyzes the compliance of the support frame to perform safety assessment, thereby realizing automated support frame safety assessment and achieving the technical effect of improving the accuracy and reliability of support frame safety assessment.

[0103] Embodiment 2

[0104] Based on the same inventive concept as the evaluation method of a high support frame structure in the above-mentioned embodiment, Figure 2 As shown, the present application provides an evaluation system for a high support frame structure, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0105] A support frame image acquisition module 11 is used to acquire an image of a high support frame to be evaluated to obtain a support frame image;

[0106] An image segmentation module 12 is used to segment the support frame image to obtain a plurality of frame region images;

[0107] A horizontal and vertical deviation analysis module 13 is used to perform horizontal deviation analysis and vertical deviation analysis on the multiple frame area images to obtain multiple horizontal deviation degrees and multiple vertical deviation degrees;

[0108] A compliance analysis module 14, configured to analyze and obtain the horizontal compliance and vertical compliance of the high support frame based on the multiple horizontal deviations and the multiple vertical deviations;

[0109] A compliance correction module 15, configured to calculate the compliance of the high support frame according to the horizontal compliance and the vertical compliance, and perform correction calculation according to the height of the high support frame to obtain a corrected compliance;

[0110] The safety assessment module 16 is used to assess and obtain the safety level of the high support frame based on the modified compliance.

[0111] Furthermore, the image segmentation module 12 is used to perform the following steps:

[0112] Based on multiple sample high support frames, a sample support frame image set is acquired;

[0113] Performing image segmentation on each sample support frame image in the sample support frame image set to obtain a plurality of sample frame region image sets;

[0114] Using the sample support frame image set and multiple sample frame region image sets, construct a support frame image segmentor;

[0115] The support frame image segmentor is used to perform image segmentation on the support frame image to obtain the multiple frame area images.

[0116] The sample support frame image set and a plurality of sample frame region image sets are used to construct a support frame image segmentor, including:

[0117] Based on semantic segmentation, construct an encoding unit and a decoding unit in the support frame image segmentor;

[0118] The sample support frame image set and multiple sample frame region image sets are used to train the encoding unit and the decoding unit until convergence requirements are met, thereby obtaining a support frame image segmentor.

[0119] Furthermore, the horizontal and vertical deviation analysis module 13 is used to perform the following steps:

[0120] Acquire a sample frame area image set, and perform horizontal deviation and vertical deviation evaluation to obtain a sample horizontal deviation degree set and a sample vertical deviation degree set;

[0121] Based on a convolutional neural network, a horizontal deviation analyzer is constructed according to the sample frame area image set and the sample horizontal deviation degree set;

[0122] Based on the convolutional neural network, a vertical deviation analyzer is constructed according to the sample frame area image set and the sample vertical deviation degree set, and a frame deviation analysis model is obtained by combining the horizontal deviation analyzer;

[0123] The multiple frame area images are input into the frame deviation analysis model to obtain the multiple horizontal deviations and the multiple vertical deviations.

[0124] Furthermore, the compliance analysis module 14 is used to perform the following steps:

[0125] Based on the positions of the plurality of frame region images in the support frame image, a plurality of frame region weights are allocated and obtained, wherein a frame region image with a higher position has a greater frame region weight;

[0126] Using the multiple frame area weights, weighted calculation is performed on the multiple horizontal deviations and the multiple vertical deviations to obtain a comprehensive horizontal deviation and a comprehensive vertical deviation;

[0127] According to the comprehensive horizontal deviation and the comprehensive vertical deviation, the horizontal compliance and the vertical compliance are calculated and obtained.

[0128] Furthermore, the compliance correction module 15 is used to perform the following steps:

[0129] Obtain the average height information of multiple sample high support frames;

[0130] The compliance is corrected and calculated based on the height information and the average height information to obtain a corrected compliance.

[0131] Furthermore, the security assessment module 16 is used to perform the following steps:

[0132] Obtain a sample correction compliance set, and obtain a sample security level set;

[0133] Using the sample correction compliance set and the sample safety level set, based on a decision tree, a safety assessment decision maker is constructed;

[0134] The security assessment decision maker is used to assess and decide on the revised compliance to obtain the security level.

[0135] It should be noted that the above-mentioned sequence of the embodiments of the present application is only for description and does not represent the advantages and disadvantages of the embodiments. And the above-mentioned specific embodiments of this specification are described. Other embodiments are within the scope of the attached claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0136] The above description is only a preferred embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

[0137] This specification and drawings are merely exemplary illustrations of the present application and are deemed to cover any and all modifications, variations, combinations or equivalents within the scope of the present application. Obviously, a person skilled in the art may make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application fall within the scope of the present application and its equivalents, the present application intends to include these modifications and variations.

Claims

1. A method for evaluating a high support frame structure, characterized in that: The method comprises: Acquire an image of a high support frame to be evaluated to obtain a support frame image; Performing image segmentation on the support frame image to obtain a plurality of frame region images; Performing horizontal deviation analysis and vertical deviation analysis on the multiple frame area images to obtain multiple horizontal deviation degrees and multiple vertical deviation degrees; Based on the multiple horizontal deviations and the multiple vertical deviations, analyzing and obtaining the horizontal compliance and the vertical compliance of the high support frame; The compliance of the high support frame is calculated according to the horizontal compliance and the vertical compliance, and a correction calculation is performed according to the height of the high support frame to obtain a corrected compliance; Based on the revised compliance, the safety level of the high support frame is evaluated.

2. The method according to claim 1, characterized in that Performing image segmentation on the support frame image to obtain a plurality of frame region images, including: Based on multiple sample high support frames, a sample support frame image set is acquired; Performing image segmentation on each sample support frame image in the sample support frame image set to obtain a plurality of sample frame region image sets; Using the sample support frame image set and multiple sample frame region image sets, construct a support frame image segmentor; The support frame image segmentor is used to perform image segmentation on the support frame image to obtain the multiple frame area images.

3. The method according to claim 2, characterized in that The sample support frame image set and a plurality of sample frame region image sets are used to construct a support frame image segmentor, comprising: Based on semantic segmentation, construct an encoding unit and a decoding unit in the support frame image segmentor; The sample support frame image set and multiple sample frame region image sets are used to train the encoding unit and the decoding unit until convergence requirements are met, thereby obtaining a support frame image segmentor.

4. The method according to claim 1, characterized in that: Performing horizontal deviation analysis and vertical deviation analysis on the multiple frame area images to obtain multiple horizontal deviations and multiple vertical deviations includes: Acquire a sample frame area image set, and perform horizontal deviation and vertical deviation evaluation to obtain a sample horizontal deviation degree set and a sample vertical deviation degree set; Based on a convolutional neural network, a horizontal deviation analyzer is constructed according to the sample frame area image set and the sample horizontal deviation degree set; Based on the convolutional neural network, a vertical deviation analyzer is constructed according to the sample frame area image set and the sample vertical deviation degree set, and a frame deviation analysis model is obtained by combining the horizontal deviation analyzer; The plurality of frame area images are input into the frame deviation analysis model to obtain the plurality of horizontal deviations and the plurality of vertical deviations.

5. The method according to claim 1, characterized in that Based on the multiple horizontal deviations and the multiple vertical deviations, analyzing and obtaining the horizontal compliance and the vertical compliance of the high support frame includes: Based on the positions of the plurality of frame region images in the support frame image, a plurality of frame region weights are allocated and obtained, wherein a frame region image with a higher position has a greater frame region weight; Using the multiple frame area weights, weighted calculation is performed on the multiple horizontal deviations and the multiple vertical deviations to obtain a comprehensive horizontal deviation and a comprehensive vertical deviation; According to the comprehensive horizontal deviation and the comprehensive vertical deviation, the horizontal compliance and the vertical compliance are calculated and obtained.

6. The method according to claim 1, characterized in that The compliance of the high support frame is calculated according to the horizontal compliance and the vertical compliance, and a correction calculation is performed according to the height of the high support frame to obtain the corrected compliance, including: Acquiring height information of the high support frame; Obtain the average height information of multiple sample high support frames; The compliance is corrected and calculated based on the height information and the average height information to obtain a corrected compliance.

7. The method according to claim 1, characterized in that Based on the modified compliance, the safety level of the high support frame is evaluated, including: Obtain a sample correction compliance set, and obtain a sample security level set; Using the sample correction compliance set and the sample safety level set, based on a decision tree, a safety assessment decision maker is constructed; The security assessment decision maker is used to assess and decide on the revised compliance to obtain the security level.

8. An evaluation system for a high support frame structure, characterized in that: The system comprises: A support frame image acquisition module, used to acquire an image of a high support frame to be evaluated, and obtain a support frame image; An image segmentation module, used to perform image segmentation on the support frame image to obtain a plurality of frame area images; A horizontal and vertical deviation analysis module, used for performing horizontal deviation analysis and vertical deviation analysis on the multiple frame area images to obtain multiple horizontal deviation degrees and multiple vertical deviation degrees; A compliance analysis module, configured to analyze and obtain the horizontal compliance and vertical compliance of the high support frame based on the multiple horizontal deviations and the multiple vertical deviations; A compliance correction module, used to calculate the compliance of the high support frame according to the horizontal compliance and the vertical compliance, and perform correction calculation according to the height of the high support frame to obtain a corrected compliance; A safety assessment module is used to assess and obtain a safety level of the high support frame based on the revised compliance.

Images