An intelligent remote security monitoring system for construction engineering

Abstract

The application discloses a kind of building engineering intelligent remote security monitoring systems, it is related to building engineering technical field, including monitoring time period acquisition module, image data packet to be analyzed acquisition module, image processing module and abnormal monitoring module, it solves the technical problem that the safety monitoring system of current unmanned aerial vehicle is more simple for the judgment and analysis of shielding condition, it is difficult to accurately judge shielding, by quantitative analysis to shielding area and the complex coefficient calculation of shielding boundary line, image can be analyzed in real time to unmanned aerial vehicle shooting, shielding area abnormal block and shielding boundary abnormal block are quickly marked, the abnormal change of shielding area can be accurately identified, the accuracy and sensitivity of abnormal detection are improved, security risks can be eliminated in time, ensure the construction safety of construction site.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of building engineering, and specifically relates to an intelligent remote security monitoring system for building engineering. BACKGROUND

[0002] Safety monitoring of a construction site is an important link to ensure construction safety. The traditional security monitoring system mainly relies on fixed cameras for real-time monitoring. However, due to the complex environment of the construction site, there are a large number of obstructions such as building materials, equipment, and temporary facilities, resulting in many blind spots in monitoring and making it difficult to fully cover the construction area. In addition, the traditional monitoring system lacks the ability to dynamically analyze changes in the blocked area and cannot timely detect potential safety hazards caused by abnormal accumulation of obstructions or equipment failure.

[0003] In recent years, with the rapid development of unmanned aerial vehicles, unmanned aerial vehicles have been widely used in the monitoring field of construction sites. Unmanned aerial vehicles can flexibly fly and capture image data of the construction site from multiple angles and all directions, effectively making up for the shortcomings of fixed cameras.

[0004] However, although the image data captured by the existing unmanned aerial vehicles has a wide coverage, it lacks quantitative analysis of the blocked area and cannot accurately determine whether the change in the blocked area is normal. It also lacks accurate calculation and dynamic analysis of the area and boundary changes of the blocked area, making it difficult to accurately determine whether the obstruction is abnormal and unable to timely and effectively take measures to improve the monitoring effect and eliminate safety hazards. Based on this, an intelligent remote security monitoring system for building engineering is proposed. SUMMARY

[0005] The purpose of the present application is to provide an intelligent remote security monitoring system for building engineering, which solves the technical problem that the existing safety monitoring system of unmanned aerial vehicles is relatively simple in judging and analyzing the blocking condition and is difficult to accurately determine whether the obstruction is abnormal.

[0006] An intelligent remote security monitoring system for building engineering, comprising:

[0007] A monitoring period acquisition module obtains a plurality of monitoring periods corresponding to a construction site;

[0008] A to-be-analyzed image data packet acquisition module acquires a plurality of regional images captured by an unmanned aerial vehicle in a plurality of monitoring periods in a preset number of days T2, binds the plurality of regional images and the corresponding monitoring periods one by one to form an image data packet calibrated by a time sequence, where T2 is a positive integer satisfying 360 >= T2 >= 30;

[0009] An image processing module obtains a blocked area interval reference table and a boundary transformation interval reference table corresponding to the construction site in each monitoring period, respectively;

[0010] An abnormality monitoring module is configured to acquire real-time monitoring images of the UAV, obtain real-time shielding areas and real-time complexity coefficients corresponding to each calibration block in the real-time monitoring images, and mark shielding abnormal blocks in the real-time monitoring images according to the shielding area interval reference table and the boundary transformation interval reference table.

[0011] As a further scheme of the present application, the specific manner of obtaining the plurality of monitoring time periods corresponding to the construction site is:

[0012] The predetermined construction time period of the construction site is evenly divided into a plurality of monitoring time periods Ch according to a preset time interval T1, wherein T1 is the preset time interval, h is a different monitoring time period, h=1, 2, …, n, n is the number of monitoring time periods, and n is a positive integer, satisfying n≥2.

[0013] As a further scheme of the present application, the image processing module includes a pre-division processing unit, a shielding area interval reference table acquisition unit, and a boundary transformation interval reference table acquisition unit.

[0014] The pre-division processing unit is configured to evenly divide each regional image in the image data packet to be analyzed corresponding to each monitoring time period into a plurality of calibration blocks.

[0015] The shielding area interval reference table acquisition unit is configured to analyze each calibration block of each regional image in the image data packet to be analyzed corresponding to each monitoring time period, and obtain a shielding area interval reference table corresponding to each monitoring time period of the construction site.

[0016] The boundary transformation interval reference table acquisition unit is configured to analyze each calibration block of each regional image in the image data packet to be analyzed corresponding to each monitoring time period, and obtain a boundary transformation interval reference table corresponding to each monitoring time period of the construction site.

[0017] As a further scheme of the present application, the specific manner of obtaining the shielding area interval reference table corresponding to each monitoring time period of the construction site is:

[0018] S1: randomly selecting one monitoring time period from each monitoring time period as a target time period;

[0019] S2: randomly selecting one calibration block from the plurality of calibration blocks as a target block;

[0020] The shielding area of the target block corresponding to each regional image in the image data packet of the target time period is obtained, wherein r represents different regional images contained in the image data packet of the target time period, and a represents the number of regional images contained in the image data packet of the target time period, a is a positive integer and a>1.

[0021] S3: screening Mr according to the preset screening condition A, obtaining a numerical value Mb satisfying the condition, and determining a standard occlusion area H1 according to a comparison result of a quantity of the Mb and a preset threshold Y1, obtaining a mean value CZ of absolute values of differences between respective occlusion area Mr and Mp, generating an occlusion area interval L1 [FB, FA] according to the standard occlusion area H1 and the CZ, wherein Mp is a mean value of Mr;

[0022] S4: obtaining an occlusion area interval Le corresponding to each calibration block of the construction site in a target period, binding the occlusion area interval Le corresponding to each calibration block of the construction site in the target period and the target period, and generating an occlusion area interval reference table R1 corresponding to the construction site in the target period, wherein e represents different calibration blocks in the region image, and is a block number corresponding to each calibration block, and e=1, 2, …, c, wherein c represents the number of calibration blocks, and c is a positive integer and c>1;

[0023] S5: repeating the above steps S1-S4 to generate an occlusion area interval reference table Rh corresponding to the construction site in each monitoring period.

[0024] As a further scheme of the present application: the specific way of generating the occlusion area interval L1 is:

[0025] obtaining a mean value CZ of absolute values of differences between respective occlusion area Mr and the mean value Mp of Mr, taking a sum of the standard occlusion area H1 corresponding to the calibration block of the construction site in the target period and the CZ as an upper limit value FA of the occlusion area interval corresponding to the calibration block of the construction site in the target period, taking a difference between the standard occlusion area H1 corresponding to the calibration block of the construction site in the target period and the CZ as a lower limit value FB of the occlusion area interval corresponding to the calibration block of the construction site in the target period, and further generating the occlusion area interval L1 [FB, FA] corresponding to the calibration block of the construction site in the target period.

[0026] As a further scheme of the present application: the specific way of determining the standard occlusion area H1 is:

[0027] Obtaining the values Mb in each shielding area Mr satisfying the preset screening condition A: |Mr-Mp|≥Y2, wherein b is the number of values in Mr satisfying the preset screening condition A, a≥b≥1, when the number b is greater than the preset threshold Y1, defining the mean value Mp of Mr as the standard shielding area H1 corresponding to the calibration block of the construction site in the target period, when the number b is less than the preset threshold Y1, defining the mean value of the maximum value and the minimum value in Mr as the standard shielding area H1 corresponding to the calibration block of the construction site in the target period.

[0028] As a further scheme of the present application: the specific way of obtaining the boundary transformation interval reference table corresponding to the construction site at each monitoring period is:

[0029] S01: selecting the same monitoring period as step S1 from each monitoring period as the target period;

[0030] S02: selecting the same calibration block as step S2 from the plurality of calibration blocks as the target block;

[0031] S03: obtaining the complexity coefficient Ur of the shielding boundary line corresponding to the target block of each area image in the target period image data packet; generating the boundary transformation interval X1 according to the mean value Up of the complexity coefficient Ur and the mean value Q of the absolute value difference between Ur and Up;

[0032] S04: repeating steps S02-S03 to further obtain the boundary transformation interval Xe corresponding to each calibration block of the construction site in the target period, and binding the boundary transformation interval Xe corresponding to each calibration block of the construction site in the target period with the target period to generate the boundary transformation interval reference table K1 corresponding to the construction site in the target period;

[0033] S05: repeating the above steps S01-S04 to generate the boundary transformation interval reference table Kh corresponding to the construction site at each monitoring period.

[0034] As a further scheme of the present application: the specific way of obtaining the complexity coefficient Ur of the shielding boundary line corresponding to the target block of each area image in the target period image data packet is:

[0035] S031: selecting one target block from the target blocks of each area image as an analysis block without replacement; obtaining the shielding boundary line corresponding to the shielding area in the analysis block, constructing a two-dimensional coordinate system with the center point of the analysis block as the origin, obtaining the coordinates corresponding to each inflection point on the shielding boundary line of the analysis block, and calculating the distance Gg between each inflection point on the shielding boundary line of the analysis block and the center point of the analysis block according to the Euclidean distance formula; through the formula, , the complex coefficient U1 of the occlusion boundary line of the analysis block is obtained, Gi is any one of Gg, wherein Gp is the mean value of Gg, g represents different inflection points on the occlusion boundary line of the analysis block, g=1, 2, …, d, wherein d represents the number of inflection points on the occlusion boundary line of the analysis block, d is a positive integer and d>1;

[0036] S032: repeating step S031 to obtain the complex coefficient Ur corresponding to each target block occlusion boundary line of each region image in the target period image data packet, obtaining the mean value Q of the absolute value difference between each complex coefficient Ur and Up, taking the sum of Up and Q as the upper limit value BHA of the boundary transformation interval of the target block of the construction site in the target period, taking the difference between Up and Q as the lower limit value BHB of the boundary transformation interval of the target block of the construction site in the target period, and then obtaining the boundary transformation interval X1 [BHB, BHA] of the target block of the construction site in the target period, wherein Up is the mean value of Ur.

[0037] As a further scheme of the present application: the specific way of marking the occlusion abnormal block in the real-time monitoring image is:

[0038] obtaining the real-time occlusion area corresponding to each calibration block in the real-time monitoring image, matching the occlusion area interval reference table of the corresponding period as the occlusion area interval comparison reference table according to the acquisition time of the real-time monitoring image, comparing the real-time occlusion area corresponding to each calibration block in the real-time monitoring image with the occlusion area interval corresponding to each calibration block in the occlusion area interval comparison reference table one by one, marking the calibration block whose real-time occlusion area does not belong to the corresponding occlusion area interval as an occlusion area abnormal block, otherwise, no processing is performed, obtaining the real-time complex coefficient of the occlusion boundary line corresponding to the occlusion area abnormal block marked in the real-time monitoring image, matching the boundary transformation interval reference table of the corresponding period as the boundary transformation interval comparison reference table according to the acquisition time of the real-time monitoring image, comparing the real-time complex coefficient of the occlusion boundary line corresponding to the occlusion area abnormal block marked in the real-time monitoring image with the boundary transformation interval corresponding to the calibration block corresponding to the occlusion area abnormal block in the boundary transformation interval comparison reference table one by one, marking the calibration block whose real-time complex coefficient does not belong to the corresponding boundary transformation interval as an occlusion boundary abnormal block, and marking the corresponding calibration block as an occlusion abnormal block for output, otherwise, no processing is performed.

[0039] Compared with the prior art, the present application has the following beneficial effects:

[0040] The present application can analyze the image shot by the unmanned aerial vehicle in real time, quickly mark the occlusion area abnormal block and the occlusion boundary abnormal block, that is, the occlusion abnormal block, through quantitative analysis of the occlusion area and complex coefficient calculation of the occlusion boundary line, the system can accurately identify the abnormal change of the occlusion area, improve the accuracy and sensitivity of the abnormal detection. Real-time acquisition of image data shot by the unmanned aerial vehicle, and rapid analysis and judgment of the abnormal change of the occlusion area. Once the abnormality is detected, the system will immediately generate an abnormal report and notify the relevant personnel, so that the problem can be handled in time, and the staff can go to the scene for investigation and treatment in time, which can eliminate the safety hidden danger in time and ensure the construction safety of the construction site. BRIEF DESCRIPTION OF DRAWINGS

[0041] Figure 1 It is a schematic diagram of the system framework structure of the present application.

[0042] Figure 2 It is a schematic diagram of the calibration process of the occlusion abnormal block. DETAILED DESCRIPTION

[0043] The technical solutions of the present application will be described in detail below with reference to the embodiments. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0044] Embodiment one: please refer to Figure 1 Figure 2 The present application provides an intelligent remote security monitoring system for construction engineering, comprising:

[0045] The monitoring period acquisition module sets multiple monitoring periods according to the specified construction period of the construction site, and then obtains multiple monitoring periods corresponding to the construction site.

[0046] It should be noted that the specified construction period is the specified construction time of the construction site, which can be manually obtained and entered. The time intervals between the multiple monitoring periods can be equal or unequal. Here, the time intervals between the multiple monitoring periods are equal. According to the preset time interval T1, the specified construction period of the construction site is evenly divided into multiple monitoring periods Ch, wherein T1 is the preset time interval, the specific value is determined by the relevant personnel according to the demand, h is different monitoring period, h=1, 2, …, n, n is the number of monitoring periods, and n is a positive integer, n≥2.

[0047] ​The image data packet to be analyzed is obtained by the unmanned aerial vehicle in the preset number of days T2 in the plurality of monitoring time periods, and the plurality of region images of the construction area are photographed. The plurality of monitoring time periods of the construction site are sorted in time sequence, and the plurality of region images of the construction area photographed by the unmanned aerial vehicle in the preset number of days T2 in each monitoring time period are correspondingly bound to form an image data packet calibrated by time sequence, and then the plurality of monitoring time periods of the construction site are obtained. Corresponding image data packets to be analyzed, wherein the specific value of the preset number of days T2 is determined by relevant personnel according to the demand, and here T2 is a positive integer, satisfying 360≥T2≥30;

[0048] The image data of the construction area photographed by the unmanned aerial vehicle in the preset number of days T2 in the plurality of monitoring time periods is obtained, which ensures that the image data photographed by the unmanned aerial vehicle can completely cover these time periods, and the preset number of days T2 is not less than 30 days, so as to obtain more representative data.

[0049] It should be noted that the image shooting of the construction site by the unmanned aerial vehicle from multiple angles and in all directions is a mature technology, and therefore will not be described here.

[0050] The image processing module analyzes the image data in the image data packet to be analyzed corresponding to the plurality of monitoring time periods of the construction site, and then obtains the corresponding shielding area interval reference table and boundary transformation interval reference table of the construction site in each monitoring time period, and the specific method is:

[0051] The pre-division processing unit performs the same pre-division processing on each region image in the image data packet to be analyzed corresponding to the plurality of monitoring time periods of the construction site, so that each region image has a plurality of calibration blocks.

[0052] The specific method of pre-division processing is to uniformly divide the region image into a plurality of calibration blocks. It should be noted that the pre-division processing of each region image in the image data packet to be analyzed corresponding to the plurality of monitoring time periods is the same, and the number and shape of the calibration blocks in each region image are the same.

[0053] It should be noted that the image photographed by the unmanned aerial vehicle has a fixed number of pixels, a fixed actual length, and no special situation such as irregular image size.

[0054] The shielding area interval reference table acquisition unit analyzes each calibration block of each region image in the image data packet to be analyzed corresponding to each monitoring time period, and then obtains the shielding area interval reference table corresponding to each monitoring time period of the construction site, and the specific method is:

[0055] S1: randomly selecting one monitoring period as a target period from the monitoring periods;

[0056] S2: randomly selecting one calibration block as a target block from the calibration blocks;

[0057] S3: obtaining the occluded area Mr of the target block corresponding to each area image in the image data packet of the target period and outputting, wherein r represents different area images contained in the image data packet of the target period, and the value is r = 1, 2, …, a, wherein a represents the number of area images contained in the image data packet of the target period, a is a positive integer and a > 1;

[0058] It should be noted that for the construction site image taken by the unmanned aerial vehicle, image analysis software (such as Adobe Photoshop, ImageJ, etc.) can be used. After importing the image into the software, the conversion relationship between the image pixels and the actual length is set according to a certain proportion (for example, the pixel length corresponding to an actual length of 10 meters of an object in the image is known, and the conversion ratio is determined), and then the occluded area contour is manually or automatically recognized by the software. The software can calculate the area (in pixels, and the actual area is obtained by conversion ratio) and the occluded area corresponding to the contour. The above are existing and mature technologies, and therefore no further description is given here.

[0059] Obtaining the number Mb of values Mb in each occluded area Mr that satisfy the preset screening condition A, wherein b is the number of values in Mr that satisfy the preset screening condition A, a ≥ b ≥ 1, and comparing the number b with the preset threshold Y1. When the number b is greater than the preset threshold Y1, it means that the number of values in Mr that satisfy the preset screening condition A is relatively large, and thus the mean value of Mr is representative, and then the mean value Mp of Mr is defined as the standard occluded area H1 corresponding to the calibration block of the construction site in the target period. When the number b is less than the preset threshold Y1, it means that the number of values in Mr that satisfy the preset screening condition A is relatively small, and the mean value of Mr is not representative, and then the mean value of the maximum and minimum values of Mr is defined as the standard occluded area H1 corresponding to the calibration block of the construction site in the target period, i.e. H1 = (Mmin + Mmax) / 2, wherein Mmax and Mmin are the maximum and minimum values of Mr, respectively. Here, the preset screening condition A is specifically: |Mr - Mp| ≥ Y2, wherein Mp is the mean value of Mr, and Y2 is a preset threshold. The specific values of the preset thresholds Y1 and Y2 are determined by relevant personnel according to requirements;

[0060] obtaining the mean value CZ of the absolute value of the difference between each shielding area Mr and the mean value Mp of Mr, taking the sum of the standard shielding area H1 corresponding to the calibration block of the construction site in the target period and CZ as the upper limit value FA of the shielding area interval corresponding to the calibration block of the construction site in the target period, and taking the difference between the standard shielding area H1 corresponding to the calibration block of the construction site in the target period and CZ as the lower limit value FB of the shielding area interval corresponding to the calibration block of the construction site in the target period, thereby generating the shielding area interval L1 [FB, FA] corresponding to the calibration block of the construction site in the target period;

[0061] S4: repeating the above steps S2-S3, thereby obtaining the shielding area interval Le corresponding to each calibration block of the construction site in the target period, respectively, and binding the shielding area interval Le corresponding to each calibration block in the target period, respectively, to the target period, to generate the shielding area interval reference table R1 corresponding to the construction site in the target period;

[0062] wherein e represents different calibration blocks in the region image, and is the block number corresponding to each calibration block, and e=1, 2, …, c, wherein c represents the number of calibration blocks, and c is a positive integer and c>1;

[0063] S5: repeating the above steps S1-S4, thereby obtaining the shielding area interval reference table Rh corresponding to the construction site in each monitoring period, respectively.

[0064] The boundary transformation interval reference table acquisition unit analyzes each calibration block of each region image in the to-be-analyzed image data packet corresponding to each monitoring period, respectively, thereby obtaining the boundary transformation interval reference table corresponding to the construction site in each monitoring period, respectively, and the specific way is:

[0065] S01: selecting the same monitoring period as step S1 from each monitoring period as the target period;

[0066] S02: selecting the same calibration block as step S2 from the plurality of calibration blocks as the target block;

[0067] S03: obtaining the center points corresponding to the target blocks of each region image in the target period image data packet and the shielding boundary lines corresponding to the shielding regions in each target block, analyzing the shielding boundary lines corresponding to the target blocks of each region image in the target period image data packet, thereby obtaining the complexity coefficients of the shielding boundary lines corresponding to the target blocks of each region image in the target period image data packet, and analyzing the complexity coefficients of the shielding boundary lines corresponding to the target blocks of each region image in the target period image data packet, thereby obtaining the boundary transformation interval reference table X1 corresponding to the target block of the construction site in the target period;

[0068] S031: selecting one target block from the target blocks of the respective region images as an analysis block without replacement;

[0069] obtaining the occlusion boundary line corresponding to the occlusion region in the analysis block, constructing a two-dimensional coordinate system with the center point of the analysis block as the origin, obtaining the coordinates of each inflection point on the occlusion boundary line of the analysis block, and calculating the distance Gg between each inflection point on the occlusion boundary line of the analysis block and the center point of the analysis block according to the Euclidean distance formula;

[0070] It should be noted that the inflection point coordinates on the occlusion boundary line can be extracted by the edge detection algorithm of the image processing software (such as OpenCV), and a two-dimensional rectangular coordinate system can be constructed with the center point of the analysis block as the origin (0, 0). The unit length of the x-axis and the y-axis can be the conversion ratio of image pixels and actual length. The above are existing and mature calculation methods, and therefore will not be described here.

[0071] where g represents different inflection points on the occlusion boundary line of the analysis block, and takes values of g = 1, 2, …, d, where d represents the number of inflection points on the occlusion boundary line of the analysis block, and d is a positive integer and d > 1;

[0072] The complex coefficient U1 of the occlusion boundary line of the analysis block is obtained by the formula, , where Gi is any one of Gg, and i ≥ d ≥ 1, where Gp is the mean of Gg.

[0073] S032: repeating step S031 to obtain the complex coefficient Ur corresponding to the occlusion boundary line of each target block of the region image in the target time period data packet, obtaining the mean Q of the absolute value of the difference between each complex coefficient Ur and Up, where Up is the mean of Ur, and taking the sum of Up and Q as the upper limit value BHA of the boundary transformation interval of the target block of the construction site in the target time period, and taking the difference between Up and Q as the lower limit value BHB of the boundary transformation interval of the target block of the construction site in the target time period, thereby obtaining the boundary transformation interval X1 [BHB, BHA] of the target block of the construction site in the target time period;

[0074] S04: repeating the above steps S02-S03 to obtain the boundary transformation interval Xe corresponding to each calibration block of the construction site in the target time period, and binding the boundary transformation interval Xe corresponding to each calibration block of the construction site in the target time period with the target time period to generate the boundary transformation interval reference table K1 corresponding to the construction site in the target time period;

[0075] S05: repeating the above steps S01-S04 to obtain the boundary transformation interval reference table Kh corresponding to the construction site in each monitoring time period.

[0076] The abnormality monitoring module acquires the real-time monitoring image of the UAV, and inputs the real-time monitoring image into the image processing module for pre-division processing of the real-time monitoring image, and obtains the real-time shielding area of each calibration block in the real-time monitoring image. According to the acquisition time of the real-time monitoring image, the shielding area interval reference table of the corresponding time period is matched as a shielding area interval comparison reference table. The real-time shielding area of each calibration block in the real-time monitoring image is compared with the shielding area interval of each calibration block in the shielding area interval comparison reference table. The shielding area abnormal block is marked. The specific method is as follows:

[0077] The calibration block whose real-time shielding area does not belong to the corresponding shielding area interval is marked as a shielding area abnormal block. Otherwise, no processing is performed.

[0078] The abnormality monitoring module acquires the real-time monitoring image of the UAV, and inputs the real-time monitoring image into the image processing module for pre-division processing of the real-time monitoring image, and obtains the real-time shielding area of each calibration block in the real-time monitoring image. According to the acquisition time of the real-time monitoring image, the shielding area interval reference table of the corresponding time period is matched as a shielding area interval comparison reference table. The real-time shielding area of each calibration block in the real-time monitoring image is compared with the shielding area interval of each calibration block in the shielding area interval comparison reference table. The shielding area abnormal block is marked. The specific method is as follows:

[0079] Embodiment two: as embodiment two of the present application, in the specific implementation, compared with embodiment one, the difference between the technical scheme of the present embodiment and embodiment one is that in the present embodiment, the shielding area abnormal block is further analyzed. The real-time monitoring image is input into the boundary transformation interval reference table acquisition unit to analyze the complexity coefficient of the shielding boundary line corresponding to the shielding area abnormal block in the real-time monitoring image, and then the real-time complexity coefficient of the shielding boundary line corresponding to the shielding area abnormal block in the real-time monitoring image is obtained. According to the acquisition time of the real-time monitoring image, the boundary transformation interval reference table of the corresponding time period is matched as a boundary transformation interval comparison reference table. The real-time complexity coefficient of the shielding boundary line corresponding to the shielding area abnormal block in the real-time monitoring image is compared with the boundary transformation interval corresponding to the calibration block in the boundary transformation interval comparison reference table. The calibration block whose real-time complexity coefficient does not belong to the corresponding boundary transformation interval is marked as a shielding boundary abnormal block, and the corresponding calibration block is marked as a shielding abnormal block for output. Otherwise, no processing is performed.

[0080] Through the accurate calculation and analysis of the shielding area, the boundary and the normal fluctuation range, the accuracy and sensitivity of the abnormality judgment can be improved, and the abnormal change of the shielding area caused by abnormal accumulation of objects, sudden equipment failure and the like can be found in time. Once the abnormality is determined, the staff can be arranged to go to the shielding area for on-site inspection immediately, and it can be checked whether the abnormal change of the shielding area is caused by temporary stacking of objects, equipment failure or other factors that may affect safety, so as to eliminate the safety hidden danger in time, ensure that the monitoring area can normally play a role, and guarantee the construction safety of the construction site. The change of the monitoring shielding area of the construction site can be well mastered, the safety hidden danger hidden in the abnormal change can be found in time, and the response measures can be prepared in advance.

[0081] Embodiment three: as an embodiment three of the application, in the specific implementation, compared with the embodiment one and the embodiment two, the technical scheme of the embodiment is to combine the schemes of the embodiment one and the embodiment two.

[0082] The above formulas are all dimensionless numerical calculations, the formulas are obtained by collecting a large amount of data to simulate the most recent real situation, and the preset parameters and threshold values in the formulas are set by the person skilled in the art according to the actual situation, and the contents not described in detail in the specification all belong to the prior art known by the person skilled in the art.

[0083] The above is only a specific embodiment of the application, but the protection scope of the application is not limited to this, any person skilled in the art can easily think of changes or replacements within the technical range disclosed in the application, which should be covered in the protection scope of the application. Therefore, the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A smart remote security monitoring system for building engineering, characterized in that, include: The monitoring period acquisition module obtains multiple monitoring periods corresponding to the construction site. The image data packet acquisition module acquires multiple area images taken by the UAV during multiple monitoring periods within a preset number of days T2. The multiple area images are bound one-to-one with the corresponding monitoring periods to form an image data packet with time series as the label. Here, T2 is a positive integer that satisfies 360≥T2≥30. The image processing module obtains reference tables for the occlusion area ranges and boundary transformation ranges of the construction site during each monitoring period. The specific method for obtaining the reference tables for the occlusion area ranges of the construction site during each monitoring period is as follows: S1: Randomly select one monitoring period from each monitoring period as the target period; S2: Randomly select one of the multiple calibration blocks as the target block; Obtain the occlusion area Mr corresponding to the target block of each region image in the image data packet of the target time period, where r refers to the different region images contained in the image data packet of the target time period, and the value is r=1,2,...,a, where a refers to the number of region images contained in the image data packet of the target time period, a is a positive integer and a>1; S3: Filter Mr according to the preset filtering condition A to obtain the value Mb that meets the condition, and determine the standard occlusion area H1 based on the comparison result of the number of Mb with the preset threshold Y1. Obtain the mean CZ of the absolute value of the difference between each occlusion area Mr and Mp. Generate the occlusion area interval L1 [FB, FA] based on the standard occlusion area H1 and CZ, where Mp is the mean of Mr. S4: Obtain the occlusion area interval Le corresponding to each calibrated block of the construction site in the target time period, bind the occlusion area interval Le corresponding to each calibrated block in the target time period with the target time period, and generate the occlusion area interval reference table R1 corresponding to the construction site in the target time period, where e refers to different calibrated blocks in the regional image, and is also the block number corresponding to each calibrated block, with values ​​of e=1, 2, ..., c, where c refers to the number of calibrated blocks, c is a positive integer and c>1; S5: Repeat steps S1-S4 above to generate a reference table Rh for the occlusion area intervals of the construction site at each monitoring time period; The specific method for obtaining the reference table of boundary transformation intervals for construction sites at each monitoring period is as follows: S01: Select the same monitoring period as step S1 from each monitoring period as the target period; S02: Select the same calibration block as step S2 from multiple calibration blocks as the target block; S03: Obtain the complexity coefficient Ur of the occlusion boundary line corresponding to the target block of each region image in the target time period image data packet; generate the boundary transformation interval X1 based on the mean Up of the complexity coefficient Ur and the mean Q of the absolute value of the difference between Ur and Up. S04: Repeat steps S02-S03 to obtain the boundary transformation intervals Xe corresponding to each calibrated block of the construction site in the target time period. Bind the boundary transformation intervals Xe corresponding to each calibrated block in the target time period to the target time period to generate the boundary transformation interval reference table K1 corresponding to the construction site in the target time period. S05: Repeat steps S01-S04 above to generate a reference table Kh for the boundary transformation intervals of the construction site at each monitoring period. The anomaly monitoring module is used to acquire real-time monitoring images of the UAV, obtain the real-time occlusion area and real-time complexity coefficient corresponding to each calibrated block in the real-time monitoring image, and mark the occlusion anomaly blocks in the real-time monitoring image according to the occlusion area interval reference table and the boundary transformation interval reference table.

2. The intelligent remote security monitoring system for building engineering according to claim 1, characterized in that, The specific method for obtaining multiple monitoring time periods corresponding to a construction site is as follows: The construction site's designated construction period is evenly divided into multiple monitoring periods Ch according to a preset time interval T1, where T1 is the preset time interval, h is a different monitoring period, h=1, 2, ..., n, n is the number of monitoring periods, and n is a positive integer, satisfying n≥2.

3. The intelligent remote security monitoring system for building engineering according to claim 2, characterized in that, The image processing module includes a pre-division processing unit, an occlusion area interval reference table acquisition unit, and a boundary transformation interval reference table acquisition unit; The pre-division processing unit is used to uniformly divide the images of each region in the image data packets to be analyzed corresponding to multiple monitoring time periods into multiple calibration blocks; The occlusion area interval reference table acquisition unit is used to analyze each calibrated block of each region image in the image data packet to be analyzed corresponding to each monitoring period, and obtain the occlusion area interval reference table corresponding to the construction site at each monitoring period. The boundary transformation interval reference table acquisition unit is used to analyze each calibration block of each region image in the image data packet to be analyzed corresponding to each monitoring period, and obtain the boundary transformation interval reference table corresponding to the construction site at each monitoring period.

4. The intelligent remote security monitoring system for building engineering according to claim 1, characterized in that, The specific method for generating the occlusion area interval L1 is as follows: The mean CZ of the absolute values ​​of the differences between the area Mr of each shading region and the mean Mp of Mr is obtained. The sum of the standard shading area H1 corresponding to the designated block of the construction site in the target time period and CZ is taken as the upper limit FA of the shading area interval corresponding to the designated block of the construction site in the target time period. The difference between the standard shading area H1 corresponding to the designated block of the construction site in the target time period and CZ is taken as the lower limit FB of the shading area interval corresponding to the designated block of the construction site in the target time period. Thus, the shading area interval L1 [FB, FA] corresponding to the designated block of the construction site in the target time period is generated.

5. The intelligent remote security monitoring system for building engineering according to claim 1, characterized in that, The specific method for determining the standard shading area H1 is as follows: Obtain the values ​​Mb in each occlusion area Mr that satisfy the preset filtering condition A: |Mr-Mp|≥Y2, where b is the number of values ​​in Mr that satisfy the preset filtering condition A, a≥b≥1. When the number b is greater than the preset threshold Y1, the average value Mp of Mr is defined as the standard occlusion area H1 corresponding to the designated block of the construction site in the target time period. When the number b is less than the preset threshold Y1, the average of the maximum and minimum values ​​in Mr is defined as the standard occlusion area H1 corresponding to the designated block of the construction site in the target time period.

6. The intelligent remote security monitoring system for building engineering according to claim 1, characterized in that, The specific method for obtaining the complexity coefficient Ur of the occlusion boundary line corresponding to each region image in the target time period image data packet is as follows: S031: Select a target block without replacement from the target blocks of each region image as the analysis block; obtain the occlusion boundary line corresponding to the occlusion area in the analysis block; construct a two-dimensional coordinate system with the center point of the analysis block as the origin; obtain the coordinates corresponding to each vertex on the occlusion boundary line of the analysis block; and calculate the distance Gg between each vertex on the occlusion boundary line of the analysis block and the center point of the analysis block according to the Euclidean distance formula; using the formula... To obtain the complexity coefficient U1 of the occlusion boundary line of the analysis block, Gi is any one of Gg, where Gp is ​​the mean of Gg, and g refers to different inflection points on the occlusion boundary line of the analysis block, with values ​​of g=1, 2, ..., d, where d refers to the number of inflection points on the occlusion boundary line of the analysis block, and d is a positive integer and d>

1. S032: Repeat step S031 to obtain the complexity coefficient Ur corresponding to the occlusion boundary line of the target block in each region of the image data packet for the target time period. Obtain the mean Q of the absolute value of the difference between each complexity coefficient Ur and Up. Take the sum of Up and Q as the upper limit BHA of the boundary transformation interval corresponding to the target block of the construction site in the target time period. Take the difference between Up and Q as the lower limit BHB of the boundary transformation interval corresponding to the target block of the construction site in the target time period. Then obtain the boundary transformation interval X1 [BHB, BHA] corresponding to the target block of the construction site in the target time period, where Up is the mean of Ur.

7. The intelligent remote security monitoring system for building engineering according to claim 6, characterized in that, The specific method for marking occlusion anomalies in real-time monitoring images is as follows: The real-time occlusion area corresponding to each calibrated block in the real-time monitoring image is obtained. Based on the acquisition time of the real-time monitoring image, an occlusion area interval reference table for the corresponding time period is used as an occlusion area interval comparison reference table. The real-time occlusion area corresponding to each calibrated block in the real-time monitoring image is compared with the corresponding occlusion area intervals in the occlusion area interval comparison reference table one by one. Calibration blocks whose real-time occlusion area does not belong to the corresponding occlusion area interval are marked as occlusion area abnormal blocks; otherwise, no processing is performed. The corresponding occlusion area of ​​the blocks marked as occlusion area abnormal blocks in the real-time monitoring image is obtained. The real-time complexity coefficient of the corresponding occlusion boundary line is determined. Based on the acquisition time of the real-time monitoring image, a boundary transformation interval reference table for the corresponding time period is matched and used as a boundary transformation interval comparison reference table. The real-time complexity coefficient of the occlusion boundary line corresponding to the occlusion area abnormal block in the real-time monitoring image is compared with the boundary transformation interval corresponding to the corresponding calibration block in the boundary transformation interval comparison reference table one by one. The calibration block whose real-time complexity coefficient does not belong to the corresponding boundary transformation interval is marked as an occlusion boundary abnormal block, and the corresponding calibration block is marked as an occlusion abnormal block and output. Otherwise, no processing is performed.

Images