A construction project monitoring system

Abstract

The present invention belongs to the field of construction monitoring, and discloses a construction monitoring system for a construction project, including a partitioning device, an unmanned aerial vehicle, and a monitoring device; the partitioning device is used to partition the construction site of the construction project, and divide the construction site into a plurality of shooting areas; the unmanned aerial vehicle is used to shoot each shooting area respectively to obtain a construction site image; the monitoring device is used to identify each construction site image respectively, and determine whether there is an event that affects construction safety in the construction site image. The present invention improves the efficiency of obtaining the monitoring results of the entire construction site, and can also take higher-resolution photos of areas with a high probability of occurrence of events that affect construction safety, further improving the accuracy of identification.

Description

Technical Field

[0001] The present invention relates to the field of construction monitoring, and in particular to a construction project monitoring system. Background Art

[0002] In order to improve the safety of outdoor construction projects, in the prior art, drones are usually used to photograph the construction site of the construction project to obtain images of the construction site. Afterwards, manual or machine recognition is used to determine whether there are any events that affect construction safety in the image.

[0003] When the construction site is relatively large, a single shot cannot meet the requirement of full coverage. The existing technology usually divides the construction site into a preset number of shooting areas of the same area, and then uses a drone to shoot each shooting area separately to obtain a preset number of multiple images, and then performs manual or machine recognition on each image to obtain the monitoring results of the entire construction site.

[0004] However, this shooting method does not take into account the different probabilities of events affecting construction safety at different locations in the construction site. The fixed number method easily leads to too many images being shot in areas with low probability of events affecting construction safety. Since too many images need to be identified, the efficiency of obtaining monitoring results for the entire construction site is affected, which is not conducive to timely discovering events affecting construction safety at the construction site. Summary of the invention

[0005] The purpose of the present invention is to disclose a construction project monitoring system to solve the problem of how to reasonably determine the number of images while ensuring the monitoring effect in the process of using a drone to photograph the construction site of the construction project and performing safety monitoring based on the photographed images, thereby improving the efficiency of obtaining the monitoring results of the entire construction site.

[0006] In order to achieve the above object, the present invention adopts the following technical solution:

[0007] The present invention provides a construction project monitoring system, including a partitioning device, a drone and a monitoring device;

[0008] The partition device is used to partition the construction site of the construction project and divide the construction site into multiple shooting areas, including:

[0009] When monitoring the construction site for the first N times, the process of obtaining the shooting area includes:

[0010] Divide the construction site into multiple shooting areas of equal size;

[0011] Starting from the N+1th monitoring of the construction site, the process of obtaining the shooting area includes:

[0012] The first step is to obtain a plan map containing the construction site;

[0013] The second step is to establish a rectangular coordinate system in the plane map and obtain the outer rectangle of the area of ​​the construction site in the plane map;

[0014] The third step is to initialize the value of b to 1, divide the outer rectangle into D regions of equal area, and store the obtained regions into the set Z. b ;

[0015] The fourth step is to calculate Z b The regional coefficient of each region in ;

[0016] Step 5: Add 1 to the value of b and take the areas whose regional coefficient is greater than the pre-set regional coefficient comparison value as set E. b The elements in the set F store the regions whose regional coefficients are less than or equal to the pre-set regional coefficient comparison value into the set F;

[0017] Step 6: Determine E b Is the number of elements in set F 0? If so, each element in set F is taken as a shooting area, and the process of obtaining the shooting area is ended; if not, proceed to step 7;

[0018] Step 7: E b Each element in is divided into D regions of equal area, and the obtained regions are stored in the set Z b , proceed to step 4;

[0019] The drone is used to photograph each shooting area separately to obtain images of the construction site;

[0020] The monitoring device is used to identify each construction site image separately and determine whether there are any events that affect construction safety in the construction site image.

[0021] Preferably, the construction site is divided into a plurality of shooting areas of equal size, including:

[0022] Get a floor plan map that includes the construction site;

[0023] Establishing a rectangular coordinate system in the plane map, and obtaining an outer rectangle of the construction site area in the plane map;

[0024] Divide the outer rectangle into multiple shooting areas of equal size.

[0025] Preferably, obtaining the outer rectangle of the area of ​​the construction site in the plan map includes:

[0026] A1 and A2 represent the maximum and minimum values ​​of the abscissa of the area of ​​the construction site in the rectangular coordinate system respectively;

[0027] B1 and B2 represent the maximum and minimum values ​​of the vertical coordinates of the construction site area in the rectangular coordinate system respectively;

[0028] Then the horizontal coordinates of the pixel points in the outer rectangle satisfy A2≤x≤A1 and the vertical coordinates satisfy B2≤y≤B1, where x and y are the horizontal coordinates and vertical coordinates of the pixel points respectively.

[0029] Preferably, the outer rectangle is divided into a plurality of shooting areas of the same area, including:

[0030] L1 and W1 represent the length and width of the outer rectangle respectively; L2 and W2 represent the length and width of the image captured by the drone at the restricted flight altitude H, which correspond to the length and width of the plane map containing the construction site;

[0031] Then in the outer rectangle, the number of rows in the shooting area is The number of columns in the shooting area is

[0032] Divide the outer rectangle into The same shooting area.

[0033] Preferably, the value of D is 4.

[0034] Preferably, the outer rectangle is divided into D regions of equal area, including:

[0035] L1 and W1 represent the length and width of the outer rectangle respectively, and the length of the area is The width of the region is

[0036] Divide the outer rectangle into D parts with an area of area.

[0037] Preferably, the calculation formula of the area coefficient is as follows:

[0038]

[0039] regcoft c Represents the area coefficient of area c, evenum c Indicates the number of events that affect construction safety in area c during the most recent Nrec monitoring of the construction site, exte c represents the area of ​​region c, exte sc Indicates the area of ​​the construction site, equnum crepresents the number of construction machines in area c when the construction site was monitored last time, equtotal represents the number of construction machines in the construction site when the construction site was monitored last time, λ1, λ2 and λ3 represent the first quantity factor, area factor and second quantity factor respectively.

[0040] Preferably, the first quantity factor, the area factor and the second quantity factor are respectively and

[0041] Preferably, the regional coefficient control value set in advance is

[0042] Preferably, photographing each photographing area separately to obtain a construction site image includes:

[0043] The shooting areas are photographed above the center of each shooting area, so that the construction site image obtained by shooting can include the complete shooting area.

[0044] Beneficial effects:

[0045] Different from the existing method of specifying the number of shooting areas in advance, the present invention only uses a fixed number of shooting areas of the same size during the first N times of monitoring the construction site. After that, the present invention adaptively obtains areas of different sizes based on the area coefficient, and the number of areas is also related to the number of events affecting construction safety occurring at different locations in the construction site, the area of ​​the area, and the number of construction machinery present, so that the area with a lower probability of an event affecting construction safety is larger, and the area with a higher probability of an event affecting construction safety is smaller. In this way, the number of shooting areas changes with the actual situation of the construction site, which can effectively reduce the probability of taking too many images of areas with a low probability of affecting construction safety, improve the efficiency of obtaining the monitoring results of the entire construction site, and take higher resolution photos of areas with a high probability of events affecting construction safety, further improving the accuracy of recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0047] Figure 1 The present invention is a schematic diagram of a construction project monitoring system. DETAILED DESCRIPTION

[0048] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents the selected embodiments of the present invention. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present invention.

[0049] like Figure 1 In one embodiment shown, the present invention provides a construction project monitoring system, including a partitioning device, a drone and a monitoring device;

[0050] The partition device is used to partition the construction site of the construction project and divide the construction site into multiple shooting areas, including:

[0051] When monitoring the construction site for the first N times, the process of obtaining the shooting area includes:

[0052] Divide the construction site into multiple shooting areas of equal size;

[0053] Starting from the N+1th monitoring of the construction site, the process of obtaining the shooting area includes:

[0054] The first step is to obtain a plan map containing the construction site;

[0055] The second step is to establish a rectangular coordinate system in the plane map and obtain the outer rectangle of the area of ​​the construction site in the plane map;

[0056] The third step is to initialize the value of b to 1, divide the outer rectangle into D regions of equal area, and store the obtained regions into the set Z. b ;

[0057] The fourth step is to calculate Z b The regional coefficient of each region in ;

[0058] Step 5: Add 1 to the value of b and take the areas whose regional coefficient is greater than the pre-set regional coefficient comparison value as set E. b The elements in the set F store the regions whose regional coefficients are less than or equal to the pre-set regional coefficient comparison value into the set F;

[0059] Step 6: Determine E bIs the number of elements in set F 0? If so, each element in set F is taken as a shooting area, and the process of obtaining the shooting area is ended; if not, proceed to step 7;

[0060] Step 7: E b Each element in is divided into D regions of equal area, and the obtained regions are stored in the set Z b , proceed to step 4;

[0061] The drone is used to photograph each shooting area separately to obtain images of the construction site;

[0062] The monitoring device is used to identify each construction site image separately and determine whether there are any events that affect construction safety in the construction site image.

[0063] In the above scheme, the present invention adopts a fixed number of shooting areas of the same size only in the first N times of monitoring the construction site. After that, the present invention adaptively obtains areas of different sizes based on the area coefficient, and the number of areas is also related to the number of events affecting construction safety occurring at different positions in the construction site, the area of ​​the area, and the number of construction machinery present, so that the area with a lower probability of an event affecting construction safety is larger, and the area with a higher probability of an event affecting construction safety is smaller. In this way, the number of shooting areas changes with the actual situation of the construction site, which can effectively reduce the probability of taking too many images of areas with a low probability of affecting construction safety, improve the efficiency of obtaining the monitoring results of the entire construction site, and take higher resolution photos of areas with a high probability of events affecting construction safety, further improving the accuracy of recognition.

[0064] Preferably, the value of N is 5.

[0065] Preferably, the construction site is divided into a plurality of shooting areas of equal size, including:

[0066] Get a floor plan map that includes the construction site;

[0067] Establishing a rectangular coordinate system in the plane map, and obtaining an outer rectangle of the construction site area in the plane map;

[0068] Divide the outer rectangle into multiple shooting areas of equal size.

[0069] By obtaining the outer rectangle, it is helpful to include the irregular area of ​​the construction site into a regular outer rectangle, which is conducive to the subsequent division of the rectangular area.

[0070] Preferably, a rectangular coordinate system is established in the plane map, including:

[0071] A rectangular coordinate system is established in the plane map, with the lower left corner of the plane map as the coordinate origin, the due north direction of the plane map as the positive direction of the Y axis, and the due east direction as the positive direction of the X axis.

[0072] Preferably, obtaining the outer rectangle of the area of ​​the construction site in the plan map includes:

[0073] A1 and A2 represent the maximum and minimum values ​​of the abscissa of the area of ​​the construction site in the rectangular coordinate system respectively;

[0074] B1 and B2 represent the maximum and minimum values ​​of the vertical coordinates of the construction site area in the rectangular coordinate system respectively;

[0075] Then the horizontal coordinates of the pixel points in the outer rectangle satisfy A2≤x≤A1 and the vertical coordinates satisfy B2≤y≤B1, where x and y are the horizontal coordinates and vertical coordinates of the pixel points respectively.

[0076] Preferably, the outer rectangle is divided into a plurality of shooting areas of the same area, including:

[0077] L1 and W1 represent the length and width of the outer rectangle respectively; L2 and W2 represent the length and width of the image captured by the drone at the restricted flight altitude H, which correspond to the length and width of the plane map containing the construction site;

[0078] Then in the outer rectangle, the number of rows in the shooting area is The number of columns in the shooting area is

[0079] Divide the outer rectangle into The same shooting area.

[0080] Furthermore, in obtaining After obtaining the same shooting areas, the intersection of the pixel points corresponding to each shooting area and the pixel points corresponding to the construction site area will be obtained respectively;

[0081] Delete the shooting areas whose intersection is an empty set.

[0082] Since the irregular construction site areas were regularized before, areas that did not originally belong to the construction site were introduced. Therefore, if the area coefficients of these areas are calculated and drones are used to take pictures, it will obviously affect the speed of obtaining monitoring results. Therefore, through the above-mentioned screening process, the effectiveness of the remaining shooting areas can be improved, thereby improving the efficiency of obtaining monitoring results for the entire construction site.

[0083] Preferably, the value of D is 4.

[0084] Furthermore, the value of D may also be 9.

[0085] Preferably, the outer rectangle is divided into D regions of equal area, including:

[0086] L1 and W1 represent the length and width of the outer rectangle respectively, and the length of the area is The width of the region is

[0087] Divide the outer rectangle into D parts with an area of area.

[0088] By dividing the outer rectangle into regions of the same area, the region coefficient of each region can be calculated respectively, and the process of cyclically obtaining the shooting regions of the present invention can be started.

[0089] Preferably, the calculation formula of the area coefficient is as follows:

[0090]

[0091] regcoft c represents the area coefficient of area c, evenum c Indicates the number of events that affect construction safety in area c during the most recent Nrec monitoring of the construction site, exte c represents the area of ​​region c, exte sc Indicates the area of ​​the construction site, equnum c represents the number of construction machines in area c when the construction site was monitored last time, equtotal represents the number of construction machines in the construction site when the construction site was monitored last time, λ1, λ2 and λ3 represent the first quantity factor, area factor and second quantity factor respectively.

[0092] In the present invention, the regional coefficient is related to the monitoring results of the most recent Nrec times. When the number of events affecting construction safety in region c increases, the area increases, and the number of construction machines exists increases, the regional coefficient increases, and the probability that such a region will continue to be divided increases. This calculation method of the regional coefficient makes the number of shooting areas finally obtained by the present invention adaptively related to the number of events affecting construction safety, the area of ​​the region, and the number of construction machines, thereby effectively reducing the number of shooting areas with a low probability of events affecting construction safety, and realizing adaptive changes in the number of shooting areas, effectively improving the efficiency of monitoring the construction site.

[0093] Preferably, the value of Nrec is 5.

[0094] Preferably, the first quantity factor, the area factor and the second quantity factor are respectively and

[0095] Preferably, the regional coefficient control value set in advance is

[0096] Preferably, photographing each photographing area separately to obtain a construction site image includes:

[0097] The shooting areas are photographed above the center of each shooting area, so that the construction site image obtained by shooting can include the complete shooting area.

[0098] Furthermore, when photographing the photographing area, the photographing height can maximize the proportion of the photographing area in the construction site.

[0099] The process of photographing altitude includes:

[0100] When the shooting area is photographed at different heights, the area of ​​the shooting area occupies different proportions in the construction site image. As the shooting height becomes lower, the proportion becomes higher and higher. Finally, the height that allows the shooting area to appear completely in the construction site image and occupies the largest proportion is determined, and this height is used as the shooting height.

[0101] Preferably, each construction site image is identified respectively to determine whether there is an event that affects construction safety in the construction site image, including:

[0102] Initialize each construction site image respectively to obtain an initialized image;

[0103] The initialization image is input into the pre-trained image recognition model for recognition, and the events that affect construction safety contained in the initialization image are obtained.

[0104] Preferably, each construction site image is initialized to obtain an initialized image, including:

[0105] Let h represent the construction site image, and the process of processing the hth image is as follows:

[0106] Get the grayscale image gryh corresponding to h;

[0107] Perform boundary detection on gryh to obtain boundary pixel points;

[0108] Obtain the contrast area in h based on the boundary pixels;

[0109] Determine the color space clspa where the initialization image is located based on the contrast area;

[0110] Get the initialization image in clspa.

[0111] Traditional image recognition methods generally only use grayscale images as input data and input them into the image recognition model for recognition. However, this recognition method does not take into account that under different shooting conditions and in different color spaces, there are component images that contain more effective image detail information. Therefore, directly using grayscale images as the object of recognition may affect the accuracy of recognition because the grayscale images do not contain enough information.

[0112] Therefore, the present invention first detects the boundary, then obtains the comparison area, and selects the color space of the initialization image based on the comparison area. Since the comparison area has outstanding representativeness, it can avoid comparing the color space based on all images, and only needs to compare based on the comparison area to obtain accurate comparison results. The efficiency of comparison is effectively improved, thereby improving the efficiency of obtaining the initialization image in the best color space.

[0113] Preferably, the boundary detection algorithms include Edge-Flow, Frei-Chen, etc. You only need to select one of them for boundary detection.

[0114] Preferably, obtaining the contrast area in h based on the boundary pixel points includes:

[0115] Use a sliding window of preset size to slide in GRYH to obtain multiple non-overlapping local areas;

[0116] Calculate the contrast coefficient of each local area separately;

[0117] The local area with the largest contrast coefficient is taken as the contrast area.

[0118] Preferably, the preset size of the sliding window is 25×25.

[0119] Preferably, respectively calculating the contrast coefficient of each local area includes:

[0120] Delete the local area that does not contain the boundary pixels, and use the following formula to calculate the contrast coefficient for the remaining local area:

[0121] The calculation formula of contrast coefficient is:

[0122]

[0123] compcef j Represents the contrast coefficient of local area j, numegpx j represents the number of boundary pixels contained in local area j, numtotal represents the total number of pixels contained in local area j, mij and maj represent the minimum and maximum grayscale values ​​of pixels in local area j respectively, numf kIt represents the number of pixels with gray value k in local area j, d1 represents the boundary factor, and d2 represents the effective data factor.

[0124] In the present invention, the contrast coefficient is related to the number of boundary pixels and the distribution of the number of pixels of different grayscale values ​​in the area. The more boundary pixels are included and the more uniform the distribution of the number of pixels of different grayscale values ​​is, the larger the contrast coefficient is. In this way, the area with the largest contrast coefficient in the construction site image can be accurately selected as the contrast area, thereby improving the accuracy of the subsequent color space determination of the present invention.

[0125] Preferably, the boundary factor is The effective data factor is

[0126] Preferably, determining the color space clspa where the initialization image is located based on the comparison area includes:

[0127] Obtaining a set LU of coordinates of pixel points in the comparison area;

[0128] Based on LU, the image component values ​​of the red, green and blue components of the construction site image in the RGB color space are calculated respectively;

[0129] Calculate the image component value of the L component of the construction site image in the Lab color space based on LU;

[0130] Calculate the image component value of the V component of the construction site image in the HSV color space based on LU;

[0131] The color space where the maximum image component value is located is taken as clspa.

[0132] By calculating the image component values, the single-channel image containing the most detail information can be screened out as the object of recognition, thereby increasing the accuracy of the final recognition of events that affect construction safety.

[0133] Preferably, the calculation formula of the image component value is:

[0134]

[0135] imgcompval q represents the image component value of image q, Uq represents the set of pixel points corresponding to the coordinates in LU in image q, and pval n represents the pixel value of pixel n in Uq in image q, Ugry represents the set of pixels corresponding to the coordinates in LU in image gry, and pval m Represents the grayscale value of pixel m in Ugry in image gry.

[0136] When calculating the image component value, the present invention calculates the variance of the areas corresponding to the coordinates in the LU in different images, so that the image carrying more detail information has a larger variance and the obtained image component value is larger, thereby identifying the image carrying more detail information.

[0137] Specifically, the pixel value has different value ranges in different images. For example, in the L component of the Lab color space, the value range is 0 to 100.

[0138] Preferably, obtaining the initialization image in clspa includes:

[0139] If clspa is an RGB color space, the image corresponding to the maximum image component value is used as the initialization image;

[0140] If clspa is the Lab color space, the L component image is used as the initialization image;

[0141] If clspa is in HSV color space, the V component image is used as the initialization image.

[0142] Preferably, the image recognition model comprises a CNN model.

[0143] When training the CNN model, images containing events that affect construction safety in different color spaces are used as training sets for training, thereby obtaining multiple CNN models that can detect events that affect construction safety in different color spaces.

[0144] Preferably, the initialization image is input into a pre-trained image recognition model for recognition, including:

[0145] Input the initialized image into the trained image recognition model corresponding to clspa for recognition.

[0146] Preferably, events that affect construction safety include the distance between construction workers and construction machinery being less than the safety distance, construction workers being located in a prohibited area, the number of construction machinery stacked in a construction passage being greater than a set number threshold, and the like.

[0147] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A construction project monitoring system, characterized in that: including zoning devices, drones and surveillance devices; The partition device is used to partition the construction site of the construction project and divide the construction site into multiple shooting areas, including: When monitoring the construction site for the first N times, the process of obtaining the shooting area includes: Divide the construction site into multiple shooting areas of equal size; Starting from the N+1th monitoring of the construction site, the process of obtaining the shooting area includes: The first step is to obtain a plan map containing the construction site; The second step is to establish a rectangular coordinate system in the plane map and obtain the outer rectangle of the area of ​​the construction site in the plane map; The third step is to initialize the value of b to 1, divide the outer rectangle into D regions of equal area, and store the obtained regions into the set Z. b ; The fourth step is to calculate Z b The regional coefficient of each region in ; Step 5: Add 1 to the value of b and take the areas whose regional coefficient is greater than the pre-set regional coefficient comparison value as set E. b The elements in the set F store the regions whose regional coefficients are less than or equal to the pre-set regional coefficient comparison value into the set F; Step 6: Determine E b Is the number of elements in set F 0? If so, each element in set F is taken as a shooting area, and the process of obtaining the shooting area is ended; if not, proceed to step 7; Step 7: E b Each element in is divided into D regions of equal area, and the obtained regions are stored in the set Z b , proceed to step 4; The drone is used to photograph each shooting area separately to obtain images of the construction site; The monitoring device is used to identify each construction site image separately to determine whether there is an event that affects construction safety in the construction site image; The calculation formula of the area coefficient is as follows: regcoft c represents the area coefficient of area c, evenum c Indicates the number of events that affect construction safety in area c during the most recent Nrec monitoring of the construction site, exte c represents the area of ​​region c, exte sc Indicates the area of ​​the construction site, equnum c represents the number of construction machines in area c when the construction site was monitored last time, equtotal represents the number of construction machines in the construction site when the construction site was monitored last time, λ1, λ2 and λ3 represent the first quantity factor, area factor and second quantity factor respectively; Identify each construction site image separately to determine whether there are any events that affect construction safety in the construction site image, including: Initialize each construction site image respectively to obtain an initialized image; Input the initialization image into the pre-trained image recognition model for recognition, and obtain the events that affect construction safety contained in the initialization image; Each construction site image is initialized to obtain an initialization image, including: Let h represent the construction site image, and the process of processing the hth image is as follows: Get the grayscale image gryh corresponding to h; Perform boundary detection on gryh to obtain boundary pixel points; Obtain the contrast area in h based on the boundary pixels; Determine the color space clspa where the initialization image is located based on the contrast area; Get the initialization image in clspa.

2. A construction project monitoring system according to claim 1, characterized in that: The construction site is divided into multiple shooting areas of equal size, including: Get a floor plan map that includes the construction site; Establishing a rectangular coordinate system in the plane map, and obtaining an outer rectangle of the construction site area in the plane map; Divide the outer rectangle into multiple shooting areas of equal size.

3. A construction project monitoring system according to claim 1 or 2, characterized in that: Get the outer rectangle of the construction site area in the plan map, including: A1 and A2 represent the maximum and minimum values ​​of the abscissa of the area of ​​the construction site in the rectangular coordinate system respectively; B1 and B2 represent the maximum and minimum values ​​of the vertical coordinates of the area of ​​the construction site in the rectangular coordinate system respectively; Then the horizontal coordinates of the pixel points in the outer rectangle satisfy A2≤x≤A1 and the vertical coordinates satisfy B2≤y≤B1, where x and y are the horizontal coordinates and vertical coordinates of the pixel points respectively.

4. A construction project monitoring system according to claim 1, characterized in that: Divide the outer rectangle into multiple shooting areas of equal size, including: L1 and W1 represent the length and width of the outer rectangle respectively; L2 and W2 represent the length and width of the image captured by the drone at the restricted flight altitude H, which correspond to the length and width of the plane map containing the construction site; Then in the outer rectangle, the number of rows in the shooting area is The number of columns in the shooting area is Divide the outer rectangle into The same shooting area.

5. A construction project monitoring system according to claim 1, characterized in that: The value of D is 4.

6. A construction project monitoring system according to claim 1, characterized in that: Divide the outer rectangle into D regions of equal area, including: L1 and W1 represent the length and width of the outer rectangle respectively, and the length of the area is The width of the region is Divide the outer rectangle into D parts with an area of area.

7. A construction project monitoring system according to claim 1, characterized in that: The first quantity factor, area factor and second quantity factor are and 8. A construction project monitoring system according to claim 7, characterized in that: The area coefficient control value set in advance is 9. A construction project monitoring system according to claim 1, characterized in that: Each shooting area is photographed separately to obtain construction site images, including: The shooting areas are photographed above the center of each shooting area, so that the construction site image obtained by shooting can include the complete shooting area.

Images