CN118842880B - A construction project monitoring system - Google Patents
A construction project monitoring system Download PDFInfo
- Publication number
- CN118842880B CN118842880B CN202410840711.3A CN202410840711A CN118842880B CN 118842880 B CN118842880 B CN 118842880B CN 202410840711 A CN202410840711 A CN 202410840711A CN 118842880 B CN118842880 B CN 118842880B
- Authority
- CN
- China
- Prior art keywords
- construction
- area
- construction site
- image
- region
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/08—Construction
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Signal Processing (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Primary Health Care (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Remote Sensing (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Image Analysis (AREA)
- Emergency Alarm Devices (AREA)
Abstract
本发明属于施工监控领域，公开了一种建设工程施工监控系统，包括分区装置、无人机和监控装置；分区装置用于对建设工程的施工现场进行分区，将施工现场分为多个拍摄区域；无人机用于分别对每个拍摄区域进行拍摄，获得施工现场图像；监控装置用于分别对每个施工现场图像进行识别，判断施工现场图像中是否存在影响施工安全的事件。本发明提高获得整个施工现场的监控结果的效率，还能够给出现影响施工安全的事件的概率高的区域拍摄分辨率更高的照片，进一步提高识别的准确性。
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 judge 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
The invention relates to the field of construction monitoring, in particular to a construction monitoring system for construction engineering.
Background
In order to improve the safety of construction engineering of outdoor construction, in the prior art, an unmanned aerial vehicle is generally used for shooting a construction site of the construction engineering to obtain an image of the construction site, and then whether an event affecting the construction safety exists in the image is judged by means of manual identification or machine identification.
When the area of a construction site is relatively large, the requirement of complete coverage cannot be met by single shooting, the prior art generally divides the construction site into a plurality of shooting areas with the same area, then uses an unmanned aerial vehicle to shoot each shooting area respectively to obtain a plurality of images with the preset number, and then carries out manual identification or machine identification on each image respectively to obtain a monitoring result of the whole construction site.
However, this photographing method does not take into account the different positions in the construction site, and the probability of occurrence of an event affecting the construction safety is different. The fixed quantity of the method is easy to cause that too many images are shot in the area with low probability of affecting the construction safety, and the efficiency of obtaining the monitoring result of the whole construction site is affected due to the fact that too many images need to be identified, so that the method is not beneficial to timely finding the event affecting the construction safety of the construction site of the construction engineering.
Disclosure of Invention
The invention aims to disclose a construction monitoring system for construction engineering, which solves the problem of reasonably determining the number of images on the premise of ensuring the monitoring effect in the process of shooting a construction site of the construction engineering by using an unmanned aerial vehicle and carrying out safety monitoring according to the shot images, thereby improving the efficiency of obtaining the monitoring result of the whole construction site.
In order to achieve the above purpose, the invention adopts the following technical scheme:
The invention provides a construction monitoring system for construction engineering, which comprises a partitioning device, an unmanned aerial vehicle and a monitoring device;
the subregion device is used for carrying out the subregion to the job site of construction engineering, divides into a plurality of shooting regions with the job site, includes:
When monitoring the construction site for the first N times, the process of acquiring the shooting area comprises the following steps:
dividing a construction site into a plurality of shooting areas with the same area;
Starting from the (n+1) th time of monitoring the construction site, the process of acquiring the shooting area comprises the following steps:
firstly, obtaining a plane map containing a construction site;
secondly, establishing a rectangular coordinate system in the planar map, and acquiring a peripheral rectangle of a construction site area in the planar map;
Thirdly, initializing the value of b to be 1, dividing the peripheral rectangle into D areas with the same area, and storing the obtained areas into a set Z b;
fourthly, calculating the region coefficient of each region in Z b respectively;
Fifthly, adding 1 to the value of b, taking the region with the region coefficient larger than the region coefficient comparison value set in advance as an element in the set E b, and storing the region with the region coefficient smaller than or equal to the region coefficient comparison value set in advance into the set F;
step six, judging whether the number of the elements in the E b is 0, if so, taking each element in the set F as a shooting area respectively, and ending the process of acquiring the shooting area;
Seventh, dividing each element in E b into areas with the same area as D, storing the obtained areas into a set Z b, and entering a fourth step;
the unmanned aerial vehicle is used for shooting each shooting area respectively to obtain a construction site image;
The monitoring device is used for respectively identifying each construction site image and judging whether an event affecting construction safety exists in the construction site images.
Preferably, dividing the construction site into a plurality of photographing areas having the same area includes:
acquiring a plane map containing a construction site;
establishing a rectangular coordinate system in a planar map, and acquiring a peripheral rectangle of a region of a construction site in the planar map;
The peripheral rectangle is divided into a plurality of photographing regions of the same area.
Preferably, acquiring a peripheral rectangle of an area of a construction site in a planar map includes:
A1 and A2 are respectively used for representing the maximum value and the minimum value of the abscissa of the area of the construction site in a rectangular coordinate system;
respectively using B1 and B2 to represent the maximum value and the minimum value of the ordinate of the area of the construction site in a rectangular coordinate system;
The abscissa of the pixel points in the peripheral rectangle satisfies A2 x 1 and the ordinate satisfies B2 y1, x and y are the abscissa and the ordinate of the pixel points, respectively.
Preferably, dividing the peripheral rectangle into a plurality of photographing regions of the same area includes:
The length and the width of the peripheral rectangle are respectively represented by L1 and W1, and the length and the width of the image are respectively represented by L2 and W2 in the image shot by the unmanned aerial vehicle at the limited flying height H and correspond to the length and the width of the image in a plane map containing a construction site;
The number of lines of the photographing region is in the peripheral rectangle The number of columns of the shooting area is
Dividing the peripheral rectangle intoThe shooting areas are the same in area.
Preferably, D has a value of 4.
Preferably, dividing the peripheral rectangle into D areas of equal area comprises:
the length and width of the peripheral rectangle are denoted by L1 and W1, respectively, the length of the region being The width of the region is
Dividing the peripheral rectangle into D areasIs a region of (a) in the above-mentioned region(s).
Preferably, the area coefficient is calculated as follows:
regcoft c denotes a region coefficient of the region c, evenum c denotes the number of events affecting the construction safety in the region c during the last Nrec times of monitoring the construction site, exte c denotes the area of the region c, exte sc denotes the area of the construction site, equnum c denotes the number of construction machines present in the region c when the construction site was monitored last time, equtotal denotes the number of construction machines present in the construction site when the construction site was monitored last time, and λ 1、λ2 and λ 3 denote the first number factor, the area factor, and the second number factor, respectively.
Preferably, the first number factor, the area factor and the second number factor are respectivelyAnd
Preferably, the area coefficient comparison value set in advance is
Preferably, photographing each photographing region separately to obtain a construction site image, including:
the shooting areas are respectively shot above the center of each shooting area, so that the shot construction site image can contain the complete shooting area.
The beneficial effects are that:
The method is different from the existing method for designating the number of shooting areas in advance, the shooting areas with the same size are adopted in the process of monitoring the construction site for the first N times, then, the method can adaptively obtain the areas with different sizes based on the area coefficient, the number of the areas is also related to the number of the events affecting the construction safety, the area of the areas and the number of the existing construction machines, which occur at different positions in the construction site, so that the area of the area with lower probability of the events affecting the construction safety is smaller, the area of the area with higher probability of the events affecting the construction safety is smaller, the number of the shooting areas is changed along with the change of the actual condition of the construction site, the occurrence probability of the events with excessive images shot at the area with lower probability of the events affecting the construction safety can be effectively reduced, the efficiency of obtaining the monitoring result of the whole construction site is improved, the picture with higher resolution of the areas with higher probability of the events affecting the construction safety can also be provided, and the recognition accuracy is further improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic diagram of a construction monitoring system for construction projects according to the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present invention.
The invention provides a construction monitoring system for a construction project, which is shown in an embodiment in fig. 1, and comprises a partitioning device, a unmanned plane and a monitoring device;
the subregion device is used for carrying out the subregion to the job site of construction engineering, divides into a plurality of shooting regions with the job site, includes:
When monitoring the construction site for the first N times, the process of acquiring the shooting area comprises the following steps:
dividing a construction site into a plurality of shooting areas with the same area;
Starting from the (n+1) th time of monitoring the construction site, the process of acquiring the shooting area comprises the following steps:
firstly, obtaining a plane map containing a construction site;
secondly, establishing a rectangular coordinate system in the planar map, and acquiring a peripheral rectangle of a construction site area in the planar map;
Thirdly, initializing the value of b to be 1, dividing the peripheral rectangle into D areas with the same area, and storing the obtained areas into a set Z b;
fourthly, calculating the region coefficient of each region in Z b respectively;
Fifthly, adding 1 to the value of b, taking the region with the region coefficient larger than the region coefficient comparison value set in advance as an element in the set E b, and storing the region with the region coefficient smaller than or equal to the region coefficient comparison value set in advance into the set F;
step six, judging whether the number of the elements in the E b is 0, if so, taking each element in the set F as a shooting area respectively, and ending the process of acquiring the shooting area;
Seventh, dividing each element in E b into areas with the same area as D, storing the obtained areas into a set Z b, and entering a fourth step;
the unmanned aerial vehicle is used for shooting each shooting area respectively to obtain a construction site image;
The monitoring device is used for respectively identifying each construction site image and judging whether an event affecting construction safety exists in the construction site images.
In the scheme, the invention adopts the shooting areas with the same size in the process of monitoring the construction site for the first N times, then, the invention adaptively obtains the areas with different sizes based on the area coefficient, the number of the areas is also related to the number of the events affecting the construction safety, the area of the areas and the number of the existing construction machines, which occur at different positions in the construction site, so that the area of the area with lower probability of the events affecting the construction safety is smaller, the area of the area with higher probability of the events affecting the construction safety is smaller, the number of the shooting areas is changed along with the change of the real condition of the construction site, the occurrence probability of the events with excessive images shot at the area with low probability of the construction safety can be effectively reduced, the efficiency of obtaining the monitoring result of the whole construction site is improved, the photo with higher resolution of the area with higher probability of the events affecting the construction safety can be given, and the identification accuracy is further improved.
Preferably, the value of N is 5.
Preferably, dividing the construction site into a plurality of photographing areas having the same area includes:
acquiring a plane map containing a construction site;
establishing a rectangular coordinate system in a planar map, and acquiring a peripheral rectangle of a region of a construction site in the planar map;
The peripheral rectangle is divided into a plurality of photographing regions of the same area.
By acquiring the peripheral rectangle, the irregular construction site area is contained in one regular peripheral rectangle, so that the subsequent division of the rectangular area is facilitated.
Preferably, establishing a rectangular coordinate system in the planar map includes:
And establishing a rectangular coordinate system in the plane map by taking the lower left corner of the plane map as the origin of coordinates, taking the north-right direction of the plane map as the positive direction of the Y axis and the east-right direction as the positive direction of the X axis.
Preferably, acquiring a peripheral rectangle of an area of a construction site in a planar map includes:
A1 and A2 are respectively used for representing the maximum value and the minimum value of the abscissa of the area of the construction site in a rectangular coordinate system;
respectively using B1 and B2 to represent the maximum value and the minimum value of the ordinate of the area of the construction site in a rectangular coordinate system;
The abscissa of the pixel points in the peripheral rectangle satisfies A2 x 1 and the ordinate satisfies B2 y1, x and y are the abscissa and the ordinate of the pixel points, respectively.
Preferably, dividing the peripheral rectangle into a plurality of photographing regions of the same area includes:
The length and the width of the peripheral rectangle are respectively represented by L1 and W1, and the length and the width of the image are respectively represented by L2 and W2 in the image shot by the unmanned aerial vehicle at the limited flying height H and correspond to the length and the width of the image in a plane map containing a construction site;
The number of lines of the photographing region is in the peripheral rectangle The number of columns of the shooting area is
Dividing the peripheral rectangle intoThe shooting areas are the same in area.
Further, in obtainingAfter shooting areas with the same area, respectively acquiring intersections of pixel points corresponding to each shooting area and corresponding pixel points of the area of the construction site;
the shot region whose intersection is the empty set is deleted.
Since the irregular areas of the construction site are regularized before, and the areas which do not originally belong to the construction site are introduced, if the areas are subjected to area coefficient calculation, shooting by using an unmanned aerial vehicle and the like, the speed of obtaining the monitoring result is obviously influenced, so that the effectiveness of the remaining shooting areas can be improved through the screening process, and the efficiency of obtaining the monitoring result of the whole construction site is improved.
Preferably, D has a value of 4.
Further, D may also have a value of 9.
Preferably, dividing the peripheral rectangle into D areas of equal area comprises:
the length and width of the peripheral rectangle are denoted by L1 and W1, respectively, the length of the region being The width of the region is
Dividing the peripheral rectangle into D areasIs a region of (a) in the above-mentioned region(s).
By dividing the peripheral rectangle into areas of the same area, the area coefficient of each area can be calculated separately, starting the process of the present invention of circularly acquiring as a shooting area.
Preferably, the area coefficient is calculated as follows:
regcoft c denotes a region coefficient of the region c, evenum c denotes the number of events affecting the construction safety in the region c during the last Nrec times of monitoring the construction site, exte c denotes the area of the region c, exte sc denotes the area of the construction site, equnum c denotes the number of construction machines present in the region c when the construction site was monitored last time, equtotal denotes the number of construction machines present in the construction site when the construction site was monitored last time, and λ 1、λ2 and λ 3 denote the first number factor, the area factor, and the second number factor, respectively.
In the present invention, the region coefficient is related to the most recent Nrec monitoring results, and when the number of events affecting the construction safety is increased, the area is increased, and the number of construction machines is increased in the region c, the region coefficient is increased, so that the probability of such region being continuously divided is increased. The calculation mode of the area coefficient ensures that the number of the shooting areas obtained finally is adaptively related to the occurrence times of the events affecting the construction safety, the area of the areas and the number of the construction machines, thereby effectively reducing the number of the shooting areas with low probability of the events affecting the construction safety, realizing the self-adaptive change of the number of the shooting areas and effectively improving the efficiency of monitoring the construction site.
Preferably Nrec has a value of 5.
Preferably, the first number factor, the area factor and the second number factor are respectivelyAnd
Preferably, the area coefficient comparison value set in advance is
Preferably, photographing each photographing region separately to obtain a construction site image, including:
the shooting areas are respectively shot above the center of each shooting area, so that the shot construction site image can contain the complete shooting area.
Further, when shooting the shooting area, the shooting height can make the proportion of the shooting area in the construction site maximum.
The process of photographing the height includes:
when shooting the shooting areas at different heights, the proportion of the areas of the shooting areas in the construction site image is different, the proportion is higher and higher along with the lower shooting height, and finally, the height which can enable the shooting areas to completely appear in the construction site image and has the largest proportion is determined, and the height is taken as the shooting height.
Preferably, the identifying each construction site image separately, judging whether there is an event affecting construction safety in the construction site image, includes:
Initializing each construction site image to obtain an initialized image;
Inputting the initialized image into a pre-trained image recognition model for recognition, and acquiring an event which is contained in the initialized image and affects construction safety.
Preferably, the initializing process is performed on each construction site image to obtain an initialized image, including:
H is used for representing a construction site image, and the treatment process of the h is as follows:
Acquiring a gray image gryh corresponding to h;
performing boundary detection on gryh to obtain boundary pixel points;
Acquiring a contrast area in h based on boundary pixel points;
determining a color space clspa in which the initialized image is based on the contrast region;
An initialization image is acquired at clspa.
In the conventional image recognition method, only a gray image is used as input data to be input into an image recognition model for recognition, but the recognition method does not consider that under different shooting conditions, component images with more effective image detail information exist in different color spaces, so that the gray image is directly taken as a recognition object, and the accuracy of recognition may be affected due to insufficient information contained in the gray image.
Therefore, the invention firstly passes the boundary detection, then acquires the comparison area, and selects the color space for acquiring the initialized image based on the comparison area, and because the comparison area has outstanding representativeness, the color space can be prevented from being compared based on all the images, and accurate comparison results can be obtained only by comparing based on the comparison area. The efficiency of contrast is effectively improved, thereby improving the efficiency of obtaining an initialized image in an optimal color space.
Preferably, the boundary detection algorithm includes Edge-Flow, frei-Chen, and the like. Only one of them is selected for boundary detection.
Preferably, acquiring the contrast area in h based on the boundary pixel point includes:
sliding in gryh by using a sliding window with a preset size to obtain a plurality of non-overlapping local areas;
respectively calculating the contrast coefficient of each local area;
and taking the local area with the largest contrast coefficient as a contrast area.
Preferably, the preset size of the sliding window is 25×25.
Preferably, calculating the contrast coefficient of each local area separately includes:
deleting the local area which does not contain the boundary pixel points, and calculating the contrast coefficient of the rest local area by adopting the following formula:
the calculation formula of the contrast coefficient is as follows:
compcef j denotes a contrast coefficient of the local region j, numegpx j denotes the number of boundary pixel points included in the local region j, numtotal denotes the total number of pixel points included in the local region j, mij and maj denote the minimum and maximum values of the gradation value of the pixel points in the local region j, respectively, numf k denotes the number of pixel points having a gradation value k in the local region j, d 1 denotes the boundary factor, and d 2 denotes the effective data factor.
In the invention, the contrast coefficient is related to the number of boundary pixel points and the number distribution of the pixel points with different gray values in the area, and the more the number of the boundary pixel points is contained, the more the number distribution among the pixel points with different gray values is uniform, the larger the contrast coefficient is, so that the area with the largest contrast coefficient in the construction site image can be accurately selected as the contrast area, and the accuracy of the subsequent color space determination of the invention is improved.
Preferably, the boundary factor isThe effective data factor is
Preferably, determining the color space clspa in which the initialization image is located based on the contrast region includes:
Acquiring a set LU of coordinates of pixel points in a comparison area;
calculating image component values of three components of red, green and blue of the construction site image in an RGB color space based on the LU respectively;
calculating an image component value of an L component of the construction site image in the Lab color space based on the LU;
Calculating an image component value of a V component of the job site image in the HSV color space based on the LU;
the color space in which the largest image component value is located is taken as clspa.
By calculating the image component values, single-channel images containing the most detailed information can be screened out to serve as identification objects, and the accuracy of finally identifying the event affecting construction safety is improved.
Preferably, the calculation formula of the image component values is:
imgcompval q denotes an image component value of the image q, uq denotes a set of pixels corresponding to coordinates in the LU in the image q, pval n denotes a pixel value of a pixel n in the Uq in the image q, ugry denotes a set of pixels corresponding to coordinates in the LU in the image gry, pval m denotes a gray value of a pixel m in the Ugry in the image gry.
When the image component value is calculated, the variance is calculated on the corresponding areas of the coordinates in the LU in different images, so that the larger the image carrying the detail information is, the larger the variance is, the larger the obtained image component value is, and the image carrying the detail information is identified.
Specifically, the pixel values are different in the value ranges in different images, for example, the value ranges from 0 to 100 in the L component of the Lab color space.
Preferably, acquiring an initialization image in clspa includes:
if clspa is RGB color space, the image corresponding to the largest image component value is used as the initialization image;
if clspa is Lab color space, taking the L component image as an initialization image;
if clspa is HSV color space, the V component image is used as the initialization image.
Preferably, the image recognition model comprises a CNN model.
When the CNN model is trained, images containing the events affecting construction safety in different color spaces are used as training sets to train, so that a plurality of CNN models which can respond to the events affecting construction safety in different color spaces are obtained.
Preferably, inputting the initialized image into a pre-trained image recognition model for recognition includes:
inputting the initialized image into a training-before image recognition model corresponding to clspa for recognition.
Preferably, the event affecting the construction safety includes that the distance between the constructor and the construction machine is smaller than the safety distance, that the constructor is located in an area where access is prohibited, that the number of construction machines piled up in the construction passageway is larger than a set number threshold value, etc.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (9)
1. The construction monitoring system for the construction engineering is characterized by comprising a partitioning device, an unmanned aerial vehicle and a monitoring device;
the subregion device is used for carrying out the subregion to the job site of construction engineering, divides into a plurality of shooting regions with the job site, includes:
When monitoring the construction site for the first N times, the process of acquiring the shooting area comprises the following steps:
dividing a construction site into a plurality of shooting areas with the same area;
Starting from the (n+1) th time of monitoring the construction site, the process of acquiring the shooting area comprises the following steps:
firstly, obtaining a plane map containing a construction site;
secondly, establishing a rectangular coordinate system in the planar map, and acquiring a peripheral rectangle of a construction site area in the planar map;
Thirdly, initializing the value of b to be 1, dividing the peripheral rectangle into D areas with the same area, and storing the obtained areas into a set Z b;
fourthly, calculating the region coefficient of each region in Z b respectively;
Fifthly, adding 1 to the value of b, taking the region with the region coefficient larger than the region coefficient comparison value set in advance as an element in the set E b, and storing the region with the region coefficient smaller than or equal to the region coefficient comparison value set in advance into the set F;
step six, judging whether the number of the elements in the E b is 0, if so, taking each element in the set F as a shooting area respectively, and ending the process of acquiring the shooting area;
Seventh, dividing each element in E b into areas with the same area as D, storing the obtained areas into a set Z b, and entering a fourth step;
the unmanned aerial vehicle is used for shooting each shooting area respectively to obtain a construction site image;
the monitoring device is used for respectively identifying each construction site image and judging whether an event affecting construction safety exists in the construction site images or not;
the calculation formula of the region coefficients is as follows:
regcoft c denotes an area coefficient of an area c, evenum c denotes the number of events affecting construction safety in the area c during the last Nrec times of monitoring of the construction site, exte c denotes the area of the area c, exte sc denotes the area of the construction site, equnum c denotes the number of construction machines present in the area c when the construction site was monitored last time, equtotal denotes the number of construction machines present in the construction site when the construction site was monitored last time, and λ 1、λ2 and λ 3 denote a first number factor, an area factor, and a second number factor, respectively;
Identifying each construction site image respectively, judging whether an event affecting construction safety exists in the construction site images or not, and comprising the following steps:
Initializing each construction site image to obtain an initialized image;
Inputting the initialized image into a pre-trained image recognition model for recognition, and acquiring an event which is contained in the initialized image and affects construction safety;
Initializing each construction site image to obtain an initialized image, wherein the initializing comprises the following steps:
H is used for representing a construction site image, and the treatment process of the h is as follows:
Acquiring a gray image gryh corresponding to h;
performing boundary detection on gryh to obtain boundary pixel points;
Acquiring a contrast area in h based on boundary pixel points;
determining a color space clspa in which the initialized image is based on the contrast region;
An initialization image is acquired at clspa.
2. The construction engineering construction monitoring system according to claim 1, wherein the construction site is divided into a plurality of shot areas having the same area, comprising:
acquiring a plane map containing a construction site;
establishing a rectangular coordinate system in a planar map, and acquiring a peripheral rectangle of a region of a construction site in the planar map;
The peripheral rectangle is divided into a plurality of photographing regions of the same area.
3. A construction engineering construction monitoring system according to claim 1 or 2, wherein obtaining a peripheral rectangle of an area of a construction site in a planar map comprises:
A1 and A2 are respectively used for representing the maximum value and the minimum value of the abscissa of the area of the construction site in a rectangular coordinate system;
respectively using B1 and B2 to represent the maximum value and the minimum value of the ordinate of the area of the construction site in a rectangular coordinate system;
The abscissa of the pixel points in the peripheral rectangle satisfies A2 x 1 and the ordinate satisfies B2 y1, x and y are the abscissa and the ordinate of the pixel points, respectively.
4. The construction engineering construction monitoring system according to claim 1, wherein dividing the peripheral rectangle into a plurality of shot areas having the same area, comprises:
The length and the width of the peripheral rectangle are respectively represented by L1 and W1, and the length and the width of the image are respectively represented by L2 and W2 in the image shot by the unmanned aerial vehicle at the limited flying height H and correspond to the length and the width of the image in a plane map containing a construction site;
The number of lines of the photographing region is in the peripheral rectangle The number of columns of the shooting area is
Dividing the peripheral rectangle intoThe shooting areas are the same in area.
5. A construction engineering construction monitoring system according to claim 1, wherein D has a value of 4.
6. A construction engineering construction monitoring system according to claim 1, wherein dividing the peripheral rectangle into D areas of the same area comprises:
the length and width of the peripheral rectangle are denoted by L1 and W1, respectively, the length of the region being The width of the region is
Dividing the peripheral rectangle into D areasIs a region of (a) in the above-mentioned region(s).
7. The construction engineering construction monitoring system according to claim 1, wherein the first quantity factor, the area factor and the second quantity factor are respectivelyAnd
8. The construction engineering construction monitoring system according to claim 7, wherein the area coefficient comparison value set in advance is
9. The construction engineering construction monitoring system according to claim 1, wherein photographing each photographing region separately to obtain a construction site image comprises:
the shooting areas are respectively shot above the center of each shooting area, so that the shot construction site image can contain the complete shooting area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410840711.3A CN118842880B (en) | 2024-06-27 | 2024-06-27 | A construction project monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410840711.3A CN118842880B (en) | 2024-06-27 | 2024-06-27 | A construction project monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118842880A CN118842880A (en) | 2024-10-25 |
| CN118842880B true CN118842880B (en) | 2025-03-28 |
Family
ID=93147433
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410840711.3A Active CN118842880B (en) | 2024-06-27 | 2024-06-27 | A construction project monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118842880B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119315435A (en) * | 2024-12-12 | 2025-01-14 | 国网四川省电力公司信息通信公司 | An intelligent substation inspection system based on drone technology and image analysis technology |
| CN119996632A (en) * | 2025-02-26 | 2025-05-13 | 山东潍旭项目管理有限公司 | An intelligent remote security monitoring system for construction projects |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112903026A (en) * | 2021-02-25 | 2021-06-04 | 南京翰氜信息科技有限公司 | Engineering safety remote online monitoring system based on machine vision and artificial intelligence |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9989965B2 (en) * | 2015-08-20 | 2018-06-05 | Motionloft, Inc. | Object detection and analysis via unmanned aerial vehicle |
| CN113741527B (en) * | 2021-09-13 | 2024-01-19 | 德仕能源科技集团股份有限公司 | Oil well inspection method, equipment and medium based on multiple unmanned aerial vehicles |
| KR102855954B1 (en) * | 2022-07-26 | 2025-09-08 | 한국수자원공사 | Construction safety monitering integrated control system and construction for construction safety monitering integrated control centor structured the same |
| CN115454132A (en) * | 2022-09-30 | 2022-12-09 | 西安万飞控制科技有限公司 | A 3D path planning method and system for unmanned aerial vehicle inspection for mountainous photovoltaic power plants |
| CN117475608B (en) * | 2023-12-28 | 2024-03-08 | 云南远信科技有限公司 | Multi-scene security monitoring method based on unmanned aerial vehicle cluster |
-
2024
- 2024-06-27 CN CN202410840711.3A patent/CN118842880B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112903026A (en) * | 2021-02-25 | 2021-06-04 | 南京翰氜信息科技有限公司 | Engineering safety remote online monitoring system based on machine vision and artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118842880A (en) | 2024-10-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118842880B (en) | A construction project monitoring system | |
| CN110060237B (en) | Fault detection method, device, equipment and system | |
| CN110163842B (en) | Building crack detection method and device, computer equipment and storage medium | |
| CN109829445B (en) | Vehicle detection method in video stream | |
| CN112241699A (en) | Object defect category identification method and device, computer equipment and storage medium | |
| CN111935479B (en) | Target image determination method and device, computer equipment and storage medium | |
| US12159405B2 (en) | Method for detecting medical images, electronic device, and storage medium | |
| CN112070079B (en) | X-ray contraband package detection method and device based on feature map weighting | |
| CN108009543A (en) | A kind of licence plate recognition method and device | |
| US8649612B1 (en) | Parallelizing cascaded face detection | |
| CN111797829A (en) | License plate detection method and device, electronic equipment and storage medium | |
| CN109711407B (en) | License plate recognition method and related device | |
| CN112597846A (en) | Lane line detection method, lane line detection device, computer device, and storage medium | |
| CN112329881A (en) | License plate recognition model training method, license plate recognition method and device | |
| CN111803956B (en) | Method and device for determining game plug-in behavior, electronic equipment and storage medium | |
| CN112926426A (en) | Ship identification method, system, equipment and storage medium based on monitoring video | |
| CN112330619A (en) | Method, device and equipment for detecting target area and storage medium | |
| CN114170642A (en) | Image detection processing method, device, equipment and storage medium | |
| CN109816720B (en) | Road center detection method, airborne equipment and storage medium | |
| CN112419231B (en) | Visibility determination method, apparatus, computer device, and storage medium | |
| CN118644868A (en) | A container identification method | |
| CN119360362B (en) | Image processing method and device, electronic equipment and storage medium | |
| CN110569921A (en) | Vehicle logo identification method, system, device and computer readable medium | |
| CN113065454B (en) | High-altitude parabolic target identification and comparison method and device | |
| CN114494712B (en) | Object extraction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |