Remote supervision method and device and medium
By using drones to capture images and combining them with 3D models and convolutional neural networks to identify building components, the problem of ensuring construction quality during manual inspections has been solved, enabling efficient and reliable project progress assessment and delay warnings.
Patent Information
- Application Number
- CN202410858324.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-06-28
- Publication Date
- 2025-12-30
AI Technical Summary
Current construction project supervision mainly relies on manual inspections, which makes it difficult to guarantee construction quality and accurately assess progress, and is prone to omissions and subjective errors.
By using drones to capture images and constructing 3D models and convolutional neural networks to identify building components, and combining internal and external image information, the actual construction progress can be calculated and delay warnings can be issued.
It enables efficient and reliable project progress assessment, reduces subjective errors from manual inspections, and improves the accuracy and efficiency of construction quality control.
Smart Images
Figure CN121236631A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of image data processing technology, and in particular to a remote monitoring method, device and medium. Background Technology
[0002] Currently, the supervision of construction projects mostly relies on manual inspections. However, manual inspections cannot quickly cover all parts of the entire construction project, are prone to omissions, and result in compromised construction quality. Furthermore, manual inspections depend heavily on subjective experience, making it difficult to obtain reliable project progress information. Summary of the Invention
[0003] The purpose of this invention is to provide a remote supervision method, device, and medium that uses drones to capture images for remote supervision of construction projects, thereby obtaining reliable and effective project progress data and realizing project progress management.
[0004] The objective of this invention can be achieved through the following technical solutions:
[0005] A remote supervision method includes the following steps:
[0006] A drone control scheme is pre-designed based on the construction progress of the building project;
[0007] Determine the corresponding drone control scheme based on the current planned construction progress, and control the drone to capture images related to the construction project.
[0008] By comparing the overlapping and differences between the current images taken by the drone and the design drawings, the actual construction progress can be determined.
[0009] The method for determining the actual construction progress by comparing the overlap and differences between the current images captured by the drone and the design drawings is as follows:
[0010] Reconstruct the 3D model of the building project based on the current image and the design drawings respectively, to obtain the current 3D model of the building project and the design 3D model;
[0011] The current 3D model of the building project is scaled and its angle adjusted so that the corners of its building structure overlap with the design 3D model.
[0012] Calculate the ratio of the volume of the overlapping part of the two 3D models to the volume of the designed 3D model to determine the actual construction progress.
[0013] The images of the construction project captured by the drone include both external and internal images of the construction project.
[0014] The method for determining the actual construction progress by comparing the overlap and differences between the current images captured by the drone and the design drawings is as follows:
[0015] Identify the types and quantities of building components in the current internal images captured by the drone, compare them with the types and quantities of building components in the design drawings, and calculate the completion rate of the internal project;
[0016] Identify the architectural structure, types and quantities of building components, and architectural texture information in the current external images captured by the drone, compare them with the design images, and calculate the completion rate of the external project;
[0017] The actual construction progress is calculated by combining the completion rates of internal and external projects.
[0018] The method for calculating the actual construction progress by combining the completion rates of internal and external projects is as follows: express the completion rates of internal and external projects as percentages, and calculate the average of the two to obtain the actual construction progress.
[0019] The identification of the types and quantities of building components is achieved using a target detection model.
[0020] The recognition of the building structure and building texture information is achieved using a convolutional neural network.
[0021] The method further includes:
[0022] Compare the actual construction progress with the planned construction progress to determine if there are any project delays. If there are delays, issue a delay warning.
[0023] A remote monitoring device includes a memory, a processor, and a program stored in the memory, wherein the processor executes the program to implement the method described above.
[0024] A storage medium having a program stored thereon, which, when executed, implements the method described above.
[0025] Compared with the prior art, the present invention has the following beneficial effects:
[0026] (1) By designing the UAV control scheme in advance, the present invention can control the UAV to take the required images at the appropriate position according to the planned schedule, avoiding subsequent image processing errors caused by inaccurate image shooting position and angle, improving the effectiveness of the captured images, reducing invalid image redundancy, and improving processing efficiency.
[0027] (2) The present invention calculates the actual construction progress by comparing the degree of overlap and difference between the current image and the design drawings. The method is simple and can effectively utilize the building engineering details in the reconstructed model volume or image. The calculated project progress is highly reliable and is not affected by subjective experience. Attached Figure Description
[0028] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation
[0029] The present invention will now be described in detail with reference to the accompanying drawings and specific embodiments. These embodiments are based on the technical solution of the present invention and provide detailed implementation methods and specific operating procedures. However, the scope of protection of the present invention is not limited to the following embodiments.
[0030] This embodiment provides a remote supervision method, such as Figure 1 As shown, it includes the following steps:
[0031] S1, pre-sets a drone control scheme based on the construction progress of the building project.
[0032] The processor pre-stores multiple drone control schemes, each corresponding to a different construction schedule. Each drone control scheme records the flight path and the hovering coordinates within that flight path.
[0033] S2, determine the corresponding drone control scheme based on the current planned construction progress, and control the drone to take images related to the construction project.
[0034] When the preset supervision period is reached or a real-time supervision request is received, the drone control scheme is executed to control the drone to fly along the flight path recorded in the drone control scheme. When the drone reaches each hovering coordinate point, it stays for a preset period of time. During this period, the image acquisition device built into the drone is controlled to collect and feed back architectural images of the building to be supervised.
[0035] In another embodiment, the image acquisition tasks in steps S1 and S2 can also be carried out by cameras fixed at certain preset locations, or by patrol personnel carrying cameras.
[0036] S3 compares the overlapping and differences between the current images taken by the drone and the design drawings to determine the actual construction progress.
[0037] In one embodiment, the actual construction progress can be determined by constructing a three-dimensional model, specifically including the following steps:
[0038] S301, reconstruct the three-dimensional model of the building project based on the current image and the design drawings respectively, to obtain the current three-dimensional model of the building project and the design three-dimensional model;
[0039] S302, scale and adjust the angle of the current 3D model of the building project so that the corners of the building structure overlap with the design 3D model;
[0040] S303 calculates the proportion of the volume of the overlapping part of the two 3D models to the volume of the designed 3D model, and determines the actual construction progress.
[0041] In another embodiment, the images of the construction project captured by the drone include external and internal images of the construction project. The construction progress can be determined based on the degree of overlap of important information in the images, specifically including the following steps:
[0042] S311 uses a target detection model to identify the types and quantities of building components in the current internal images captured by the drone, and compares them with the types and quantities of building components in the design drawings to calculate the completion rate of the internal project.
[0043] S312 uses a convolutional neural network to identify the architectural structure, type and quantity of building components, and architectural texture information in the current external image captured by the drone, and compares it with the design image to calculate the completion rate of the external project.
[0044] S313, calculate the actual construction progress by combining the completion rates of internal and external works.
[0045] Specifically, the completion rate of internal and external projects is expressed as a percentage, and the average of the two is calculated to obtain the actual construction progress.
[0046] S4 compares the actual construction progress with the planned construction progress to determine if there are any project delays. If there are project delays, a delay warning is issued.
[0047] This embodiment also provides a remote monitoring device, including a memory, a processor, and a program stored in the memory, wherein the processor executes the program to implement the method described above.
[0048] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0049] The preferred embodiments of the present invention have been described in detail above. It should be understood that those skilled in the art can make numerous modifications and variations based on the concept of the present invention without creative effort. Therefore, all technical solutions that can be obtained by those skilled in the art based on the concept of the present invention through logical analysis, reasoning, or limited experimentation on the basis of existing technology should be within the scope of protection defined by the claims.
Claims
1. A remote oversight method characterized by, The method comprises the following steps: According to the construction progress of the building project, a preset unmanned aerial vehicle control scheme is determined; According to the current planned construction progress, a corresponding unmanned aerial vehicle control scheme is determined to control the unmanned aerial vehicle to shoot images related to the building project; The current images shot by the unmanned aerial vehicle are compared with the overlapping and different parts of the design drawings to determine the actual construction progress.
2. The method of claim 1, wherein, The method for comparing the current images shot by the unmanned aerial vehicle with the overlapping and different parts of the design drawings to determine the actual construction progress is as follows: According to the current images and the design drawings, three-dimensional models of the building project are reconstructed respectively to obtain a current three-dimensional model of the building project and a design three-dimensional model; The current three-dimensional model of the building project is scaled and adjusted in angle so that the corner points of the building structure thereof overlap with the design three-dimensional model; The proportion of the volume of the overlapping part of the two three-dimensional models to the volume of the design three-dimensional model is calculated to determine the actual construction progress.
3. The method of claim 1, wherein, The images related to the building project shot by the unmanned aerial vehicle include external images of the building project and internal images of the building project.
4. The method of claim 3, wherein, The method for comparing the current images shot by the unmanned aerial vehicle with the overlapping and different parts of the design drawings to determine the actual construction progress is as follows: The types and quantities of building components in the current internal images shot by the unmanned aerial vehicle are identified and compared with the types and quantities of building components in the design drawings to calculate the internal engineering completion degree; The building project structure, the types and quantities of building components, and the building texture information in the current external images shot by the unmanned aerial vehicle are identified and compared with the design images to calculate the external engineering completion degree; The actual construction progress is calculated by combining the internal engineering completion degree and the external engineering completion degree.
5. The method of claim 4, wherein, The method for calculating the actual construction progress by combining the internal engineering completion degree and the external engineering completion degree is as follows: the internal engineering completion degree and the external engineering completion degree are expressed in the form of percentages, and the average of the two is calculated to obtain the actual construction progress.
6. The method of claim 4, wherein, The identification of the types and quantities of building components adopts a target detection model.
7. The method of claim 4, wherein the step of monitoring comprises the step of: The identification of the building project structure and the building texture information adopts a convolutional neural network. 8. The method of claim 1, wherein, The method further comprises: The actual construction progress is compared with the planned construction progress to determine whether there is a project delay, and if there is a project delay, a delay warning is given.
9. A remote monitoring device, comprising a memory, a processor, and a program stored in the memory, characterized in that, The processor implements the method according to any one of claims 1-8 when executing the program.
10. A storage medium having stored thereon a program, characterized by The program is executed to implement the method according to any one of claims 1-8.