Methods, devices, equipment, and storage media for detecting the construction progress of steel structure buildings.

Abstract

This application discloses a method, apparatus, equipment, and storage medium for detecting the construction progress of steel structure buildings. The method includes: acquiring on-site construction images, a three-dimensional design model, and delivery notes for the target steel structure building; inputting the on-site construction images, the three-dimensional design model, and the delivery notes into a pre-trained steel structure building height detection model to obtain the height of the target steel structure building; and obtaining the construction progress at the installation unit level based on the height of the target steel structure building and the structure of the three-dimensional design model. According to the construction progress detection method for steel structure buildings provided in this application, by utilizing on-site construction images, design models, and signed delivery notes of the target steel structure building, the construction progress at the installation unit level can be automatically identified, effectively assisting project managers and owners in controlling on-site progress, making management decisions, and controlling performance risks.

Description

Technical Field

[0001] This invention relates to the field of intelligent construction technology, and in particular to a method, apparatus, equipment and storage medium for detecting the construction progress of steel structure buildings. Background Technology

[0002] Prefabricated steel structure buildings assemble prefabricated steel structure components on-site, eliminating the need for cast-in-place joints. They offer advantages such as precise design, fast installation, strong seismic performance, light weight, and environmental friendliness.

[0003] However, the current on-site installation progress management of steel structure construction mainly relies on manual height calculation and component assembly progress reporting. However, manual reporting has problems such as low data reliability and delayed reporting time, which may lead to performance risks due to inaccurate on-site installation progress. Summary of the Invention

[0004] This application provides a method, apparatus, equipment, and storage medium for detecting the construction progress of steel structure buildings. To provide a basic understanding of some aspects of the disclosed embodiments, a brief summary is given below. This summary is not intended as a general commentary, nor is it intended to identify key / important components or describe the scope of protection of these embodiments. Its sole purpose is to present some concepts in a simple form as a prelude to the detailed description that follows.

[0005] In a first aspect, embodiments of this application provide a method for detecting the construction progress of a steel structure building, including:

[0006] Obtain on-site construction images, 3D design models, and delivery manifests for the target steel structure building;

[0007] By inputting on-site construction images, 3D design models, and incoming freight bills into a pre-trained steel structure building height detection model, the height of the target steel structure building can be obtained.

[0008] Based on the height of the target steel structure building and the structure of the three-dimensional design model, the construction schedule of the installation unit granularity of the target steel structure building is obtained.

[0009] In an optional embodiment, before inputting on-site construction images, a 3D design model, and arrival freight bills into the pre-trained steel structure building height detection model, the method further includes:

[0010] A height detection model for steel structure buildings is trained. The model includes a target detection module, a camera calibration module, and a prior optimization module connected in sequence.

[0011] In an optional embodiment, the target detection module for training the steel structure building height detection model includes:

[0012] Obtain the labeled dataset of on-site construction images;

[0013] The first loss function is constructed based on the actual top and bottom heights of the labeled target steel structure building, as well as the detected top and bottom heights.

[0014] The target detection module is trained based on the on-site construction image dataset, the first loss function, and the preset target detection algorithm to obtain the trained target detection module.

[0015] In an optional embodiment, the camera calibration module for training the steel structure building height detection model includes:

[0016] A camera parameter calibration model is constructed based on a preset algorithm;

[0017] A second loss function is constructed based on the labeled angle between the real camera and the horizontal plane, the angle of view of the real camera, and the calculated angle between the camera and the horizontal plane and the angle of view of the camera.

[0018] The camera parameter calibration model is trained based on the second loss function to obtain the trained camera calibration module.

[0019] In an optional embodiment, the prior optimization module for training the steel structure building height detection model includes:

[0020] A model for calculating the height of steel structure buildings is constructed based on a pre-set algorithm;

[0021] Based on the 3D design model and the incoming freight bill, a Gaussian distribution of the building height that can be built from the completed installation units is fitted to obtain the prior height of the target steel structure building.

[0022] Construct a third loss function based on the prior height;

[0023] The building height calculation model is trained based on the third loss function to obtain the trained prior optimization module.

[0024] In an optional embodiment, on-site construction images, a 3D design model, and an arrival freight bill are input into a pre-trained steel structure building height detection model to obtain the height of the target steel structure building, including:

[0025] Input the on-site construction images into the target detection module to obtain the top and bottom edge heights of the detected steel structure building;

[0026] Input the bottom edge height into the camera calibration module to obtain the calculated camera parameters;

[0027] By inputting the camera parameters, top edge height, 3D design model, and inbound freight bill into the prior optimization module, the optimized height of the target steel structure building is obtained.

[0028] In an optional embodiment, after obtaining the construction progress of the target steel structure building installation unit granularity, the method further includes:

[0029] The construction progress of the target steel structure building installation unit is dynamically displayed in the 3D design model.

[0030] Secondly, embodiments of this application provide a device for detecting the construction progress of a steel structure building, comprising:

[0031] The acquisition module is used to acquire on-site construction images, 3D design models, and delivery manifests for the target steel structure building.

[0032] The detection module is used to input on-site construction images, 3D design models, and incoming freight bills into a pre-trained steel structure building height detection model to obtain the height of the target steel structure building.

[0033] The analysis module is used to obtain the construction progress of the target steel structure building at the level of installation units, based on the height of the target steel structure building and the structure of the three-dimensional design model.

[0034] Thirdly, embodiments of this application provide an electronic device, including a processor and a memory storing program instructions. The processor is configured to execute the steel structure building construction progress detection method provided in the above embodiments when executing the program instructions.

[0035] Fourthly, embodiments of this application provide a computer-readable medium having computer-readable instructions stored thereon, which are executed by a processor to implement a method for detecting the construction progress of a steel structure building provided in the above embodiments.

[0036] The technical solutions provided in this application embodiment may include the following beneficial effects:

[0037] According to the construction progress detection method for steel structure buildings provided in the embodiments of this application, the construction progress of steel structure buildings at the installation unit level is automatically identified by utilizing on-site construction images, three-dimensional design models and on-site acceptance data of prefabricated steel components. This method can make reasonable and full use of existing information, effectively and accurately identify the construction progress, and assist project managers and owners in controlling on-site progress, making management decisions and controlling performance risks.

[0038] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and are not intended to limit the invention. Attached Figure Description

[0039] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0040] Figure 1 This is a flowchart illustrating a method for detecting the construction progress of a steel structure building according to an exemplary embodiment;

[0041] Figure 2 This is a schematic diagram illustrating a height detection model for a steel structure building according to an exemplary embodiment;

[0042] Figure 3 This is a schematic diagram illustrating a height detection device for a steel structure building according to an exemplary embodiment;

[0043] Figure 4 This is a structural schematic diagram of a steel structure building height detection device according to an exemplary embodiment;

[0044] Figure 5 This is a schematic diagram of the structure of an electronic device according to an exemplary embodiment;

[0045] Figure 6 This is a schematic diagram illustrating a computer storage medium according to an exemplary embodiment. Detailed Implementation

[0046] The following description and accompanying drawings fully illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

[0047] It should be understood that the described embodiments are merely some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without inventive effort are within the scope of protection of the present invention.

[0048] In the following description, when referring to the accompanying drawings, the same numbers in different drawings denote the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of systems and methods consistent with some aspects of the invention as detailed in the appended claims.

[0049] Currently, some software developers are creating progress management software and progress calculation tools for construction site management, which can effectively improve the efficiency and real-time performance of progress calculations. Among these, height calculation primarily uses ground reference points to calculate the relative height of the building, or uses laser rangefinders to measure distance and calculate height. The former does not consider factors such as shooting focal length and perspective, relying solely on reference points for conversion, resulting in lower accuracy. The latter requires the purchase of specialized equipment, involves large amounts of measurement data, and is relatively complex to operate. Furthermore, neither of these methods considers the intricate design and prefabrication characteristics of prefabricated steel structure buildings, only calculating building height and lacking organic integration with component data, resulting in a limited perspective.

[0050] Based on this, the embodiments of this application provide a method for detecting the construction progress of steel structure buildings. By utilizing on-site construction images, three-dimensional design models, and on-site acceptance data of prefabricated steel components of the target steel structure building, the construction progress of the steel structure building at the installation unit level can be automatically identified. This method can make reasonable and full use of existing information, effectively and accurately identify the construction progress, and assist project managers and owners in controlling on-site progress, making management decisions, and controlling performance risks.

[0051] The method for detecting the height of steel structure buildings provided in this application will be described in detail below with reference to the accompanying drawings. See also... Figure 1 The method specifically includes the following steps.

[0052] S101 acquires on-site construction images, 3D design models, and delivery manifests for the target steel structure building.

[0053] In one implementation, images of the construction site are captured by a camera to obtain on-site construction images of the target steel structure building, which include the complete target steel structure building. To accelerate image processing, the construction images can undergo preprocessing such as size normalization, pixel adjustment, and background filtering. For example, irrelevant areas such as the background and ground can be fused and identified from construction images of the same scene taken at different times, and the irrelevant areas can be covered by pixel assignment to reduce interference.

[0054] Furthermore, it also includes acquiring a pre-built 3D design model corresponding to the target steel structure building. The 3D design model contains the target building structure and its components, and the components include component models and dimensions. It also includes acquiring the arrival manifests for the prefabricated target steel structure components. The manifests describe the component models and arrival times of each complete set of installation units shipped.

[0055] S102 inputs on-site construction images, 3D design models, and incoming freight bills into a pre-trained steel structure building height detection model to obtain the height of the target steel structure building.

[0056] In one exemplary embodiment, before performing step S102, the method further includes: training a steel structure building height detection model, which is a deep neural network built based on the RCNN algorithm, and the model structure is as follows. Figure 2 As shown, it includes a target detection module, a camera calibration module, and a priori optimization module connected in sequence.

[0057] In one embodiment, the target detection module is used to detect the bounding box of the steel structure building in the input on-site construction image, and to obtain the top and bottom heights of the steel structure building based on the detected bounding box.

[0058] Specifically, an object detection module can be trained. First, an annotated dataset of on-site construction images is obtained, including multiple images from different time periods and locations. The top and bottom edges of the steel structures in these images are then annotated, resulting in the annotated on-site construction image dataset. The top edge height is the distance from the top edge of the building in the image to the bottom edge of the image, and the bottom edge height is the distance from the bottom edge of the building in the image to the bottom edge of the image. Based on the actual top and bottom edges of the annotated target steel structure, as well as the detected top and bottom edges, a first loss function is constructed, as shown below:

[0059]

[0060] in, This represents the first loss function constructed, where N is the number of network channels. Let be the actual top edge height corresponding to the i-th channel. The height of the detected top edge corresponding to the i-th channel. Let be the actual bottom edge height corresponding to the i-th channel. The height of the bottom edge detected for the i-th channel.

[0061] Furthermore, the target detection module is trained based on the on-site construction image dataset, the first loss function, and the preset target detection algorithm to obtain the trained target detection module. For example, the RCNN target detection algorithm is used to identify buildings in the on-site construction images and output the corresponding top and bottom edge heights of the buildings.

[0062] After obtaining the trained object detection module, a camera calibration module can be cascaded after the RCNN network. For example, a camera parameter calibration model can be built using a PointNet network. Camera parameters are estimated, including the camera focal length *f*, the angle θ between the camera and the horizontal plane, and the camera's field of view angle *h*. θ The position of the horizontal plane at the camera's height in the image, v0; the position of the optical center in the image, v. c and the height h of the cameracam .

[0063] In one possible implementation, a second loss function is constructed based on the labeled angle between the real camera and the horizontal plane, the angle of view of the real camera, and the calculated angle between the camera and the horizontal plane and the angle of view of the camera. The constructed second loss function is shown in the following formula:

[0064]

[0065] in, The second loss function is constructed, where N is the number of network channels, and θ i Let be the angle between the real camera in the i-th network channel and the horizontal plane. Let be the angle between the camera and the horizontal plane calculated for the i-th channel. Let be the angle of the actual camera field of view of the i-th channel. Let be the angle of view of the camera for the detection of the i-th channel.

[0066] Calculate the angle θ between the camera and the horizontal plane, and the angle h of the camera's field of view. θ Then, the height h of the camera can be estimated based on the bottom edge height output by the target detection module. cam The camera's focal length f, the position of the horizontal plane at the camera's height v0 in the image, and the position of the optical center v in the image. c .

[0067]

[0068]

[0069] v c =ftanθ+v O

[0070]

[0071] Where λ is the image pixel height and x is the mid-axis coordinate of the target steel structure building.

[0072] The camera parameter calibration model is trained based on the second loss function to obtain the trained camera calibration module, which can calculate the camera parameters.

[0073] Furthermore, a prior optimization module can be cascaded after the camera calibration module, for example, by constructing a prior optimization module using a PointNet network. The prior optimization module outputs the optimized steel structure building height. This includes: constructing a steel structure building height calculation model; fitting a Gaussian distribution of the building height that can be assembled from the completed installation units based on the 3D design model and the on-site freight manifest to obtain the prior height of the target steel structure building; constructing a third loss function based on the prior height; and training the building height calculation model based on the third loss function to obtain the trained prior optimization module.

[0074] In one exemplary embodiment, the height of the target steel structure building can be calculated based on camera parameters and the top edge height output by the target detection module:

[0075]

[0076] Furthermore, the three-dimensional design model of the building and the data of the incoming freight bill are obtained. Based on historical construction data, a Gaussian distribution of the building height that can be built from the completed installation units is fitted, which is used as the prior height of the target steel structure building, and a third loss function is constructed.

[0077] Among them, the building height that can be erected by the units that have been installed on site meets the distribution requirements. The third loss function can then be defined as:

[0078]

[0079] Where μ represents the expected value, σ 2 It represents the standard deviation.

[0080] The prior optimization module is trained using the constructed third loss function to ensure that the height of the target steel structure building calculated by it satisfies the prior condition of a Gaussian distribution, resulting in more accurate calculation results.

[0081] In an alternative implementation, the height detection model of a multi-layered cascaded steel structure building can be optimized as a whole, and the loss function of the overall network is:

[0082]

[0083] Where M is the number of network layers, and α1, α2, and α3 are user-defined parameters.

[0084] By training the target detection module, camera calibration module, and prior optimization module of the steel structure building height detection model, and optimizing the overall model, a well-trained steel structure building height detection model can be obtained.

[0085] Furthermore, the on-site construction images, 3D design model, and incoming freight bills are input into the trained steel structure building height detection model to obtain the height of the target steel structure building. This includes: first, inputting the on-site construction images into the target detection module to obtain the bounding box of the detected steel structure building area; and then obtaining the top and bottom heights of the building based on the bounding box. Next, the bottom height output by the target detection module is input into the camera calibration module to obtain the calculated camera parameters, including the camera focal length f, the angle θ between the camera and the horizontal plane, and the camera field of view angle h. θ The position of the horizontal plane at the camera's height in the image, v0; the position of the optical center in the image, v. c and the height h of the camera cam Then, the camera parameters, the top edge height output by the target detection module, the 3D design model, and the incoming freight bill are input into the prior optimization module to obtain the optimized height of the target steel structure building.

[0086] According to this step, the height of the steel structure building is automatically identified by using on-site construction images, three-dimensional design models, and on-site acceptance data of prefabricated steel components.

[0087] S103 obtains the construction schedule of the target steel structure building installation unit granularity based on the height of the target steel structure building and the structure of the three-dimensional design model.

[0088] In one exemplary embodiment, after detecting the height of the target steel structure building, the obtained height is compared with the three-dimensional design model to see which installation unit corresponds to the detected height, thereby determining the construction progress of the installation unit granularity.

[0089] Furthermore, the construction progress of the target steel structure building installation units is dynamically displayed in the 3D design model. For example, the installation units of the target steel structure building are divided into three categories: completed, arrived on site, and not yet arrived. Different levels of transparency are assigned to the installation units at different progress stages in the 3D model for differentiation. For example, the transparency of completed installation units is displayed at 100%, the transparency of arrived installation units is displayed at 50%, and the transparency of not yet arrived installation units is displayed at 0%. Those skilled in the art can set different transparency display methods or use different colors for display; this application embodiment does not impose specific limitations.

[0090] Optionally, after obtaining the construction progress of each installation unit, the solution also includes acquiring the construction progress of each installation unit and automatically generating a construction progress table for each installation unit, displaying the construction progress of each installation unit in the table. This solution solves the problems of low reliability and delayed reporting of manually entered data. It can intuitively display rich component-level data.

[0091] In an exemplary scenario, the implementation equipment for the steel structure building height detection method provided in this application embodiment is as follows: Figure 3 The system includes: cameras, a client, a computing engine, a storage server, and a large display screen. Cameras installed at the construction site capture on-site construction images of the target steel structure building. These images are sent to the client, which receives the on-site construction images, a 3D design model of the target steel structure, and delivery receipts for prefabricated steel components. The client then sends a calculation request to the computing engine, which automatically identifies the installation progress of the target building based on a pre-trained steel structure height detection model and stores the results on the server. The large display screen reads the data from the storage server to show the progress. Different levels of transparency can be assigned to the 3D model for differentiation. For example, completed installation units can be displayed at 100% transparency, units already on site at 50% transparency, and units not yet on site at 0% transparency.

[0092] According to the construction progress detection method for steel structure buildings provided in the embodiments of this application, the construction progress of the steel structure building at the installation unit level is automatically identified by utilizing on-site construction images, three-dimensional design models, and on-site acceptance data of prefabricated steel components. The progress is then displayed intuitively through a three-dimensional model. This method can make reasonable and full use of existing information, effectively and accurately identify the construction progress, and assist project managers and owners in controlling on-site progress, making management decisions, and controlling performance risks.

[0093] This application also provides a steel structure building height detection device, which is used to perform the steel structure building height detection method described in the above embodiments, such as... Figure 4 As shown, the device includes:

[0094] The acquisition module 401 is used to acquire on-site construction images, three-dimensional design models, and on-site freight manifests of the target steel structure building;

[0095] The detection module 402 is used to input on-site construction images, three-dimensional design models and incoming freight bills into a pre-trained steel structure building height detection model to obtain the height of the target steel structure building.

[0096] Analysis module 403 is used to obtain the construction progress of the installation unit granularity of the target steel structure building based on the height of the target steel structure building and the structure of the three-dimensional design model.

[0097] It also includes a model training module for training a steel structure building height detection model. The steel structure building height detection model includes a target detection module, a camera calibration module, and a prior optimization module connected in sequence.

[0098] It also includes a dynamic display module, which is used to dynamically display the construction progress of the target steel structure building installation unit granularity in the 3D design model.

[0099] It should be noted that the steel structure building height detection device provided in the above embodiments is only illustrated by the division of the above functional modules when performing the steel structure building height detection method. In practical applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the steel structure building height detection device and the steel structure building height detection method embodiments provided in the above embodiments belong to the same concept, and the implementation process is detailed in the method embodiments, which will not be repeated here.

[0100] This application also provides an electronic device corresponding to the steel structure building height detection method provided in the foregoing embodiments, to execute the steel structure building height detection method described above.

[0101] Please refer to Figure 5 This illustrates a schematic diagram of an electronic device provided by some embodiments of this application. For example... Figure 5 As shown, the electronic device includes: a processor 500, a memory 501, a bus 502, and a communication interface 503. The processor 500, the communication interface 503, and the memory 501 are connected via the bus 502. The memory 501 stores a computer program that can run on the processor 500. When the processor 500 runs the computer program, it executes the steel structure building height detection method provided in any of the foregoing embodiments of this application.

[0102] The memory 501 may include high-speed random access memory (RAM) or non-volatile memory, such as at least one disk storage device. Communication between this system network element and at least one other network element is achieved through at least one communication interface 503 (which can be wired or wireless), such as the Internet, wide area network, local area network, or metropolitan area network.

[0103] Bus 502 can be an ISA bus, PCI bus, or EISA bus, etc. Buses can be divided into address buses, data buses, control buses, etc. Memory 501 is used to store programs. After receiving execution instructions, processor 500 executes the program. The steel structure building height detection method disclosed in any of the aforementioned embodiments of this application can be applied to processor 500, or implemented by processor 500.

[0104] The processor 500 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of the processor 500 or by instructions in software form. The processor 500 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor may be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this application can be directly embodied in the execution of a hardware decoding processor, or executed by a combination of hardware and software modules in the decoding processor. The software modules may reside in random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, registers, or other mature storage media in the art. The storage medium is located in memory 501. The processor 500 reads the information in memory 501 and, in conjunction with its hardware, completes the steps of the above method.

[0105] The electronic device provided in this application embodiment and the steel structure building height detection method provided in this application embodiment are based on the same inventive concept and have the same beneficial effects as the methods they adopt, operate or implement.

[0106] This application also provides a computer-readable storage medium corresponding to the steel structure building height detection method provided in the foregoing embodiments. Please refer to... Figure 6 The computer-readable storage medium shown is an optical disc 600, on which a computer program (i.e., a program product) is stored. When the computer program is run by a processor, it executes the steel structure building height detection method provided in any of the foregoing embodiments.

[0107] It should be noted that examples of computer-readable storage media may also include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other optical and magnetic storage media, which will not be elaborated here.

[0108] The computer-readable storage medium provided in the above embodiments of this application and the steel structure building height detection method provided in the embodiments of this application are based on the same inventive concept and have the same beneficial effects as the methods adopted, run or implemented by the application programs stored therein.

[0109] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0110] The above embodiments merely illustrate several implementation methods of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of this patent should be determined by the appended claims.

Claims

1. A method for detecting the construction progress of a steel structure building, characterized in that, include: Obtain on-site construction images, 3D design models, and delivery manifests for the target steel structure building; A steel structure building height detection model is trained, which includes a target detection module, a camera calibration module, and a prior optimization module connected in sequence. The process involves inputting the on-site construction images, 3D design model, and incoming freight bill into a pre-trained steel structure building height detection model to obtain the height of the target steel structure building. This includes: inputting the on-site construction images into the target detection module to obtain the top and bottom edge heights of the detected steel structure building; inputting the bottom edge height into the camera calibration module to obtain calculated camera parameters; and inputting the camera parameters, top edge height, 3D design model, and incoming freight bill into the prior optimization module to obtain the optimized height of the target steel structure building. Based on the height of the target steel structure building and the structure of the three-dimensional design model, the construction progress of the installation unit granularity of the target steel structure building is obtained.

2. The method according to claim 1, characterized in that, The target detection module for training the steel structure building height detection model includes: Obtain the labeled dataset of on-site construction images; The first loss function is constructed based on the actual top and bottom heights of the labeled target steel structure building, as well as the detected top and bottom heights. The target detection module is trained based on the on-site construction image dataset, the first loss function, and the preset target detection algorithm to obtain the trained target detection module.

3. The method according to claim 1, characterized in that, The camera calibration module for training the steel structure building height detection model includes: A camera parameter calibration model is constructed based on a preset algorithm; A second loss function is constructed based on the labeled angle between the real camera and the horizontal plane, the angle of view of the real camera, and the calculated angle between the camera and the horizontal plane and the angle of view of the camera. The camera parameter calibration model is trained according to the second loss function to obtain the trained camera calibration module.

4. The method according to claim 1, characterized in that, The prior optimization module for training the steel structure building height detection model includes: A model for calculating the height of steel structure buildings is constructed based on a pre-set algorithm; Based on the three-dimensional design model and the incoming freight bill, a Gaussian distribution of the building height that can be built from the completed installation units is fitted, and the prior height of the target steel structure building is obtained. Construct a third loss function based on the prior height; The building height calculation model is trained based on the third loss function to obtain the trained prior optimization module.

5. The method according to claim 1, characterized in that, After obtaining the construction progress of the target steel structure building installation unit particle size, the process also includes: The construction progress of the target steel structure building installation unit granularity is dynamically displayed in the three-dimensional design model.

6. A device for detecting the construction progress of a steel structure building, characterized in that, include: The acquisition module is used to acquire on-site construction images, 3D design models, and delivery manifests for the target steel structure building. The training module is used to train the steel structure building height detection model, which includes a target detection module, a camera calibration module, and a prior optimization module connected in sequence. The detection module is used to input the on-site construction images, 3D design model, and incoming freight bill into a pre-trained steel structure building height detection model to obtain the height of the target steel structure building; including: inputting the on-site construction images into the target detection module to obtain the top and bottom edge heights of the detected steel structure building; inputting the bottom edge height into the camera calibration module to obtain calculated camera parameters; and inputting the camera parameters, top edge height, 3D design model, and incoming freight bill into the prior optimization module to obtain the optimized height of the target steel structure building. The analysis module is used to obtain the construction progress of the installation unit granularity of the target steel structure building based on the height of the target steel structure building and the structure of the three-dimensional design model.

7. An electronic device, characterized in that, The device includes a processor and a memory storing program instructions, the processor being configured to, when executing the program instructions, perform the method for detecting the construction progress of a steel structure building as described in any one of claims 1 to 5.

8. A computer-readable medium, characterized in that, It stores computer-readable instructions, which are executed by a processor to implement a method for detecting the construction progress of a steel structure building as described in any one of claims 1 to 5.

Images