A component hoisting pose control method, device, equipment, medium and product

Abstract

Embodiments of the present application provide a kind of component hoisting pose control method, device, equipment, medium and product, the method comprises: obtaining the optimal motion pose of the component to be tracked from initial position hoisting to installation position process;During the hoisting process of the component to be tracked, the current motion position of the component to be tracked is acquired by the total station and prism arranged in advance, while the video stream data of the component to be tracked is acquired by the video acquisition device arranged in advance;According to the video stream data of the component to be tracked, the current spatial attitude of the component to be tracked at the current motion position is determined;According to optimal motion position, optimal spatial attitude, current motion position and current spatial attitude, adjustment suggestion is proposed to the component to be tracked.The method is used, by erecting a total station and a video acquisition device, real-time monitoring component hoisting pose, and giving component motion suggestion, solve the problem that component pose monitoring and control cannot be realized in the scene of small site and poor visibility condition.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of building construction, and in particular to a component hoisting pose control method, device, equipment, medium and product. BACKGROUND

[0002] In the hoisting operation of building construction, real-time and concrete grasping of the movement position and spatial pose of the component in the process of starting hoisting, moving, and finally landing is very important to ensure the accuracy and safety of the hoisting operation. In the prior art, multiple total stations are usually erected to observe the movement position and spatial pose of the component, but this method is not suitable for scenes with small sites and poor visibility. For example, due to the limitation of the position of the tower crane / hoist, the hoisting driver, the on-site commander, and the project manager may not be able to obtain the movement position and spatial pose of the component in motion in real time. SUMMARY

[0003] The component hoisting pose control method, device, equipment, medium and product provided by the embodiments of the present application can realize monitoring and control of the component pose in a scene with a small site and poor visibility.

[0004] In a first aspect, the present embodiment provides a component hoisting pose control method, which comprises:

[0005] obtaining an optimal movement pose of a to-be-tracked component in the process of hoisting from an initial position to an installation position, the optimal movement pose comprising an optimal movement position and an optimal spatial pose at the optimal movement position;

[0006] In the hoisting process of the to-be-tracked component, the current movement position of the to-be-tracked component is collected by a total station and a prism arranged in advance in a relative coordinate system of an engineering environment, and video stream data of the to-be-tracked component is collected by a video collection device arranged in advance;

[0007] determining a current spatial pose of the to-be-tracked component at the current movement position according to the video stream data of the to-be-tracked component;

[0008] proposing an adjustment suggestion for the to-be-tracked component according to the optimal movement position, the optimal spatial pose, the current movement position, and the current spatial pose.

[0009] In a second aspect, the present embodiment provides a component hoisting pose control device, which comprises:

[0010] an optimal pose determination module configured to obtain an optimal movement pose of a to-be-tracked component in the process of hoisting from an initial position to an installation position, the optimal movement pose comprising an optimal movement position and an optimal spatial pose at the optimal movement position;

[0011] The information acquisition module is used to acquire the current movement position of the component to be tracked by a total station and prism pre-arranged in the relative coordinate system of the engineering environment during the hoisting process of the component to be tracked, and to acquire video stream data of the component to be tracked by a pre-arranged video acquisition device.

[0012] The current attitude determination module is used to determine the current spatial attitude of the component to be tracked at the current motion position based on the video stream data of the component to be tracked.

[0013] The component adjustment module is used to propose adjustment suggestions for the component to be tracked based on the optimal motion position, the optimal spatial attitude, the current motion position, and the current spatial attitude.

[0014] Thirdly, this embodiment provides an electronic device, including:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the component hoisting posture control method according to any embodiment of the present invention.

[0018] Fourthly, this embodiment provides a computer-readable storage medium storing computer instructions, which are used to cause a processor to execute and implement the component hoisting posture control method described in any embodiment of the present invention.

[0019] Fifthly, embodiments of the present invention also provide a computer program product, the computer program product including a computer program, which, when executed by a processor, implements the component hoisting posture control method as described in any embodiment of the present invention.

[0020] This invention provides a method, apparatus, device, medium, and product for controlling the hoisting posture of a component. The method includes: acquiring the optimal motion posture of the component to be tracked during hoisting from an initial position to an installation position, wherein the optimal motion posture includes an optimal motion position and an optimal spatial posture at the optimal motion position; during the hoisting process of the component to be tracked, simultaneously acquiring the current motion position of the component to be tracked by a total station and a prism pre-arranged in the relative coordinate system of the engineering environment, and acquiring video stream data of the component to be tracked by a pre-arranged video acquisition device; determining the current spatial posture of the component to be tracked at the current motion position based on the video stream data of the component to be tracked; and proposing adjustment suggestions for the component to be tracked based on the optimal motion position, the optimal spatial posture, the current motion position, and the current spatial posture. Unlike existing technologies that rely on multiple total stations to observe component posture, which are unsuitable for scenarios with limited space and poor visibility, the above solution uses a single total station and a video acquisition device. The total station captures the component's real-time position, while the video acquisition device captures video stream data. Processing this video stream data allows for the identification of the component's real-time spatial posture. Based on this, the component's position and spatial posture can be observed in real time, and adjustment suggestions can be made based on the optimal motion posture. This achieves real-time monitoring of the component's position and spatial posture during hoisting and provides motion suggestions, solving the problem of not being able to monitor and control component posture in scenarios with limited space and poor visibility.

[0021] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0022] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0023] Figure 1 This is a flowchart illustrating a method for controlling the lifting posture of a component according to Embodiment 1 of the present invention.

[0024] Figure 2 This is a flowchart illustrating another method for controlling the hoisting posture of a component according to Embodiment 2 of the present invention.

[0025] Figure 3This is an example diagram of the human-machine interface in the execution of a component hoisting posture control method provided in Embodiment 2 of the present invention;

[0026] Figure 4 This is a structural schematic diagram of a component hoisting posture control device provided in Embodiment 3 of the present invention;

[0027] Figure 5 This is a schematic diagram of the structure of an electronic device provided in Embodiment 4 of the present invention. Detailed Implementation

[0028] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0030] Example 1

[0031] Figure 1 This is a flowchart illustrating a method for controlling the hoisting posture of a component according to Embodiment 1 of the present invention. This method is applicable to situations where the hoisting posture of a component is monitored and controlled during the hoisting process. This method can be executed by a control device for the hoisting posture of the component. The control device for the hoisting posture of the component can be implemented in hardware and / or software and is generally integrated into an electronic device.

[0032] like Figure 1 As shown, the method for controlling the hoisting posture of a component provided in this embodiment can specifically include the following steps:

[0033] S101. Obtain the optimal motion pose of the component to be tracked during the process of hoisting it from the initial position to the installation position.

[0034] In this embodiment, the optimal motion pose includes the optimal motion position and the optimal spatial pose at the optimal motion position. The component to be tracked can be specifically understood as a component to be hoisted and installed on the construction site. The initial position can be specifically understood as the position of the component before hoisting, and the installation position can be specifically understood as the position where the component to be tracked is to be installed. To ensure that the component to be tracked can be safely and accurately hoisted from the initial position to the installation position, the optimal movement path of the component during the entire hoisting process can be simulated in advance. The optimal movement path can be considered as composed of multiple optimal motion positions in sequence, and the optimal spatial pose at each motion position can also be simulated. The optimal motion position represents which positions the component to be tracked should be hoisted to during the hoisting process; for example, the optimal motion position can be represented using three-dimensional coordinates. The optimal spatial pose represents the spatial pose that the component to be tracked should maintain at each optimal motion position during the hoisting process; for example, the optimal spatial pose can be represented by the rotation angle relative to the three axes in the coordinate system. The optimal motion position and the optimal spatial pose at the optimal motion position constitute the optimal motion pose.

[0035] For example, modeling and motion simulation software can be used to simulate the optimal motion pose of the component to be tracked during the process of hoisting it from its initial position to its installation position. Using pre-set modeling and motion simulation software, the optimal motion positions and simulated spatial poses of the component to be tracked during the process of hoisting it from its initial position to its installation position are simulated. Scene rendering is performed on each simulated spatial pose to obtain keyframe images corresponding to the component to be tracked at each optimal motion position. Based on each keyframe image and a pre-trained component recognition model, the optimal spatial pose of the component to be tracked at the optimal motion position is obtained.

[0036] Understandably, this step can be considered a preliminary step performed before the hoisting of the component to be tracked. It determines the optimal motion path of the component from its initial position to its installation position, as well as the spatial attitude corresponding to each position along the path, providing a basis for subsequent adjustments to the attitude during the hoisting process. In determining the optimal spatial attitude of the component during the entire hoisting process, not only safety factors such as avoiding collisions with obstacles were considered, but also factors such as ensuring the convenience and cost-effectiveness of the hoisting process.

[0037] In this embodiment, before the hoisting operation begins, all equipment is set up. The system can input the component number of the component to be tracked or scan the QR code on the component via a terminal. The system will then automatically import the AI ​​training data of the component, i.e., the optimal motion pose of the component during the hoisting process from its initial position to its installation position. For example, the terminal can be augmented reality (AR) glasses, a tablet computer, a mobile phone, etc.

[0038] S102. During the hoisting process of the component to be tracked, the current movement position of the component to be tracked is collected by a total station and prism pre-arranged in the relative coordinate system of the engineering environment, while video stream data of the component to be tracked is collected by a pre-arranged video acquisition device.

[0039] It should be noted that during the hoisting operation of the component to be tracked, the real-time position and status of the component's movement, including the start of hoisting, its movement during the process, and its final placement, need to be monitored in a real-time and visual manner. To meet this requirement, a total station (or automated surveying robot) with automatic tracking and measurement capabilities and a video acquisition device can be set up in the known coordinate system of the engineering site, and their spatial coordinate positions relative to the coordinate system of the engineering environment should be confirmed. A prism should be installed on the component to be tracked, ensuring that the total station with automatic tracking and measurement capabilities and the prism maintain a clear line of sight without obstruction. For example, a high-definition camera can be used as the video acquisition device, and a 360° prism can be used. The specific location of the video acquisition device and the total station is not required, but they must maintain a clear line of sight with the component to be tracked. Based on the above setup, two data sources are obtained through the total station with automatic tracking and measurement capabilities and the video acquisition device.

[0040] The total station must have automatic tracking measurement capabilities, or an automated measurement robot can be used. A prism is mounted on the component to be tracked. By tracking the prism on the component, the total station can obtain the real-time 3D coordinates of the component during hoisting, and this real-time 3D coordinate is used as the current position. Understandably, once the 3D coordinates of the prism mounting location are known, the overall 3D coordinates of the component can be calculated based on its external dimensions and spatial orientation. For example, assuming the total station acquires the coordinates of a position at the lower left corner of the component, the overall spatial coordinates of the component can be determined based on its external dimensions and spatial orientation. Video acquisition equipment can collect real-time video stream data of the hoisting process. By processing this real-time video stream data, the component to be tracked can be identified and located, and its real-time spatial orientation can be determined.

[0041] Based on the above description, it can be seen that the component to be tracked has two data sources during the hoisting process: the real-time current position of the component can be provided by a total station and a prism, and real-time video stream data of the component can be provided by a video acquisition device. This data can be sent to the executing entity via a communication module.

[0042] S103. Based on the video stream data of the component to be tracked, determine the current spatial pose of the component at the current motion position.

[0043] In this embodiment, video stream data of the component to be tracked during the hoisting process is acquired in real time by a video acquisition device. The video stream data is further processed; since it consists of multiple frames, the current frame image corresponding to the component at the current movement position is extracted. The component to be tracked is identified and marked in the current frame image, thus using its spatial pose as the current spatial pose at the current movement position. Because the component to be tracked is hoisted from its initial position to the installation position, its current movement position is continuously updated during the hoisting process, and each current movement position has a corresponding current spatial pose.

[0044] For example, in this embodiment, a pre-trained component recognition model can be used to identify and label the components to be tracked in the video stream data. Specifically, the component recognition model can be understood as a model used to identify and label components from an image. After extracting the current frame image at the current motion position from the video stream data, the current frame image and the original component image of the component to be tracked can be used as input data and input into the pre-trained component recognition model. This allows the component to be labeled in the current frame image, and the spatial pose of the labeled component to be tracked is determined as the current spatial pose of the component to be tracked at the current position.

[0045] S104. Based on the optimal motion position, optimal spatial attitude, current motion position, and current spatial attitude, propose adjustment suggestions for the component to be tracked.

[0046] In this embodiment, to achieve pose control of the component to be tracked, adjustments can be made to both its position and orientation. Specifically, the current motion position is compared with the optimal motion position. If the difference between the two does not exceed a set error range, no movement operation suggestion is needed for the component to be tracked; if the difference exceeds the set error range, a movement operation suggestion is needed until the difference is less than the set error range. Similarly, the current spatial state is compared with the optimal spatial state. If the difference between the two does not exceed a set error range, no rotation operation suggestion is needed for the component to be tracked; if the difference exceeds the set error range, a rotation operation suggestion is needed until the difference is less than the set error range.

[0047] It should be noted that the hoisting of the component to be tracked from its initial position to its installation position is a process. Therefore, during the entire hoisting process, the current motion position and current spatial attitude will be continuously acquired. The current motion position will be compared with the corresponding optimal motion position, and the current spatial attitude will be compared with the corresponding optimal spatial attitude to determine whether the position and spatial attitude of the component to be tracked need to be adjusted.

[0048] Unlike existing technologies that rely on multiple total stations to observe component posture, which are unsuitable for scenarios with limited space and poor visibility, the above solution uses a single total station and a video acquisition device. The total station captures the component's real-time position, while the video acquisition device captures video stream data. Processing this video stream data allows for the identification of the component's real-time spatial posture. Based on this, the component's position and spatial posture can be observed in real time, and adjustment suggestions can be made based on the optimal motion posture. This achieves real-time monitoring of the component's position and spatial posture during hoisting and provides motion suggestions, solving the problem of not being able to monitor and control component posture in scenarios with limited space and poor visibility.

[0049] Example 2

[0050] Figure 2 This is a flowchart illustrating another component hoisting posture control method provided in Embodiment 2 of the present invention. This embodiment is a further optimization of the above embodiment. In this embodiment, the following are further optimized: "obtaining the optimal motion posture of the component to be tracked during the hoisting process from the initial position to the installation position", "determining the current spatial posture of the component to be tracked at the current motion position based on the video stream data of the component to be tracked", and "providing adjustment suggestions for the component to be tracked based on the optimal motion position, the optimal spatial posture, the current motion position, and the current spatial posture".

[0051] like Figure 2 As shown in the figure, this embodiment 2 provides a method for controlling the hoisting posture of a component, which specifically includes the following steps:

[0052] S201. Using preset modeling and motion simulation software, based on the relative position of the video acquisition device and the component to be tracked, simulate the optimal motion positions and simulated spatial postures of the component to be tracked during the process of hoisting from the initial position to the installation position.

[0053] In this embodiment, under a fixed coordinate system at the engineering site, the video acquisition device is set up at a certain position. Based on the relative position of the video acquisition device and the component to be tracked, it is equivalent to setting such an effect point during the modeling and motion simulation software simulation. The image that may correspond to the hoisting process of the component to be tracked is simulated through the perspective of this effect point, thereby improving the image recognition accuracy. Preferably, the modeling and motion simulation software is Building Information Modeling (BIM) software.

[0054] Specifically, based on the relative position of the video acquisition device and the component to be tracked, the path motion state of the component to be tracked from the initial position to the installation position is simulated in the modeling and motion simulation software. That is, the optimal motion path of the component to be tracked from the initial position to the installation position is simulated, which determines the optimal motion positions to which the component to be tracked moves during the hoisting process, and determines the simulated spatial posture of the control to be tracked at each optimal motion position.

[0055] S202. Render each simulated spatial posture based on the real environment scene to obtain the keyframe image corresponding to the component to be tracked at each optimal motion position.

[0056] In this embodiment, the modeling and motion simulation software has a realistic scene rendering function. By rendering the simulated spatial posture corresponding to each optimal motion position in a realistic environment, images of the component to be tracked at each optimal motion position throughout the entire hoisting process can be obtained, and these images are recorded as keyframe images corresponding to the component to be tracked. For example, a large number of keyframe images are extracted through realistic scene rendering in BIM software.

[0057] S203. Based on each keyframe image and the pre-trained component recognition model, obtain the optimal spatial pose of the component to be tracked at the optimal motion position.

[0058] In this embodiment, the component recognition model can be specifically understood as a model used to identify and label components from images. The component recognition model can be obtained by training an initial neural network model based on a training sample set. After obtaining keyframe images rendered by modeling and motion simulation software, the pre-trained component recognition model can be used to identify and label the components to be tracked in each keyframe image. Specifically, the keyframe images and the original component images of the components to be tracked can be input into the component recognition model to segment and label the components to be tracked from the keyframe images, and determine the spatial pose of the components to be tracked as the optimal spatial pose of the components.

[0059] As a specific implementation method, the steps of obtaining the optimal spatial pose of the tracked component at each optimal motion position based on each keyframe image and a pre-trained component recognition model can be optimized, including:

[0060] a1) For each optimal motion position, the keyframe image of the component to be tracked at the optimal motion position and the original component image of the component to be tracked are used as input data and input into the pre-trained component recognition model to mark the component to be tracked in the keyframe image.

[0061] In this embodiment, the original image of the component to be tracked refers to the actual image of the component, such as an image of the component manufactured at the factory. Specifically, for each optimal motion position, the keyframe image corresponding to the component at the optimal motion position and the original component image are used as input data and input into the component recognition model. The keyframe image output by the component recognition model can then annotate the component to be tracked. The component recognition model includes a segmentation algorithm that can achieve pixel-level segmentation and extraction of component edges.

[0062] b1) Determine the spatial pose of the component to be tracked marked in the keyframe image as the optimal spatial pose of the component to be tracked at the optimal motion position.

[0063] For example, spatial attitude can be represented by rotation angles relative to the three coordinate axes in a fixed coordinate system of the engineering site. Specifically, after marking the component to be tracked in the keyframe image, the rotation angles of the component to be tracked relative to the three coordinate axes in the fixed coordinate system can be determined as the optimal spatial attitude of the component to be tracked at the current movement position.

[0064] The above technical solution specifies the steps for determining the optimal spatial pose of the component to be tracked based on the component recognition model, providing a basis for subsequent adjustment of the spatial pose of the component to be tracked.

[0065] S204. During the hoisting process of the component to be tracked, the current movement position of the component to be tracked is collected by a total station and prism pre-arranged in the relative coordinate system of the engineering environment, while video stream data of the component to be tracked is collected by a pre-arranged video acquisition device.

[0066] S205. Extract the current frame image corresponding to the current motion position of the component to be tracked from the video stream data of the component to be tracked.

[0067] In this embodiment, the video stream data of the component to be tracked is composed of multiple frames of images in sequence. The image corresponding to the component to be tracked at the current motion position is extracted from the video stream data and recorded as the current frame image.

[0068] S206. Input the current frame image and the original component image of the component to be tracked as input data into the pre-trained component recognition model, and mark the component to be tracked in the current frame image.

[0069] Specifically, for each current motion position, the current frame image corresponding to the component to be tracked at the current motion position and the original component image are used as input data and fed into the component recognition model. The current frame image output by the component recognition model can then annotate the component to be tracked. The component recognition model includes a segmentation algorithm that can achieve pixel-level segmentation and extraction of component edges. For example, the annotation method can be to identify and highlight or select the component to be tracked during hoisting in the video stream data.

[0070] S207. Determine the spatial pose of the component to be tracked marked in the current frame image as the current spatial pose of the component to be tracked at the current position.

[0071] For example, spatial attitude can be represented by rotation angles relative to the three coordinate axes in a fixed coordinate system of the engineering site. Specifically, after marking the component to be tracked in the current frame image, the rotation angles of the component to be tracked relative to the three coordinate axes in the fixed coordinate system can be determined as the current spatial attitude of the component to be tracked at the current movement position.

[0072] S208. Compare whether the difference between the current motion position and the optimal motion position is within the first set error range. If yes, do not make a movement operation suggestion for the tracking component. If no, make a movement operation suggestion for the tracking component.

[0073] After simulating the optimal movement path and the optimal spatial posture using modeling and motion simulation software, these are compared in real time with the movement position and spatial posture of the component to be tracked, allowing for adjustments to the component. In this embodiment, the first set error range can be set according to actual conditions. The difference between the current movement position and the optimal movement position is taken as the absolute value. If the difference is within the first set error range, the current movement position of the component to be tracked is considered to conform to the planned optimal movement path, and no movement operation suggestion is needed. If the difference exceeds the first set error range, the current movement position of the component to be tracked is considered to not conform to the planned optimal movement path, and a movement operation suggestion is needed to ensure that the difference between the moved movement position and the optimal movement position is within the first set error range. For example, assuming the current movement position is (x, y, z) and the optimal movement position is (x, y, z1), and |z - z1| > the first set error range, the component to be tracked needs to be moved in the z-axis direction so that the coordinate difference after the movement is less than the first set error range.

[0074] S209. Compare whether the difference between the current spatial attitude and the optimal spatial attitude is within the second set error range. If yes, do not suggest a rotation operation for the component to be tracked. If no, suggest a rotation operation for the component to be tracked.

[0075] In this embodiment, the second preset error range can be set according to actual conditions. The absolute value of the difference between the current spatial state and the optimal spatial state is taken. If this difference is within the second preset error range, the current spatial state of the tracked component is considered to conform to the planned optimal spatial posture, and no rotation operation suggestion is needed. If the difference exceeds the second preset error range, the current spatial state of the tracked component is considered to not conform to the planned optimal spatial posture, and a rotation operation suggestion is needed to ensure that the difference between the spatial state of the tracked component and the optimal spatial state is within the second preset error range. For example, suppose a frame of image shows the tracked component as a rectangle, but the image is labeled as a parallelogram, indicating that the component needs to be rotated by a certain angle to reach the correct hoisting position.

[0076] The above technical solution specifies the steps for obtaining the optimal motion pose, determining the current spatial attitude of the component to be tracked, and adjusting the component. Modeling and motion simulation software is used to model and render the pose of the component during the lifting process, obtaining its optimal motion pose. Then, a total station is used to collect the real-time motion position of the component, and video stream data is collected using video acquisition equipment to obtain its real-time spatial attitude. The optimal motion pose is compared with the real-time position and attitude of the component to allow for adjustments. This enables real-time monitoring of the component's position and spatial attitude during the lifting process and provides suggestions for correcting these aspects, improving the accuracy and safety of the lifting process.

[0077] As an optional embodiment of the present invention, based on the above embodiments, this optional embodiment can optimize the training steps of the component recognition model, including:

[0078] a2) Collect a first set number of first images from the completion of component processing to the preparation of hoisting, and a second set number of second images obtained by modeling and motion simulation software based on the simulation rendering of the component in a real environment scene. Record the first images and the second images as sample images.

[0079] In this embodiment, there are no specific limitations on the first and second preset quantities, which can be set according to actual conditions. The first image can be understood as an image of the component collected during the historical hoisting process. The second image can be understood as an image obtained by simulating and rendering the component using modeling and motion simulation software. Both the first and second images can be used as sample images for training the component recognition model. It is understood that the component recognition model training step is a pre-executed step; at the engineering site, the trained component recognition model can be directly used to identify components.

[0080] b2) Label each sample image to obtain a sample training set. The sample training set includes at least one sample training pair. Each sample training pair includes a sample image and the corresponding sample image with labeled components.

[0081] In this embodiment, component annotations are performed on each sample image, and components are identified and highlighted or selected by bounding boxes. A sample image and its corresponding annotated sample image constitute a sample training pair, and a large number of sample training pairs constitute a sample training set.

[0082] c2) Train the initial neural network model based on the sample training set, and use the trained initial neural network model as the component recognition model.

[0083] For example, the initial neural network model can employ a lightweight YOLOv8-Seg algorithm. The initial neural network model is trained using a sample training set. This involves inputting sample images into the initial neural network model to obtain images of the component edges, comparing them with the sample images labeled with the components, calculating a loss function, and adjusting the parameters of the initial neural network model accordingly. This process is repeated until the model can recognize the components to be tracked through extensive training, until the loss function value meets the set conditions. The trained initial neural network model is then used as the component recognition model.

[0084] In this embodiment, based on the component number, the AI ​​training results data of the component, including model weights, evaluation charts, log files and data statistics, can be independently archived, retrieved and managed.

[0085] The above technical solution specifies the training steps of the component recognition model, providing a foundation for the subsequent recognition and annotation of the components to be tracked.

[0086] As an optional embodiment of the present invention, based on the above embodiments, this optional embodiment can further optimize the method by including:

[0087] a3) Collect safety monitoring information of the components to be tracked based on safety monitoring equipment.

[0088] In this embodiment, an IoT-based safety monitoring device is added. This device can be installed on the component to be tracked or on a building at a predetermined distance from the component during hoisting. The predetermined distance can be set according to actual conditions and is not specifically limited here. The installed safety monitoring device collects relevant safety monitoring information about the component to be tracked. For example, the safety monitoring device can be an anemometer or an ultrasonic impact detector. The anemometer can collect the wind speed around the component to be tracked or nearby buildings and record this wind speed as safety monitoring information. The ultrasonic impact detector can collect the distance between the component to be tracked and the building and record this distance as safety monitoring information.

[0089] b3) If the safety monitoring information exceeds the set safety information threshold, a safety warning will be issued.

[0090] In this embodiment, a safety information threshold is set. When the safety monitoring information exceeds the set threshold, a safety warning is issued if a risk is considered to exist during the hoisting of the component to be tracked. The safety information threshold can be set according to actual conditions. For example, if the safety monitoring information is wind speed, hoisting is recommended to stop if the current wind speed exceeds the set safe wind speed threshold. Similarly, if the safety monitoring information is the current distance between the component to be hoisted and surrounding buildings, hoisting is recommended to stop if the current distance exceeds the set safe distance threshold, indicating a risk of collision between the component and the building. A safety warning is also issued if the component is less than 50cm from the building and a collision is possible. For example, the safety warning prompts include, but are not limited to, at least one of text prompts, sound prompts, and indicator light prompts.

[0091] c3) If the safety monitoring information is less than or equal to the set safety information threshold, no safety warning will be issued.

[0092] In this embodiment, if the safety monitoring information is less than or equal to a set safety information threshold, it is considered that there is no risk during the hoisting of the component to be tracked, and no safety warning is issued. If the safety monitoring information is wind speed, then if the current wind speed is less than a set safe wind speed threshold, no safety warning is issued. If the safety monitoring information is the current distance between the component to be hoisted and surrounding buildings, then if the current distance is less than or equal to a set safe distance threshold, there is no risk of collision between the component and the buildings, and no safety warning is issued.

[0093] The above technical solution adds a safety early warning function during the component hoisting process, enabling safety alerts when there are safety risks during component hoisting, thereby improving the safety of the entire hoisting process.

[0094] As an optional embodiment of the present invention, based on the above embodiments, this optional embodiment can further optimize the method by including:

[0095] The component-related information of the component to be tracked is presented on the human-computer interaction interface. The component-related information includes at least one of the following: component parameter information, current frame image of the component to be tracked, current motion position, installation position, current position deviation, or safety warning information. The current position deviation is obtained by subtracting the installation position from the current motion position.

[0096] In this embodiment, during the hoisting process of the component to be tracked, an enhanced display method can be used to display the component-related information of the component in real time on the human-machine interface. For example, the component-related information can be presented on the human-machine interface of the electronic device integrated into this execution entity, such as on the display terminal configured for operators (e.g., tower crane operators) and managers. The display terminal can be various visualization terminals such as AR glasses, tablets, and mobile phones, or it can be an enhanced display system integrating artificial intelligence installed on a high-performance host in the on-site command room (e.g., in the project department's computer room).

[0097] As described above, the engineering project utilizes a digital management system for project management. By inputting the component number, information such as the manufacturer, materials used, and welding precautions can be obtained. Since the component number is pre-entered, the implementing entity can remotely read and obtain relevant parameters of the component to be tracked, such as material and installation information, through the project's digital management platform. This information is recorded as component parameter information and displayed in real-time on the augmented reality display system. Furthermore, the component identification model annotates the current frame image captured in real-time. This allows the current frame image of the annotated component to be tracked to be displayed on the human-computer interaction interface, providing the user with the visual effect of locking the component to be tracked in the captured video stream data using methods such as box selection. In actual working conditions, multiple components may be being hoisted. By inputting the component number, which corresponds to the component diagram, it can be identified which component to observe. Locking the component to be tracked allows staff to focus on it, facilitating better guidance. For example, a green box can be used to mark and lock the component to be tracked, while also displaying its relevant coordinates. If the component presented in the human-computer interaction interface is not the component to be observed, a prompt will be displayed indicating that there is no component to be observed in the current image.

[0098] In this embodiment, the total station acquires the three-dimensional coordinates of the component to be tracked in real time and transmits them to the execution entity via a communication module. The execution entity then uses the received three-dimensional coordinates as the current movement position of the component and displays it on the human-computer interaction interface. Simultaneously, based on the component number, the endpoint coordinates (i.e., the installation position) of the component to be tracked can be read from the modeling and motion simulation software and displayed on the human-computer interaction interface. The current position deviation can also be obtained by subtracting the installation position from the current movement position and displayed on the human-computer interaction interface. For example, high-definition video streams installed at fixed points and real-time tracking and measurement data from an intelligent total station equipped with an automatic measurement robot are fused in the system, and dynamically highlighted outlines and measurement data are rendered in real time on various display terminals such as AR glasses.

[0099] In this embodiment, safety warning information can also be presented on the human-computer interaction interface. For example, if the current wind speed is too high, a warning message such as "Wind speed too high, hoisting recommended" can be generated; if the current distance is too close, a warning message such as "Distance too close, avoid collision" can be generated. Based on these safety warning messages, safety reminders can be displayed on the human-computer interaction interface. If there is no safety warning, this part of the content on the human-computer interaction interface will be empty.

[0100] Based on the above description, the video stream data acquired by the video acquisition equipment is displayed on the human-machine interface not only as the video stream data but also as locked and labeled components to be tracked. Furthermore, component parameter information, real-time movement position, final installation position, current distance from the endpoint, and safety warning messages are added. This enhanced display information improves the visual effect, enhances the user's visual experience, and increases the readability of the human-machine interface, allowing users to more intuitively obtain relevant component information. This enhanced display information is then fed back to operations and management personnel to assist on-site implementation until the hoisting is completed.

[0101] For example, to illustrate the layout of the human-computer interaction interface more clearly, we will use a real-world scenario as an example. Figure 3 This is an example diagram of the human-machine interface in the execution of a component hoisting posture control method provided in Embodiment 2 of the present invention, as shown below. Figure 3 As shown, the content presented on the human-computer interaction interface 1 includes component parameter information 11, such as component number and material; the current frame image 12 of the component to be tracked is marked and locked; the current motion position 13, represented as (X1, Y1, Z1), where X1, Y1, and Z1 represent the current coordinates of the component to be tracked on the three coordinate axes in the coordinate system; the installation position 15, represented as (X2, Y2, Z2), where X2, Y2, and Z2 represent the final coordinates of the component to be tracked on the three coordinate axes in the coordinate system; the current position deviation 14, represented as (ΔX, ΔY, ΔZ), where ΔX, ΔY, and ΔZ represent the coordinate deviations on the three coordinate axes; and safety warning information 16 is also presented on the human-computer interaction interface.

[0102] Example 3

[0103] Figure 4 This is a structural schematic diagram of a component hoisting posture control device provided in Embodiment 3 of the present invention. This device is applicable to situations where the hoisting posture of a component is monitored and controlled during the hoisting process. The component hoisting posture control device can be implemented in hardware and / or software, and is generally integrated into electronic equipment. For example... Figure 4As shown, the device includes: an optimal pose determination module 31, an information acquisition module 32, a current pose determination module 33, and a component adjustment module 34, wherein...

[0104] The optimal pose determination module 31 is used to obtain the optimal motion pose of the component to be tracked during the process of hoisting from the initial position to the installation position. The optimal motion pose includes the optimal motion position and the optimal spatial pose at the optimal motion position.

[0105] The information acquisition module 32 is used to acquire the current movement position of the component to be tracked by a total station and prism pre-arranged in the relative coordinate system of the engineering environment during the hoisting process of the component to be tracked, and at the same time acquire the video stream data of the component to be tracked by a pre-arranged video acquisition device.

[0106] The current attitude determination module 33 is used to determine the current spatial attitude of the component to be tracked at the current motion position based on the video stream data of the component to be tracked.

[0107] The component adjustment module 34 is used to provide adjustment suggestions for the component to be tracked based on the optimal motion position, optimal spatial attitude, current motion position, and current spatial attitude.

[0108] Unlike existing technologies that rely on multiple total stations to observe component posture, which are unsuitable for scenarios with limited space and poor visibility, the above solution uses a single total station and a video acquisition device. The total station captures the component's real-time position, while the video acquisition device captures video stream data. Processing this video stream data allows for the identification of the component's real-time spatial posture. Based on this, the component's position and spatial posture can be observed in real time, and adjustment suggestions can be made based on the optimal motion posture. This achieves real-time monitoring of the component's position and spatial posture during hoisting and provides motion suggestions, solving the problem of not being able to monitor and control component posture in scenarios with limited space and poor visibility.

[0109] Optionally, the optimal pose determination module 31 includes:

[0110] The attitude simulation unit is used to simulate the optimal motion positions and simulated spatial attitudes of the component being tracked during the process of hoisting the component from its initial position to its installation position, based on the relative position of the video acquisition device and the component to be tracked, using preset modeling and motion simulation software.

[0111] The scene rendering unit is used to render each simulated spatial pose based on the real environment scene, and obtain the key frame image corresponding to the component to be tracked at each optimal motion position.

[0112] The optimal pose determination unit is used to obtain the optimal spatial pose of the component to be tracked at the optimal motion position based on each keyframe image and the pre-trained component recognition model.

[0113] Optionally, the optimal attitude determination unit is specifically used for:

[0114] For each optimal motion position, the keyframe image of the component to be tracked at the optimal motion position and the original component image of the component to be tracked are used as input data and input into the pre-trained component recognition model to mark the component to be tracked in the keyframe image.

[0115] The spatial pose of the component to be tracked, marked in the keyframe image, is determined as the optimal spatial pose of the component to be tracked at the optimal motion position.

[0116] Optionally, the current attitude determination module 33 is specifically used for:

[0117] Extract the current frame image corresponding to the current motion position of the component to be tracked from the video stream data of the component to be tracked;

[0118] The current frame image and the original component image of the component to be tracked are used as input data and fed into the pre-trained component recognition model to mark the component to be tracked in the current frame image.

[0119] The spatial pose of the component to be tracked marked in the current frame image is determined as the current spatial pose of the component to be tracked at the current position.

[0120] Optionally, the component adjustment module 34 is specifically used for:

[0121] If the difference between the current motion position and the optimal motion position is within the first set error range, then no movement operation suggestion is made for the tracking component; otherwise, a movement operation suggestion is made for the tracking component.

[0122] If the difference between the current spatial attitude and the optimal spatial attitude is within the second set error range, then no rotation operation suggestion is made for the tracking component; otherwise, a rotation operation suggestion is made for the tracking component.

[0123] Optionally, the model training module is specifically used for:

[0124] Collect a first set number of first images from the completion of component processing to the preparation for hoisting, and a second set number of second images obtained by modeling and motion simulation software based on the simulation rendering of the component in a real environment scene. Record the first images and the second images as sample images.

[0125] Each sample image is labeled with components to obtain a sample training set. The sample training set includes at least one sample training pair. Each sample training pair includes a sample image and the corresponding sample image after the components are labeled.

[0126] The initial neural network model is trained based on the sample training set, and the trained initial neural network model is used as the component recognition model.

[0127] Optionally, the device also includes a safety warning module, specifically used for:

[0128] Based on the safety monitoring information collected by the safety monitoring equipment, the safety monitoring equipment is installed on the component to be tracked or on a building at a set distance from the component to be tracked during the hoisting process;

[0129] If the safety monitoring information exceeds the set safety information threshold, a safety warning will be issued;

[0130] If the safety monitoring information is less than or equal to the set safety information threshold, no safety warning will be issued.

[0131] Optionally, the device also includes an information display module, specifically used for:

[0132] The component-related information of the component to be tracked is presented on the human-computer interaction interface. The component-related information includes at least one of the following: component parameter information, current frame image of the component to be tracked, current motion position, installation position, current position deviation, or safety warning information. The current position deviation is obtained by subtracting the installation position from the current motion position.

[0133] The component hoisting posture control device provided in the embodiments of the present invention can execute the component hoisting posture control method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0134] Example 4

[0135] Figure 5 This is a schematic diagram of an electronic device according to Embodiment 4 of the present invention. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (such as helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0136] like Figure 5As shown, the electronic device 40 includes at least one processor 41 and a memory, such as a read-only memory (ROM) 42 or a random access memory (RAM) 43, communicatively connected to the at least one processor 41. The memory stores computer programs executable by the at least one processor. The processor 41 can perform various appropriate actions and processes based on the computer program stored in the ROM 42 or loaded into the RAM 43 from storage unit 48. The RAM 43 may also store various programs and data required for the operation of the electronic device 40. The processor 41, ROM 42, and RAM 43 are interconnected via a bus 44. An input / output (I / O) interface 45 is also connected to the bus 44.

[0137] Multiple components in electronic device 40 are connected to I / O interface 45, including: input unit 46, such as keyboard, mouse, etc.; output unit 47, such as various types of monitors, speakers, etc.; storage unit 48, such as disk, optical disk, etc.; and communication unit 49, such as network card, modem, wireless transceiver, etc. Communication unit 49 allows electronic device 40 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0138] Processor 41 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 41 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 41 performs the various methods and processes described above, such as methods for controlling the posture of component hoisting.

[0139] In some embodiments, the method for controlling the lifting posture of a component can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 48. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 40 via ROM 42 and / or communication unit 49. When the computer program is loaded into RAM 43 and executed by processor 41, one or more steps of the method for controlling the lifting posture of the component described above can be performed. Alternatively, in other embodiments, processor 41 can be configured to perform the method for controlling the lifting posture of the component by any other suitable means (e.g., by means of firmware).

[0140] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0141] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0142] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0143] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0144] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or computing systems that include middleware components (e.g., application servers), or computing systems that include frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0145] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0146] This invention also provides a computer program product, including a computer program that, when executed by a processor, implements the component hoisting posture control method provided in any embodiment of this invention.

[0147] In implementing a computer program product, computer program code for performing the operations of this disclosure can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include, but are not limited to, object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as C or similar languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0148] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0149] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A method for controlling the hoisting posture of a component, characterized in that, include: The optimal motion pose of the component to be tracked is obtained during the process of hoisting from the initial position to the installation position. The optimal motion pose includes the optimal motion position and the optimal spatial pose at the optimal motion position. During the hoisting process of the component to be tracked, the current movement position of the component to be tracked is collected by a total station and prism pre-arranged in the relative coordinate system of the engineering environment, while video stream data of the component to be tracked is collected by a pre-arranged video acquisition device. Based on the video stream data of the component to be tracked, determine the current spatial pose of the component at the current motion position; Based on the optimal motion position, the optimal spatial pose, the current motion position, and the current spatial pose, adjustment suggestions are proposed for the component to be tracked; The step of obtaining the optimal motion pose of the component to be tracked during the process of hoisting it from its initial position to its installation position includes: Using pre-set modeling and motion simulation software, based on the relative position of the video acquisition device and the component to be tracked, the optimal motion positions of the component to be tracked during the process of hoisting from the initial position to the installation position and the simulated spatial posture at each of the optimal motion positions are simulated. Render the simulated spatial poses based on the real environment scene to obtain keyframe images corresponding to the tracked components at the optimal motion positions; Based on the keyframe images and the pre-trained component recognition model, the optimal spatial pose of the component to be tracked at each optimal motion position is obtained.

2. The method according to claim 1, characterized in that, The step of obtaining the optimal spatial pose of the tracked component at each of the optimal motion positions based on each of the keyframe images and the pre-trained component recognition model includes: For each optimal motion position, the keyframe image corresponding to the component to be tracked at the optimal motion position and the original component image of the component to be tracked are used as input data and input into the pre-trained component recognition model, and the component to be tracked is marked in the keyframe image. The spatial pose of the component to be tracked, marked in the keyframe image, is determined as the optimal spatial pose of the component to be tracked at the optimal motion position.

3. The method according to claim 1, characterized in that, Determining the current spatial pose of the component to be tracked at the current motion position based on the video stream data of the component to be tracked includes: Extract the current frame image corresponding to the current motion position of the component being tracked from the video stream data of the component being tracked; The current frame image and the original component image of the component to be tracked are used as input data and input into a pre-trained component recognition model to mark the component to be tracked in the current frame image. The spatial pose of the component to be tracked marked in the current frame image is determined as the current spatial pose of the component to be tracked at the current motion position.

4. The method according to claim 1, characterized in that, The step of proposing adjustment suggestions for the tracked component based on the optimal motion position, the optimal spatial pose, the current motion position, and the current spatial pose includes: If the difference between the current movement position and the optimal movement position is within a first set error range, then no movement operation suggestion is made for the tracked component; otherwise, a movement operation suggestion is made for the tracked component. If the difference between the current spatial attitude and the optimal spatial attitude is within a second set error range, then no rotation operation suggestion is made for the tracked component; otherwise, a rotation operation suggestion is made for the tracked component.

5. The method according to claim 1, characterized in that, The training steps of the component recognition model include: Collect a first set number of first images from the completion of component processing to the preparation for hoisting, and a second set number of second images obtained by the modeling and motion simulation software based on the simulation rendering of the component in a real environment scene. Record the first images and the second images as sample images. Each of the sample images is labeled with components to obtain a sample training set. The sample training set includes at least one sample training pair. Each sample training pair includes a sample image and a corresponding sample image with the labeled components. The initial neural network model is trained based on the sample training set, and the trained initial neural network model is used as the component recognition model.

6. The method according to claim 1, characterized in that, Also includes: Based on the safety monitoring information collected by the safety monitoring equipment, the safety monitoring equipment is installed on the component to be tracked or on a building at a set distance from the component to be tracked during the hoisting process; If the security monitoring information exceeds the set security information threshold, a security warning will be issued; If the security monitoring information is less than or equal to the set security information threshold, no security warning will be issued.

7. The method according to claim 1, characterized in that, Also includes: The component-related information of the component to be tracked is presented on the human-computer interaction interface. The component-related information includes at least one of the following: component parameter information, current frame image of the component to be tracked, current motion position, installation position, current position deviation, or safety warning information. The current position deviation is obtained by subtracting the installation position from the current motion position.

8. A control device for the hoisting position of a component, characterized in that, include: The optimal pose determination module is used to obtain the optimal motion pose of the component to be tracked during the process of hoisting from the initial position to the installation position. The optimal motion pose includes the optimal motion position and the optimal spatial pose at the optimal motion position. The information acquisition module is used to acquire the current movement position of the component to be tracked by a total station and prism pre-arranged in the relative coordinate system of the engineering environment during the hoisting process of the component to be tracked, and to acquire video stream data of the component to be tracked by a pre-arranged video acquisition device. The current attitude determination module is used to determine the current spatial attitude of the component to be tracked at the current motion position based on the video stream data of the component to be tracked. The component adjustment module is used to provide adjustment suggestions for the component to be tracked based on the optimal motion position, the optimal spatial attitude, the current motion position, and the current spatial attitude. The optimal pose determination module includes: The attitude simulation unit is used to simulate the optimal motion positions and simulated spatial attitudes of the component being tracked during the process of hoisting the component from its initial position to its installation position, based on the relative position of the video acquisition device and the component to be tracked, using preset modeling and motion simulation software. The scene rendering unit is used to render each simulated spatial pose based on the real environment scene, and obtain the key frame image corresponding to the component to be tracked at each optimal motion position. The optimal pose determination unit is used to obtain the optimal spatial pose of the component to be tracked at the optimal motion position based on each keyframe image and the pre-trained component recognition model.

9. An electronic device, characterized in that, include: At least one processor; as well as A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the component hoisting posture control method as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when executed by a processor, implement the component hoisting posture control method as described in any one of claims 1-7.

11. A computer program product, characterized in that, The computer program product includes a computer program that, when executed by a processor, implements the component hoisting posture control method as described in any one of claims 1-7.

Images