Foundation pit engineering monitoring method, system and electronic device based on three-dimensional point cloud

Abstract

The present application relates to the technical field of foundation pit engineering monitoring, and provides a foundation pit engineering monitoring method, system and electronic device based on three-dimensional point clouds, which comprises the following steps: generating an original three-dimensional point cloud of the i-th stage suitable for representing a foundation pit construction site according to an image set required in the i-th monitoring period; and after processing the original three-dimensional point cloud of the i-th stage into a foundation pit scene point cloud model, checking whether at least one piece of the current period of material stacking area is distributed outside the current period of foundation pit area; if yes, performing risk level analysis on the at least one piece of the current period of material stacking area according to the current period of foundation pit area; and if no, assigning a preset safety index to the corresponding foundation pit scene point cloud model. The present application overcomes the technical defect that the existing method of automatically monitoring foundation pit engineering based on three-dimensional point clouds ignores the risk of materials stacked outside the foundation pit, and has the advantages of convenience, safety and saving of manpower compared with the artificial periodic inspection method.

Description

Technical Field

[0001] This invention relates to the field of foundation pit engineering monitoring technology, and more specifically, to foundation pit engineering monitoring methods, systems, and electronic devices based on three-dimensional point clouds. Background Technology

[0002] Foundation pit engineering is a systematic project that integrates geological engineering, geotechnical engineering, structural engineering and geotechnical testing technology. Its main contents include: engineering survey, support structure design and construction, earthwork excavation and backfilling, groundwater control, information-based construction and surrounding environmental protection.

[0003] Due to the influence of geological conditions and the surrounding environment, foundation pit engineering is inherently risky during construction and use. Numerous building codes impose various safety requirements on foundation pit engineering construction. For example, the "Technical Standard for Monitoring of Building Foundation Pit Engineering" specifies key technical content including monitoring items, methods, accuracy requirements, and monitoring frequencies. This includes instrument monitoring items such as slope displacement / earth pressure, pit bottom heave, and groundwater level, as well as inspection items such as checking for cracks / excessive deformation in the support structure, overloading of the ground around the foundation pit, and changes in the load on adjacent foundation pits. The "Code for Construction of Building Foundation Engineering" stipulates that material stockpiling at the construction site should meet design load control requirements. Temporary soil stockpiles on site must have a reasonable planar range and height; stockpiling heights exceeding design overload requirements can cause foundation pit safety issues. The distance from the stockpile to the pit edge is generally no less than 3 meters for dry, dense soil or no less than 5 meters for loose soil. And so on.

[0004] However, the periodic inspections of the foundation pit construction site by construction management personnel to control the risks of stockpiled materials (such as earthwork and / or building materials) have many drawbacks, such as being time-consuming and labor-intensive, having untimely early warnings, and posing significant risks to personnel. These drawbacks are even more pronounced under severe weather conditions such as heavy rain and earthquakes. Meanwhile, automated foundation pit engineering monitoring technology focuses on foundation pit deformation, excavation volume, and collapse and seepage. There is a need to provide automated foundation pit engineering monitoring technology that focuses on the risks of stockpiled materials. Summary of the Invention

[0005] The present invention aims to at least partially solve the technical problems in related technologies. To achieve the above objectives, the present invention provides a method, system and electronic device for monitoring foundation pit engineering based on three-dimensional point clouds.

[0006] In a first aspect, the present invention provides a method for monitoring foundation pit engineering based on three-dimensional point clouds, comprising:

[0007] When the image set required for the i-th monitoring cycle is saved in the preset database with periodic updates, the i-th period native three-dimensional point cloud suitable for characterizing the foundation pit construction site is generated based on the image set, where i represents a positive integer accumulated from 1.

[0008] The original 3D point cloud of the i-th period is preprocessed to obtain the pit scene point cloud model bound to the i-th monitoring cycle;

[0009] Verify whether the corresponding point cloud model of the foundation pit scene shows at least one area of ​​the current phase of the piled-up material distributed outside the current phase of the foundation pit area;

[0010] If so, then a risk level assessment shall be conducted on at least one of the current phase of the excavation pit area;

[0011] If not, then the preset safety indicators will be assigned to the corresponding point cloud model of the foundation pit scene.

[0012] Secondly, the present invention provides a foundation pit engineering monitoring system based on three-dimensional point clouds, comprising:

[0013] The 3D point cloud generation module is used to generate a native 3D point cloud suitable for characterizing the foundation pit construction site based on the image set when the image set required for the i-th monitoring cycle is saved in the preset database with periodic updates. Here, i represents a positive integer accumulated from 1.

[0014] The point cloud scene reconstruction module is used to preprocess the original 3D point cloud of the i-th period to obtain the pit scene point cloud model bound to the i-th monitoring cycle.

[0015] The material storage risk review module is used to review whether the corresponding pit scene point cloud model shows that at least one material storage area in this phase is distributed outside the pit area in this phase. If so, the risk level of at least one material storage area in this phase is identified based on the pit area in this phase. If not, a preset safety index is assigned to the corresponding pit scene point cloud model.

[0016] Thirdly, the present invention provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, when the processor executes the computer program, it implements the foundation pit engineering monitoring method based on three-dimensional point clouds as described in the first aspect.

[0017] Using the foundation pit engineering monitoring method, system, and electronic equipment based on three-dimensional point clouds provided by this invention, the image is periodically updated by a preset database. In each monitoring cycle, an image set adapted to the foundation pit construction site is used to create a corresponding native three-dimensional point cloud. The native three-dimensional point cloud is processed into a corresponding foundation pit scene point cloud model for subsequent automated review of the risk of external materials in the foundation pit. This overcomes the technical defect of existing methods for automated monitoring of foundation pit engineering based on three-dimensional point clouds that ignore the risk of external materials in the foundation pit. Compared with manual periodic inspection methods, it has the advantages of convenience, safety, and saving manpower. Attached Figure Description

[0018] Figure 1 This is a flowchart illustrating a foundation pit engineering monitoring method based on three-dimensional point clouds, according to an embodiment of the present invention.

[0019] Figure 2 This is a schematic diagram of a foundation pit scene according to an embodiment of the present invention;

[0020] Figure 3 This is a flowchart illustrating another method for monitoring foundation pit engineering based on three-dimensional point clouds according to an embodiment of the present invention.

[0021] Figure 4 This is a schematic diagram of the architecture of a foundation pit engineering monitoring device based on three-dimensional point cloud according to an embodiment of the present invention;

[0022] Figure 5 This is a schematic diagram of the architecture of another foundation pit engineering monitoring device based on three-dimensional point cloud according to an embodiment of the present invention;

[0023] Figure 6 This is a circuit diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0024] Embodiments of the present invention will now be described in detail with reference to the accompanying drawings. When referring to the drawings, unless otherwise indicated, the same reference numerals in different drawings denote the same or similar elements. It should be noted that the embodiments described in the following exemplary embodiments do not represent all embodiments of the present invention. They are merely examples of apparatuses and methods consistent with some aspects of the present invention disclosed in the claims, and the scope of the present invention is not limited thereto. Features in the various embodiments of the present invention can be combined with each other without contradiction.

[0025] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one of that feature. In the description of this invention, "a plurality of" means at least two, such as two, three, etc., unless otherwise explicitly specified.

[0026] See Figure 1 The foundation pit engineering monitoring method based on three-dimensional point cloud provided in this embodiment of the invention includes S10 to S50.

[0027] S10, when the image set required for the i-th monitoring cycle is saved in the preset database with periodic update properties, generate the i-th period original three-dimensional point cloud suitable for characterizing the foundation pit construction site based on the image set required for the i-th monitoring cycle.

[0028] Where i represents a positive integer accumulated starting from 1, and i ≤ the total number of cycles required from the excavation of the foundation pit to its completion as planned in advance. For example, the total number of cycles can be 45 or 120 or other values. The total number of cycles should be consistent with the actual situation of the specific foundation pit project. This invention does not impose any restrictions.

[0029] For example, multiple cameras can be deployed at and near the foundation pit construction site. A central control unit (e.g., a laptop computer) can connect to each of the multiple cameras configured to take photos simultaneously via a wireless network. For example, the foundation pit construction site could be a bridge foundation pit construction site. Each camera takes a photo at regular intervals (e.g., 12 hours, 24 hours, or 48 hours). Upon completion of each photo session, the resulting image of the foundation pit scene is immediately transmitted. A single foundation pit scene image is shown below. Figure 2 As shown, for a certain camera, the time interval between two consecutive photos is a monitoring cycle.

[0030] For example, at the beginning of each monitoring cycle, the central control unit can either send a photo-taking command to multiple cameras simultaneously so that the multiple cameras can take photos at the same time, or create a sub-library in the preset database that is identified by the corresponding monitoring cycle. This sub-library is used to store the pit scene images sent from each camera to the central control unit. Multiple pit scene images with different perspectives form an image set. Each monitoring cycle is adapted to the image update cycle of the preset database and the photo-taking cycle of the cameras.

[0031] For example, during each monitoring cycle, the camera mounted on the drone can take aerial photos of the construction site above the foundation pit. The photos can then be imported from the camera into a desktop computer. The desktop computer can then extract multiple images of the foundation pit scene from different perspectives from the video and store them as a corresponding image set in a preset database.

[0032] S20, preprocess the original 3D point cloud of the i-th period to obtain the pit scene point cloud model bound to the i-th monitoring cycle.

[0033] In this embodiment of the invention, preprocessing may include point cloud denoising, point cloud filtering, and point cloud segmentation. Point cloud segmentation can be implemented using a pre-trained point cloud semantic segmentation model or a point cloud panoramic segmentation model. For example, the point cloud semantic segmentation model may use the PointNet algorithm, the PointNet++ algorithm, or other machine learning algorithms. The point cloud panoramic segmentation model may use Panoptic-PolarNet or other machine learning algorithms. Alternatively, point cloud panoramic segmentation methods such as those proposed in applications CN202010207999.2 and CN202310019910.3 may be used, which will not be elaborated here.

[0034] S30: Check whether the point cloud model of the corresponding foundation pit scene shows at least one area of ​​the current phase of the stacked material distributed outside the current phase foundation pit area. If yes, proceed to S40; otherwise, proceed to S50.

[0035] S40, conduct risk level assessment for each stockpiled area in this phase based on the foundation pit area in this phase.

[0036] S50 assigns preset safety indicators to the corresponding pit scene point cloud model.

[0037] For example, the preset safety index can be 0, true, or other forms. 0 is suitable to indicate that there is no risk of material accumulation outside the foundation pit. It should be understood that the preset safety index only needs to be able to distinguish it from the risk level. This invention does not impose any specific limitations.

[0038] Using the above-mentioned three-dimensional point cloud-based foundation pit engineering monitoring method, which is constrained by the periodic updating of images in a preset database, in each monitoring cycle, the image set adapted to the foundation pit construction site is used to create a corresponding native three-dimensional point cloud. This native three-dimensional point cloud is then processed into a corresponding foundation pit scene point cloud model for subsequent automated review of the risk of external materials in the foundation pit. This method overcomes the technical defect of existing methods for automated monitoring of foundation pit engineering based on three-dimensional point clouds that ignore the risk of external materials in the foundation pit. Compared with manual periodic inspection methods, it has advantages such as convenience, safety, and saving manpower.

[0039] Optionally, S30 includes:

[0040] The point cloud model of the foundation pit scene is selected according to the preset label table, which includes foundation pit labels and at least one stacked object label.

[0041] When the current phase of the foundation pit area that matches the foundation pit label is selected, the pit opening outline is identified for the selected current phase foundation pit area.

[0042] When a current stockpile area that matches any stockpile label is selected, the outline of the stockpile is identified for the selected current stockpile area, and the positional relationship between the outline of the stockpile and the pit opening is detected.

[0043] If the outline of the pit opening is different from the outline of at least one stockpile, the audit conclusion is confirmed as yes; otherwise, the audit conclusion is confirmed as no. The audit conclusion of no can reflect two situations: first, there is no stockpile outside the pit; second, the stockpile is at least partially inside the pit.

[0044] For example, the corresponding contour can be detected by point cloud concave hull algorithm or point cloud PCL library, or other deep learning algorithms such as convolutional neural network (CNN) can be used. This can be achieved by referring to existing technologies, and will not be elaborated here.

[0045] Given that the point cloud model of the foundation pit scene must have a point cloud region suitable for representing the foundation pit (i.e., the foundation pit region), or may or may not have a point cloud region suitable for representing the piled-up objects (i.e., the piled-up object region), based on the outline of the pit opening, in the case of a piled-up object region, it is detected whether the outline of the piled-up object is separate from the outline of the pit opening, so as to obtain a review conclusion suitable for reflecting whether there are piled-up objects outside the foundation pit, thus taking into account the simplicity and reliability of the review of the point cloud model of the foundation pit scene.

[0046] Optionally, detecting the positional relationship between the outline of the stockpile and the outline of the pit opening includes: projecting the outline of the stockpile onto the plane containing the outline of the pit opening to form a corresponding projected outline; detecting the intersection of the projected outline and the outline of the pit opening; if the number of intersections is zero, selecting any point on the projected outline as a verification point; otherwise, confirming that the outline of the pit opening intersects with the corresponding outline of the stockpile; detecting whether the verification point is located inside the outline of the pit opening; if so, confirming that the outline of the pit opening surrounds the outline of the corresponding outline of the stockpile; otherwise, confirming that the outline of the pit opening is separate from the outline of the corresponding outline of the stockpile.

[0047] The plane containing the pit opening profile is suitable for representing the ground plane. By combining the intersection detection method with the profile projection method and the single-point position detection method in an orderly manner, the simplicity, reliability and accuracy of detecting the positional relationship of the profile are taken into account.

[0048] Optionally, S40 includes:

[0049] For any stockpile area in this phase, detect the closest distance and the maximum height difference between the stockpile shape and the pit opening shape in the current phase foundation pit area.

[0050] If the nearest distance is greater than the pre-designed safe distance and the maximum height difference is less than or equal to the pre-designed safe height, the corresponding risk level will be determined as Level 1.

[0051] If the nearest distance is greater than the pre-designed safe distance and the maximum height difference is greater than the pre-designed safe height, the corresponding risk level will be determined as Level II;

[0052] If the nearest spacing is less than or equal to the pre-designed safety distance, the volume of the stockpiled material in the corresponding current stockpiling area shall be measured.

[0053] If the volume of the stacked material is less than or equal to the pre-designed safe volume and the maximum height difference is less than or equal to the pre-designed safe height, the corresponding risk level will be determined as Level III.

[0054] If the volume of the stacked material is less than or equal to the pre-designed safe volume and the maximum height difference is greater than the pre-designed safe height, the corresponding risk level will be determined as level four.

[0055] If the volume of the stacked material is greater than the pre-designed safe volume and the maximum height difference is less than or equal to the pre-designed safe height, the corresponding risk level will be determined as Level 5.

[0056] If the volume of the stacked material exceeds the pre-designed safe volume and the maximum height difference exceeds the pre-designed safe height, the corresponding risk level will be determined as Level VI.

[0057] For example, the volume of a pile can be detected by at least one of the existing techniques, such as convex hull algorithm, mesh model reconstruction method, slicing method and projection method, which will not be elaborated here.

[0058] For example, the aforementioned closest distance can be directly compared with the pre-designed safety distance, where the pre-designed safety distance can be 1 meter, 1.5 meters or other values, or the pre-designed safety distance can be proportional to the pre-designed pit depth. For example, the ratio of the pre-designed pit depth to the pre-designed pit depth is 3:1 or 2:1 or other ratios. The larger the closest distance, the farther the piled material is from the pit opening, and vice versa.

[0059] For example, the maximum height difference can be directly compared with the pre-designed safety height, which can be 1.5 meters, 2 meters or other values. The larger the maximum height difference, the higher the safety risk of landslides or tilting of the stacked material. Conversely, the lower the safety risk of the stacked material itself.

[0060] For example, the volume of the above-mentioned pile can be directly compared with the pre-designed safe volume, which can be 25 cubic meters, 50 cubic meters or other values. The larger the difference between the pile volume and the maximum height, the higher the safety risk caused by the pile near the foundation pit. Conversely, the lower the difference, the lower the safety risk caused by the pile near the foundation pit.

[0061] If the distance between the material storage area and the foundation pit area meets the safety requirements, the risk level is determined by considering the relationship between the maximum height difference and the pre-designed safe height, and is classified as Level 1 or Level 2. If the distance between the material storage area and the foundation pit area does not meet the safety requirements, in addition to considering the relationship between the maximum height difference and the pre-designed safe height, the risk level is further determined by considering the relationship between the volume of the material storage area and the pre-designed safe volume, and is classified as Level 3, Level 4, Level 5, or Level 6. Levels 1 to 6 reflect the increasing risk of materials stored outside the foundation pit, taking into account both the accuracy and simplicity of risk level assessment.

[0062] Optional, participate Figure 3 The foundation pit engineering monitoring method based on 3D point cloud also includes S60, which includes: detecting the volume ratio between the current foundation pit area and the pre-designed foundation pit shape, as a corresponding foundation pit excavation progress, which helps to improve the utilization rate of the foundation pit scene point cloud model.

[0063] For example, the volume of the foundation pit area in this phase can be measured based on the above-mentioned pit opening outline, and the pre-designed foundation pit shape can be rectangular, cylindrical or other shapes.

[0064] See Figure 4 The present invention provides a foundation pit engineering monitoring system based on three-dimensional point cloud, comprising: a three-dimensional point cloud generation module, a point cloud scene reconstruction module, and a material risk review module.

[0065] The 3D point cloud generation module is used to generate a native 3D point cloud suitable for characterizing the foundation pit construction site when the image set required for the i-th monitoring cycle is saved in the preset database with periodic updates. i represents a positive integer accumulated from 1.

[0066] The point cloud scene reconstruction module is used to preprocess the original 3D point cloud of the i-th period to obtain the pit scene point cloud model bound to the i-th monitoring cycle.

[0067] The material storage risk review module is used to review whether the corresponding foundation pit scene point cloud model shows that at least one material storage area in this phase is located outside the foundation pit area in this phase. If so, the risk level of at least one material storage area in this phase is identified based on the foundation pit area in this phase. If not, the preset safety indicators are assigned to the corresponding foundation pit scene point cloud model.

[0068] Optionally, the stacking risk assessment module is specifically used for:

[0069] The point cloud model of the foundation pit scene is selected according to the preset label table, which includes foundation pit labels and at least one stacked object label.

[0070] When the current phase of the foundation pit area that matches the foundation pit label is selected, the pit opening outline is identified for the selected current phase foundation pit area.

[0071] When a current stockpile area that matches any stockpile label is selected, the outline of the stockpile is identified for the selected current stockpile area, and the positional relationship between the outline of the stockpile and the pit opening is detected.

[0072] If the pithead outline is different from the outline of at least one pile, the audit conclusion is confirmed as yes; otherwise, the audit conclusion is confirmed as no.

[0073] Optionally, the stacking risk assessment module is also specifically used for:

[0074] For any stockpile area in this phase, detect the closest distance and the maximum height difference between the stockpile outline and the pit opening outline in the foundation pit area in this phase.

[0075] If the nearest distance is greater than the pre-designed safe distance and the maximum height difference is less than or equal to the pre-designed safe height, the corresponding risk level will be determined as Level 1.

[0076] If the nearest distance is greater than the pre-designed safe distance and the maximum height difference is greater than the pre-designed safe height, the corresponding risk level will be determined as Level II;

[0077] If the nearest spacing is less than or equal to the pre-designed safety distance, the volume of the stockpiled material in the corresponding current stockpiling area shall be measured.

[0078] If the volume of the stacked material is less than or equal to the pre-designed safe volume and the maximum height difference is less than or equal to the pre-designed safe height, the corresponding risk level will be determined as Level III.

[0079] If the volume of the stacked material is less than or equal to the pre-designed safe volume and the maximum height difference is greater than the pre-designed safe height, the corresponding risk level will be determined as level four.

[0080] If the volume of the stacked material is greater than the pre-designed safe volume and the maximum height difference is less than or equal to the pre-designed safe height, the corresponding risk level will be determined as Level 5.

[0081] If the volume of the stacked material exceeds the pre-designed safe volume and the maximum height difference exceeds the pre-designed safe height, the corresponding risk level will be determined as Level VI.

[0082] Optionally, see Figure 5 The foundation pit engineering monitoring system based on three-dimensional point clouds also includes a pit excavation progress detection module, which is used to detect the volume ratio between the current foundation pit area and the pre-designed foundation pit shape, as the corresponding foundation pit excavation progress.

[0083] See Figure 6 This invention provides an electronic device including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, it implements the aforementioned method for monitoring foundation pit engineering based on three-dimensional point clouds. The processor can be connected to the memory via a universal serial bus. It is understood that the aforementioned electronic device can be a server or a terminal device.

[0084] The present invention provides a non-transitory computer-readable storage medium storing a computer program thereon. When the computer program is executed by a processor, it implements the above-mentioned foundation pit engineering monitoring method based on three-dimensional point clouds.

[0085] Generally, the computer instructions for implementing the method of the present invention can be carried on any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable medium except for the signal itself, which is temporarily propagating.

[0086] Computer-readable storage media can be, for example, but not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatuses, or any combination thereof. More specific examples (a non-exhaustive list) of computer-readable storage media include: electrical connections having 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 fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in connection with an instruction execution system, apparatus, or device.

[0087] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof. These programming languages ​​include object-oriented programming languages—such as Java, Smalltalk, and C++—as well as conventional procedural programming languages—such as the "C" language or similar programming languages. In particular, Python, suitable for neural network computation, and platform frameworks based on TensorFlow, PyTorch, etc., can be used. 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 connected to an external computer (e.g., via the Internet using an Internet service provider).

[0088] The aforementioned foundation pit engineering monitoring system and electronic equipment based on three-dimensional point clouds can be found in the above description of the implementation details and beneficial effects of the foundation pit engineering monitoring method based on three-dimensional point clouds, which will not be repeated here.

[0089] Although embodiments of the present invention have been shown and described above, it should be understood that the above embodiments are exemplary and should not be construed as limiting the present invention. Those skilled in the art can make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention.

Claims

1. A method for monitoring foundation pit engineering based on three-dimensional point clouds, characterized in that, include: When the image set required for the i-th monitoring cycle is saved in the preset database with periodic updates, the i-th period native three-dimensional point cloud suitable for characterizing the foundation pit construction site is generated based on the image set, where i represents a positive integer accumulated from 1. The original 3D point cloud of the i-th period is preprocessed to obtain the pit scene point cloud model bound to the i-th monitoring cycle; Verify whether the corresponding point cloud model of the foundation pit scene shows at least one area of ​​the current phase of the piled-up material distributed outside the current phase of the foundation pit area; If so, then a risk level assessment shall be conducted on at least one of the current phase of the excavation pit area; If not, a preset safety indicator is assigned to the corresponding pit scene point cloud model. The preset safety indicator is 0, true, or other forms that can be distinguished from the risk level obtained through identification. The review of whether the corresponding point cloud model of the foundation pit scene shows at least one area of ​​the current phase of the pile material distributed outside the current phase of the foundation pit area includes: The point cloud model of the foundation pit scene is selected according to a preset label table, which includes foundation pit labels and at least one type of stacked object label. When the current phase foundation pit area that is compatible with the foundation pit label is selected, the pit opening outline is identified for the selected current phase foundation pit area. When the current stockpiled area that is adapted to any of the stockpiled material labels is selected, the stockpiled material outline is identified for the selected current stockpiled area, and the positional relationship between the stockpiled material outline and the pit opening outline is detected. If the outline of the pit opening is different from the outline of at least one of the piles, the audit conclusion is confirmed as yes; otherwise, the audit conclusion is confirmed as no.

2. The foundation pit engineering monitoring method based on three-dimensional point cloud as described in claim 1, characterized in that, Detecting the positional relationship between the outline of the pile and the outline of the pit opening includes: The outline of the pile is projected onto the plane containing the pit opening outline to form a corresponding projected outline. The intersection point detection is performed between the projected contour and the pit opening contour. If the number of intersection points is zero, any point on the projected contour is selected as the verification point; otherwise, it is confirmed that the pit opening contour intersects with the corresponding pile shape contour. If the verification point is located within the outline of the pit opening, it is confirmed that the outline of the pit opening surrounds the corresponding outline of the pile; otherwise, it is confirmed that the two are separate.

3. The foundation pit engineering monitoring method based on three-dimensional point cloud as described in claim 1, characterized in that, Based on the aforementioned foundation pit area, risk level assessment of at least one of the aforementioned stockpiling areas includes: For any of the material pile outlines in the current phase of the excavation area, detect the closest distance and the maximum height difference between the material pile outline and the pit opening outline in the current phase of the excavation area. If the nearest distance is greater than the pre-designed safe distance and the maximum height difference is less than or equal to the pre-designed safe height, then the corresponding risk level is determined to be Level 1. If the nearest distance is greater than the pre-designed safe distance and the maximum height difference is greater than the pre-designed safe height, then the risk level is determined to be Level II; If the nearest distance is less than or equal to the pre-designed safety distance, then the volume of the stockpiled material is detected for the corresponding stockpiled material area in this phase; If the volume of the piled-up material is less than or equal to the pre-designed safe volume and the maximum height difference is less than or equal to the pre-designed safe height, then the risk level is determined to be Level III. If the volume of the piled-up material is less than or equal to the pre-designed safe volume and the maximum height difference is greater than the pre-designed safe height, then the risk level is determined to be level four. If the volume of the piled-up material is greater than the pre-designed safe volume and the maximum height difference is less than or equal to the pre-designed safe height, then the risk level is determined to be level five. If the volume of the piled-up material is greater than the pre-designed safe volume and the maximum height difference is greater than the pre-designed safe height, then the risk level is determined to be level six.

4. The foundation pit engineering monitoring method based on three-dimensional point clouds according to any one of claims 1 to 3, characterized in that, Also includes: The volume ratio between the current excavation area and the pre-designed excavation shape is detected to determine the corresponding excavation progress.

5. A foundation pit engineering monitoring system based on three-dimensional point clouds, characterized in that, include: The 3D point cloud generation module is used to generate a native 3D point cloud suitable for characterizing the foundation pit construction site based on the image set when the image set required for the i-th monitoring cycle is saved in the preset database with periodic updates. Here, i represents a positive integer accumulated from 1. The point cloud scene reconstruction module is used to preprocess the original 3D point cloud of the i-th period to obtain the pit scene point cloud model bound to the i-th monitoring cycle. The stacking risk review module is used to review whether the corresponding foundation pit scene point cloud model shows that at least one stacking area in this phase is distributed outside the foundation pit area in this phase. If so, the risk level of at least one stacking area in this phase is identified based on the foundation pit area in this phase. If not, a preset safety index is assigned to the corresponding foundation pit scene point cloud model. The preset safety index is 0 or true or other forms that can be distinguished from the risk level obtained through identification. The aforementioned stacking risk review module is specifically used for: The point cloud model of the foundation pit scene is selected according to a preset label table, which includes foundation pit labels and at least one type of stacked object label. When the current phase foundation pit area that is compatible with the foundation pit label is selected, the pit opening outline is identified for the selected current phase foundation pit area. When the current stockpiled area that is adapted to any of the stockpiled material labels is selected, the stockpiled material outline is identified for the selected current stockpiled area, and the positional relationship between the stockpiled material outline and the pit opening outline is detected. If the outline of the pit opening is different from the outline of at least one of the piles, the audit conclusion is confirmed as yes; otherwise, the audit conclusion is confirmed as no.

6. The foundation pit engineering monitoring system based on three-dimensional point clouds according to claim 5, characterized in that, The aforementioned stacking risk review module is specifically used for: For any of the current phase material pile areas, the closest distance and the maximum height difference between the material pile outline and the pit opening outline of the current phase foundation pit area are detected. If the nearest distance is greater than the pre-designed safe distance and the maximum height difference is less than or equal to the pre-designed safe height, then the corresponding risk level is determined to be Level 1. If the nearest distance is greater than the pre-designed safe distance and the maximum height difference is greater than the pre-designed safe height, then the risk level is determined to be Level II; If the nearest distance is less than or equal to the pre-designed safety distance, then the volume of the stockpiled material is detected for the corresponding stockpiled material area in this phase; If the volume of the piled-up material is less than or equal to the pre-designed safe volume and the maximum height difference is less than or equal to the pre-designed safe height, then the risk level is determined to be Level III. If the volume of the piled-up material is less than or equal to the pre-designed safe volume and the maximum height difference is greater than the pre-designed safe height, then the risk level is determined to be level four. If the volume of the piled-up material is greater than the pre-designed safe volume and the maximum height difference is less than or equal to the pre-designed safe height, then the risk level is determined to be level five. If the volume of the piled-up material is greater than the pre-designed safe volume and the maximum height difference is greater than the pre-designed safe height, then the risk level is determined to be level six.

7. The foundation pit engineering monitoring system based on three-dimensional point clouds according to any one of claims 5 to 6, characterized in that, Also includes: The excavation progress detection module is used to detect the volume ratio between the current excavation area and the pre-designed excavation shape, as the corresponding excavation progress.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the foundation pit engineering monitoring method based on three-dimensional point cloud as described in any one of claims 1-4.

Images