Construction work amount real-time monitoring method, device, equipment, medium and product

Abstract

The invention relates to the technical field of construction monitoring, and discloses a construction project amount real-time monitoring method, device, equipment, medium and product, and the method comprises the steps: collecting video monitoring data and point cloud data; establishing a reference coordinate system of the construction site; establishing a mapping relationship among the initial point cloud data, the initial video monitoring data and the reference coordinate system; obtaining estimated volume data within a preset time interval based on the video monitoring data; determining point cloud data corresponding to the video monitoring data space, and calculating actual volume data according to the point cloud data; and correcting the single operation volume of the earthmoving mechanical equipment by using a comparison result of the actual volume data and the estimated volume data. According to the method, the point cloud data and the video data are fused according to the unified reference coordinate system, so that the video data and the point cloud data are simultaneously available in the same construction site, and the video monitoring data are corrected according to the comparison result of the video data and the point cloud data, so that the effect of obtaining the accurate engineering quantity of each earthmoving mechanical equipment is achieved.

Description

Technical Field

[0001] This invention relates to the field of construction quantity monitoring technology, specifically to a method, device, equipment, medium, and product for real-time monitoring of construction quantities. Background Technology

[0002] The accuracy and timeliness of earthwork excavation or backfilling calculations in slope engineering directly impact construction progress, cost control, and project settlement. While current periodic measurement methods based on 3D laser scanning and UAV aerial surveying can provide high-precision interim results, they are costly per measurement and are "post-construction" measurements, unable to provide real-time dynamic feedback and management of the construction process, and failing to meet the real-time information needs for construction equipment scheduling and other aspects of construction process management. Traditional video monitoring methods, based on the massive amounts of unstructured video data generated, can analyze the slope construction process, but cannot obtain the regional location of excavation or backfilling analysis results, making it difficult to meet the actual needs of high-precision measurement in engineering projects. Summary of the Invention

[0003] This invention provides a method, device, equipment, medium, and product for real-time monitoring of construction quantities, in order to solve the problems that periodic measurement methods cannot provide real-time dynamic feedback and management of the construction process, and that traditional video monitoring methods lack accuracy.

[0004] In a first aspect, the present invention provides a method for real-time monitoring of construction quantities, comprising: Within a preset time interval, initial video monitoring data and initial point cloud data are collected in real time at the construction site and periodically. Set up multiple primary control points and establish a reference coordinate system for the construction site based on the primary control points; Establish a spatial mapping relationship between the initial point cloud data, the initial video monitoring data and the reference coordinate system to obtain point cloud data and video monitoring data under a unified coordinate system; Based on video monitoring data, the operation behavior of earthmoving machinery and equipment is identified, and the estimated volume data within a preset time interval is calculated based on the characteristics of the operation behavior. Within the reference coordinate system, the point cloud data corresponding to the video monitoring data space is determined, and the actual volume data within the preset time interval is calculated based on the difference between the point cloud data of adjacent time nodes. By comparing the actual volume data with the estimated volume data, the volume of earthmoving machinery in a single operation is corrected to obtain the corrected volume process data.

[0005] In the calculation process, a reference coordinate system was first established based on the primary control points. In subsequent calculations, the positioning of point cloud data and the conversion from initial video monitoring data to video monitoring data were both calculated based on coordinates within the reference coordinate system. This allowed for the fusion of point cloud data and video data, enabling the simultaneous availability of both precise measurement data within the same construction site. Since the estimated volume data is calculated by analyzing the volume estimation process data of mechanical equipment in the video monitoring data, errors may arise between the analysis and the actual volume. Point cloud data has high accuracy in volume calculation; therefore, a correction coefficient is calculated to correct the errors in the estimated volume data by combining the actual volume data calculated from the point cloud data with the estimated volume data. This correction coefficient is then used to correct the various estimated volume process data under the estimated volume data, thereby obtaining more accurate estimated volume process data.

[0006] In one optional implementation, a spatial mapping relationship is established between the initial point cloud data, the initial video monitoring data, and the reference coordinate system to obtain the point cloud data and video monitoring data in the reference coordinate system, including: Multiple secondary control points are set up within the construction site; the coordinate information of each secondary control point within the construction site is determined in the initial point cloud data; Based on the coordinate information of each secondary control point in the initial point cloud data and the coordinate information of each secondary control point in the reference coordinate system, the rigid transformation matrix of the initial point cloud data is calculated, thereby determining the spatial mapping relationship between the initial point cloud data and the reference coordinate system. The initial point cloud data is mapped to the reference coordinate system according to the mapping relationship to obtain the point cloud data.

[0007] By first finding the mapping relationship between the secondary control points in the initial point cloud data and the reference coordinate system, and then obtaining the relative position of the initial point cloud data in the reference coordinate system based on this mapping relationship, the coordinates of each point in the point cloud data can be obtained. This process is one step in the fusion of point cloud data and video data, and also ensures the accuracy of the obtained point cloud data position.

[0008] In one optional implementation, a spatial mapping relationship is established between the initial point cloud data, the initial video monitoring data, and the reference coordinate system to obtain the point cloud data and video monitoring data in the reference coordinate system, including: The coordinate information of the secondary control points in the construction site in the reference coordinate system is mapped to the camera coordinate system to obtain the coordinate information of each secondary control point in the camera coordinate system; The coordinate information of each secondary control point in the camera coordinate system is mapped to the initial video monitoring data to obtain the image pixel coordinates of each secondary control point in the initial video monitoring data. Based on the coordinate information of each secondary control point in the reference coordinate system and the image pixel coordinates of each secondary control point in the initial video monitoring data, the camera extrinsic parameter matrix of the video monitoring data is calculated, and combined with the camera intrinsic parameter model, the spatial mapping relationship between the initial video monitoring data and the reference coordinate system is determined. The initial video monitoring data is mapped to the reference coordinate system according to the mapping relationship to obtain the video monitoring data.

[0009] By converting the reference coordinates of the secondary control points into camera coordinates, and then converting the camera coordinates into pixel coordinates of the video, a mapping relationship from three-dimensional coordinates to two-dimensional coordinates of the construction site is obtained. This mapping relationship can then be used to convert the complete initial video detection data into video detection data. This conversion process is also calculated based on the reference coordinate system, combining numerical coordinates with video images to achieve the fusion of spatial and visual information, thereby further realizing the fusion of point cloud data and video data.

[0010] In one optional implementation, multiple primary control points are set, and a reference coordinate system for the construction site is established based on the primary control points, including: Multiple primary control points were set up outside the construction site; Take any one of the first-level control points as the origin of the reference coordinate system; Obtain the second-level control points other than the origin, and define the direction from the origin to the second-level control points as the horizontal axis; Obtain the third-level control point in addition to the origin and the second-level control point. Define the reference plane of the reference coordinate system based on the plane determined by the origin, the second-level control point and the third-level control point. Determine the vertical axis and the longitudinal axis according to the reference plane, thereby constructing the reference coordinate system.

[0011] A method for determining a reference coordinate system by setting up primary control points outside the construction site has been disclosed. By using primary control points to construct the reference coordinate system, the accuracy of the established reference coordinate system can be significantly improved, thereby unifying the spatial calculation scale for subsequent processing of video data and point cloud data.

[0012] In one alternative implementation, the method further includes: The construction site was divided into multiple construction sections; The video monitoring data is divided into segmented video monitoring data corresponding to each construction section. Based on the segmented video monitoring data, the earthmoving machinery and equipment of each construction section are analyzed to obtain multiple estimated volume process data of each construction section. Based on the estimated volume process data, the estimated volume data of each construction section within the preset time interval is calculated. The point cloud data is divided into segmented point cloud data corresponding to each construction section. The actual volume data of each construction section within a preset time interval is calculated based on the segmented point cloud data of two consecutive construction sections. Based on the actual volume data and estimated volume data of each construction section, the volume correction coefficient of each construction section within the preset time interval is calculated, and the estimated volume process data is corrected according to the correction coefficient of each construction section to obtain the volume process data.

[0013] By collecting and scanning video segments and correcting the estimated volume data in each video segment, the system can accurately guide construction at the construction site, precisely locate the area where the event occurred, monitor the construction progress of each segment in real time, and promptly identify problems such as over-excavation and under-excavation. This provides data support for refined construction process management and machinery scheduling.

[0014] In one optional implementation, the point cloud data is divided into segmented point cloud data corresponding to each construction section, including: Multiple secondary control points were set up within and at the edges of each construction section. The positions of each point in the point cloud data are calibrated based on the positions of each secondary control point in the point cloud data and their coordinates in the reference coordinate system, so as to obtain the coordinate data of each point in the point cloud data in the reference coordinate system. The point cloud data is segmented based on the coordinate data of the secondary control points at the edge of each construction section and the coordinate data of each point in the point cloud data in the reference coordinate system to obtain the segmented point cloud data corresponding to each construction section.

[0015] This solution proposes a method to segment the point cloud data of the entire construction site based on the coordinate data of the secondary control points, thereby obtaining point cloud data segments for each construction section. By first synchronizing the point cloud data to the reference coordinate system and then segmenting it using the coordinate data of the secondary control points, the segmentation of the point cloud data segments becomes more accurate.

[0016] In one optional implementation, the video monitoring data is divided into segmented video monitoring data corresponding to each construction section, including: The secondary control points at the edges of each construction section are projected onto the two-dimensional plane where the video monitoring data is located, thus obtaining the position of the secondary control points in the video monitoring data; The video monitoring data is segmented based on the location of the secondary control points at the edge of each construction section in the video monitoring data, resulting in segmented video monitoring data for each construction section.

[0017] A method is presented to project the monitoring video data of each construction section from three dimensions to a two-dimensional monitoring plane, accurately dividing the monitoring video data of each construction section. Combined with the point cloud data of each construction section in the above steps, spatial matching of video data and point cloud data is achieved.

[0018] Secondly, the present invention provides a real-time monitoring device for construction quantities, comprising: The data acquisition module is used to collect initial video monitoring data and periodically collect initial point cloud data in real time within a preset time interval. The coordinate establishment module is used to set multiple primary control points and establish a reference coordinate system for the construction site based on the primary control points. The data fusion module is used to establish the spatial mapping relationship between the initial point cloud data, the initial video monitoring data and the reference coordinate system, so as to obtain the point cloud data and video monitoring data in the reference coordinate system. The volume estimation module is used to identify the operating behavior of earthmoving machinery based on video monitoring data, and to calculate the estimated volume data within a preset time interval based on the characteristics of the operating behavior. The volume calculation module is used to determine the point cloud data corresponding to the video monitoring data space in the reference coordinate system, and to calculate the actual volume data within a preset time interval based on the difference between the point cloud data of adjacent time nodes. The volume correction module is used to correct the volume of earthmoving machinery in a single operation by comparing the actual volume data with the estimated volume data, and obtain the corrected volume process data.

[0019] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform a method for real-time monitoring of construction quantities as described in the first aspect or any corresponding embodiment.

[0020] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions, which are used to cause a computer to execute a method for real-time monitoring of construction quantities as described in the first aspect or any corresponding embodiment.

[0021] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute a method for real-time monitoring of construction quantities as described in the first aspect or any corresponding embodiment. Attached Figure Description

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

[0023] Figure 1 This is a schematic diagram of an application scenario according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the first step of a method for real-time monitoring of construction quantities according to an embodiment of the present invention; Figure 3 This is a structural block diagram of a real-time monitoring device for construction quantities according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0026] 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 technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0027] As an optional application scenario of this invention, such as Figure 1 As shown, this real-time monitoring system for construction quantities may include at least one terminal device and at least one server. Figure 1 The system is illustrated in the example, which includes a computer 101, a mobile terminal 102, and a server 103, and the terminal devices such as the computer 101 and the mobile terminal 102 are connected to the server 103 through a network 110.

[0028] Specifically, the terminal device can be a smartphone, tablet, laptop, PDA, desktop computer, game console, smart TV, smart wearable device, in-vehicle terminal, VR (Virtual Reality) device, AR (Augmented Reality) device, etc. Server 103 can be a standalone physical server, a server cluster, a distributed system, or a cloud server providing cloud services. Network 110 can be a wired or wireless network, examples of which include, but are not limited to, the Internet, corporate intranet, local area network, wide area network, mobile communication network, and combinations thereof.

[0029] While current periodic measurement methods based on 3D laser scanning and UAV aerial surveying can provide high-precision interim results, they are costly per measurement and are "post-hoc" measurements, unable to provide real-time dynamic feedback and management of the construction process, and failing to meet the real-time information needs of construction process management such as equipment scheduling. Traditional video monitoring methods, based on the massive amounts of unstructured video data generated, can analyze the slope construction process, but cannot obtain the regional location of excavation or backfill analysis results, making it difficult to meet the actual needs of high-precision engineering measurement. This invention provides a method for real-time monitoring of construction quantities, which calculates calibration coefficients based on point cloud data and estimated data to correct video monitoring data, thereby achieving the effect of obtaining accurate quantities of each earthmoving machinery and equipment.

[0030] According to an embodiment of the present invention, a method for real-time monitoring of construction quantities is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0031] This embodiment provides a method for real-time monitoring of construction quantities. Figure 2 This is a flowchart of a real-time monitoring method for construction quantities according to an embodiment of the present invention, such as... Figure 2 As shown, the process includes the following steps: Step S201: Within a preset time interval, collect initial video monitoring data and periodically collect initial point cloud data within the construction site in real time.

[0032] Initial video monitoring data refers to video data obtained by deploying surveillance cameras within the construction site to monitor and record the site. Initial point cloud data refers to a dataset of surface spatial location information of the construction site acquired through 3D scanning equipment, consisting of a massive number of discrete points. A preset time interval is set to divide the computational unit length for subsequent calculations.

[0033] For example, the preset time interval can be 10 minutes, 20 minutes, etc., and there is no limitation here. Video monitoring data within the construction site can be collected using cameras or surveillance cameras deployed at the construction site, and point cloud data can be collected using a 3D laser scanner. Taking a preset time interval of 10 minutes as an example, video monitoring data is recorded continuously from 0:00 and stored in segments of 10 minutes each. Point cloud data is periodically collected from 0:00 at a frequency of once every 10 minutes.

[0034] Step S202: Set multiple primary control points and establish a reference coordinate system for the construction site based on the primary control points.

[0035] Primary control points are used to establish a reference coordinate system, which will serve as the basis for fusing point cloud data with video monitoring data. In subsequent calculations, the video monitoring data and point cloud data need to be fused together using the reference coordinate system.

[0036] Step S203: Establish the spatial mapping relationship between the initial point cloud data, the initial video monitoring data and the reference coordinate system to obtain point cloud data and video monitoring data under a unified coordinate system.

[0037] Since the spatial mapping relationship between point cloud data and the reference coordinate system and the spatial mapping relationship between initial video monitoring data and the reference coordinate system are both calculated using the reference coordinate system as the calculation reference, this calculation method can achieve accurate fusion of point cloud data and initial video monitoring data.

[0038] Step S204: Identify the operating behavior of earthmoving machinery based on video monitoring data, and calculate the estimated volume data within a preset time interval based on the operating behavior characteristics.

[0039] Estimated volume data is used to characterize the volume of each earthmoving machine's operation during a single operation, as identified by video recognition. Earthmoving machines refer to equipment used for excavation, loading, unloading, and backfilling of land within a construction site, thus changing the volume of the site. The volume of a single operation refers to the magnitude of the volume change at the current construction site resulting from a single operation. Since the machines may perform multiple operations within the preset time interval of the video recording, and since multiple machines may be involved within that time interval, multiple estimated volume process data points can be obtained. By analyzing the estimated volume process data of all earthmoving machines within the preset time period in the video monitoring data, the total volume change data of the current construction site within that time period can be calculated as the estimated volume data. Video analysis can accurately identify and count complete "effective excavation cycles."

[0040] For example, earthmoving machinery and equipment can refer to machinery and equipment such as excavators and dump trucks, and the volume of a single operation can be determined according to the design capacity of the excavator bucket or the loading capacity of the dump truck.

[0041] For example, the analysis of various earthmoving machinery can employ a target detection model optimized for small, distant targets. This model can detect earthmoving machinery such as excavators and dump trucks in real time within the video, and, combined with a multi-target tracking algorithm, assign a unique identifier to each piece of equipment and continuously track it. Semantic relationships between construction machinery and with other objects such as workers and materials are identified through relationship detection modules such as region-based bilinear attention mechanisms or graph-based relational reasoning networks. The results of visual relationship detection are then transformed into structured triplet relationships.

[0042] For example, the image "excavator is digging earth" can be represented as: (excavator, digging, earthwork). Based on the extracted triplet relationships, the operation behavior of the construction machinery is classified into specific construction operation types to determine whether it is an excavation and loading operation or an unloading and backfilling operation. Real-time cumulative recording of excavation or backfilling volume is achieved. As an example, for the sequentially connected triplet "(excavator, digging, earthwork)," excavator lifting and rotating, triplet "(excavator, loading, dump truck)," it can be determined that the excavator is performing an earthwork excavation and loading operation. For the sequentially connected triplet "dump truck moving, hopper lifting, triplet "(dump truck, unloading, earthwork)," it can be determined that the dump truck is performing an earthwork backfilling operation.

[0043] Step S205: In the reference coordinate system, determine the point cloud data corresponding to the video monitoring data space, and calculate the actual volume data within the preset time interval based on the point cloud data difference between adjacent time nodes.

[0044] Because point cloud data was collected twice, at the beginning and end of a preset time interval, the volume difference between these two adjacent point cloud datasets within the same spatial area can be calculated to accurately determine the change in earthwork volume within the construction site corresponding to the video monitoring area. Due to the high precision of point cloud measurement, this calculation result is used as the actual volume data within the preset time interval.

[0045] Step S206: Using the comparison results between the actual volume data and the estimated volume data, the volume of a single operation of the earthmoving machinery is corrected to obtain the corrected volume process data.

[0046] By utilizing point cloud data, the total number of actual volume changes within a preset time interval is calculated to obtain the actual volume change values. Then, a volume correction coefficient can be calculated to correct the volume error of each mechanical device's single operation action in the video analysis method. This allows for obtaining accurate volume measurements of each mechanical device's single operation action, thereby achieving precise, real-time, and automated monitoring and calculation of construction quantities. This embodiment provides a real-time monitoring method for construction volume. First, a reference coordinate system is established based on primary control points. In subsequent calculations, both initial point cloud data and initial video monitoring data are mapped to this reference coordinate system. This system enables the fusion of point cloud data and video data, providing both accurate measurement data simultaneously within the same construction site. Since the estimated volume data is calculated by analyzing the volume estimation process data of mechanical equipment in the video monitoring data, errors may occur between the estimated volume and the actual volume. Point cloud data has high accuracy in volume calculation; therefore, a correction coefficient is calculated to correct the error in the estimated volume data by combining the actual volume data calculated from the point cloud data with the estimated volume data. This correction coefficient is then used to correct the various estimated volume process data under the estimated volume data, thereby obtaining more accurate estimated volume process data.

[0047] Power 2 In an optional embodiment, step S203 above, establishing a spatial mapping relationship between the initial point cloud data, the initial video monitoring data, and the reference coordinate system to obtain point cloud data and video monitoring data in a unified coordinate system, specifically includes: Step a1: Set up multiple secondary control points within the construction site.

[0048] Secondary control points are set up within the construction site to provide coordinate positioning for the process of mapping point cloud data to the reference coordinate system.

[0049] For example, secondary control points can be located within the construction area, in locations convenient for instrument setup and with good visibility of the slope area to be monitored. The number should be determined based on the size of the work area and the complexity of the terrain, with a high density to ensure that at least 2-3 usable control points can be easily found at any work location. In specific implementations, secondary control points can be formed using semi-permanent markers such as affixing reflective sheets, setting up spherical targets with movable bases, or nailing measuring pins on hardened ground. This facilitates the subsequent identification of secondary control points in point cloud data and video monitoring data, and allows the point cloud data and video monitoring data to be projected onto a reference coordinate system based on the secondary control points.

[0050] Step a2: Determine the coordinate information of each secondary control point in the initial point cloud data within the construction site.

[0051] Secondary control points serve as direct reference points for calibrating video surveillance cameras and setting up 3D scanners. After performing point cloud scanning on a construction site containing secondary control points, point cloud data containing the point cloud information of the secondary control points can be obtained, and the point cloud information of each secondary control point can be identified from it.

[0052] Step a3: Based on the coordinate information of each secondary control point in the initial point cloud data and the coordinate information of each secondary control point in the reference coordinate system, calculate the rigid transformation matrix of the initial point cloud data, thereby determining the spatial mapping relationship between the initial point cloud data and the reference coordinate system.

[0053] After establishing the reference coordinate system, the coordinate data of each secondary control point in the reference coordinate system can be obtained. Based on the position of the secondary control points in the point cloud data and their coordinates in the reference coordinate system, the mapping relationship between the initial point cloud data and the reference coordinate system can be determined. This mapping relationship can be reflected in the positional relationship of the point cloud data relative to the reference coordinate system.

[0054] Step a4: Map the initial point cloud data to the reference coordinate system according to the mapping relationship to obtain the point cloud data.

[0055] After obtaining the mapping relationship between the initial point cloud data and the reference coordinate system, the coordinates of other point cloud data in the initial point cloud data in the reference coordinate system can be obtained based on this mapping relationship, thus obtaining the final point cloud data.

[0056] This embodiment provides a method for real-time monitoring of construction quantities. It first establishes the mapping relationship between secondary control points in the initial point cloud data and a reference coordinate system. Then, based on this mapping relationship, it obtains the relative positions of the initial point cloud data within the reference coordinate system, thereby acquiring the coordinates of each point in the point cloud data. This process is one step in the fusion of point cloud data and video data, and it also ensures the accuracy of the acquired point cloud data positions.

[0057] Power 3 In an optional embodiment, step S204 above, establishing the spatial mapping relationship between the initial point cloud data, the initial video monitoring data, and the reference coordinate system to obtain the point cloud data and video monitoring data in the reference coordinate system, specifically includes: Step b1: Map the coordinate information of the secondary control points in the reference coordinate system to the camera coordinate system to obtain the coordinate information of each secondary control point in the camera coordinate system.

[0058] The process of converting initial video monitoring data into video monitoring data involves transforming three-dimensional coordinates in a reference coordinate system into two-dimensional pixel coordinates in the video monitoring data frame. The camera coordinate system, as an intermediate quantity in this conversion, represents a three-dimensional coordinate system with the lens as its origin and extending forward along the lens's optical axis.

[0059] Step b2: Map the coordinate information of each secondary control point in the camera coordinate system to the initial video monitoring data to obtain the image pixel coordinates of each secondary control point in the initial video monitoring data.

[0060] This process, as the second step in converting the initial video monitoring data into video monitoring data, transforms each secondary control point, which has already been converted from the reference coordinate system to the camera coordinate system, into pixel coordinates in the video monitoring image.

[0061] Step b3: Based on the coordinate information of each secondary control point in the reference coordinate system and the image pixel coordinates of each secondary control point in the initial video monitoring data, calculate the camera extrinsic parameter matrix of the video monitoring data, and combine it with the camera's intrinsic parameter model to determine the spatial mapping relationship between the initial video monitoring data and the reference coordinate system.

[0062] The camera's extrinsic parameters describe how the reference coordinate system is transformed to the camera coordinate system through rotation and translation, while the intrinsic parameters describe how 3D points in the camera coordinate system are projected onto the 2D image pixel coordinate system. It encapsulates the camera's inherent characteristics.

[0063] For example, by identifying the correspondence between the pixel coordinates of secondary control points in the image and the three-dimensional coordinates in the reference coordinate system, the perspective point algorithm (PnP algorithm) can be used to calculate the camera's extrinsic parameter matrix (rotation matrix and translation vector), thereby achieving a precise mapping from the video pixel space to the physical reference space.

[0064] Based on the above two-step transformation calculation, we can obtain the method for transforming each secondary control point from three-dimensional coordinates to two-dimensional coordinates, which serves as a mapping relationship for transforming initial video monitoring data into video monitoring data based on the reference coordinate system.

[0065] Step b4: Map the initial video monitoring data to the reference coordinate system according to the mapping relationship to obtain the video monitoring data.

[0066] Based on the above mapping relationship, any three-dimensional coordinate point within the construction site can be mapped to obtain the corresponding pixel coordinates of the video monitoring screen. This enables the association between any pixel in the video screen and the spatial location of the construction site, thus completing the spatial processing of the video data.

[0067] This embodiment provides a real-time monitoring method for construction quantities. By converting the reference coordinates of secondary control points into camera coordinates, and then converting the camera coordinates into pixel coordinates of the video, a mapping relationship from three-dimensional to two-dimensional coordinates of the construction site is obtained. This mapping relationship can then be used to convert complete initial video detection data into video detection data. This conversion process is also calculated based on the reference coordinate system, combining numerical coordinates with video footage to achieve the fusion of spatial and visual information. Furthermore, since both video monitoring data and point cloud data are mapped from the coordinates of secondary control points to the reference coordinate system, the accuracy of the fusion of video monitoring data and point cloud data can be guaranteed, laying the foundation for subsequent correction of the estimated volume data obtained from the video monitoring data using point cloud data.

[0068] Power 4 In an optional embodiment, step S202 above, which involves setting multiple primary control points and establishing a reference coordinate system for the construction site based on these primary control points, specifically includes: Step c1: Set up multiple primary control points outside the construction site.

[0069] Primary control points are used to establish a reference coordinate system, serving as the absolute reference and long-term stability guarantee for the entire work area. Therefore, their positions need to remain unchanged throughout the entire construction period. Thus, when setting up primary control points, it is necessary to find areas outside the construction influence range where the geological conditions are stable and not prone to settlement or displacement.

[0070] For example, primary control points can be established at stable locations such as bedrock or large permanent structures. At least 3-4 points should be evenly distributed around the perimeter of the work area, ensuring good visibility between them to form a robust control network. As an example, permanent surveying markers such as observation piers with forced centering devices or deeply buried concrete markers can be used.

[0071] Step c2: Take any one of the first-level control points as the origin of the reference coordinate system.

[0072] One of the primary control points is artificially designated as the origin of the current construction site's reference coordinate system.

[0073] For example, select the most stable point with the widest field of view and assign the coordinates (0, 0, 0) as the origin of the reference coordinate system.

[0074] Step c3: Obtain the second-level control points other than the origin, and define the direction from the origin to the second-level control points as the horizontal axis.

[0075] Obtain another first-level control point in the reference coordinate system, other than the first-level control point that serves as the origin, as the second-level control point. Specify the horizontal direction from the origin to the second-level control point as the positive direction of the horizontal axis of the reference coordinate system.

[0076] For example, assuming that the first-level control point serving as the origin is P1 and the second-level control point is P2, the horizontal direction from P1 to P2 is defined as the positive X-axis direction of the coordinate system.

[0077] Step c4: Obtain the third-level control point in addition to the origin and the second-level control point. Define the reference plane of the reference coordinate system based on the plane determined by the origin, the second-level control point and the third-level control point, and determine the vertical axis and the vertical axis according to the reference plane, thereby constructing the reference coordinate system.

[0078] By using three non-collinear physical points, a three-dimensional Cartesian coordinate system can be constructed through vector operations.

[0079] In three-dimensional space, any three non-collinear points can uniquely define a plane. Therefore, by taking the origin, the second control point, and the third control point as three non-collinear points, a reference plane can be determined. After determining the reference plane and the origin, the vertical axis and the coordinate system can then be determined, thereby constructing the reference coordinate system.

[0080] For example, the direction perpendicular to the XOY plane can be determined as the vertical axis (Z-axis) according to the right-hand rule, and the longitudinal axis (Y-axis) perpendicular to both the horizontal and vertical axes can be determined, thereby constructing a unique reference coordinate system for the construction site.

[0081] In another alternative implementation, the reference coordinate system can be established directly using the national geodetic coordinate system (such as CGCS2000) or the engineering independent coordinate system. In this case, step S202 includes: using a GNSS receiver (such as an RTK device) to determine the absolute coordinate values ​​of each first-level control point in the national geodetic coordinate system or the engineering independent coordinate system, and directly defining the coordinate system as the reference coordinate system without manually specifying the origin and axis.

[0082] For example, after establishing a reference coordinate system, the three-dimensional coordinate data of any location within that system can be determined. As an example, using P1 as the station and P2 as the backsight orientation point, a total station is used to measure the precise horizontal distance, vertical angle, and horizontal angle from P1 to all other control points. Through triangulation calculations, the precise three-dimensional coordinates of all other control points relative to this assumed reference are calculated.

[0083] This embodiment provides a method for real-time monitoring of construction quantities, disclosing a method for determining a reference coordinate system by setting up primary control points outside the construction site. By using primary control points to construct the reference coordinate system, the accuracy of the established reference coordinate system can be significantly improved, thereby unifying the spatial calculation scale for subsequent processing of video data and point cloud data.

[0084] In an optional embodiment, the real-time monitoring method for construction quantities provided by the present invention further includes: Step d1: Divide the construction site into multiple construction sections.

[0085] Since the terrain and boundaries of the construction site may not be ideal for video monitoring and data collection, dividing the construction site into sections can enable the calculation and summarization of the volume of the site, thereby achieving the purpose of accurate guidance for construction and measurement.

[0086] For example, when constructing a lock slope, the lock slope can be segmented. As an example, a centerline is established along the slope's direction, and the slope is divided into several continuous, uniquely identified cross-sectional segments in three-dimensional space based on construction station numbers or terrain feature points. ,For example This indicates station numbers from K0+000 to K0+020.

[0087] Step d2 involves dividing the video monitoring data into segmented video monitoring data corresponding to each construction section, analyzing each earthmoving machinery and equipment in each construction section based on the segmented video monitoring data, obtaining multiple estimated volume process data for each construction section, and calculating the estimated volume data for each construction section within a preset time interval based on the estimated volume process data.

[0088] After dividing the construction site into multiple construction sections, subsequent calculations will be performed on a section-by-section basis. Based on the estimated volume data of earthmoving machinery for each construction section, these data are summarized to obtain the estimated volume data for each construction section within a preset time interval. See step S202 for details, which will not be elaborated upon here.

[0089] Step d3: Divide the point cloud data into segmented point cloud data corresponding to each construction section, and calculate the actual volume data of each construction section within a preset time interval based on the segmented point cloud data of two adjacent construction sections.

[0090] Calculate the actual volume data of each construction section within the preset time interval, taking each construction section as a unit. For details, please refer to step S203, which will not be repeated here.

[0091] Step d4: Calculate the volume correction coefficient for each construction section within the preset time interval based on the actual and estimated volume data of each construction section, and correct the estimated volume process data according to the correction coefficient of each construction section to obtain the volume process data.

[0092] Subsequently, the correction coefficients for each construction section within the preset time interval are calculated using actual volume data and estimated volume data, and the process data for each estimated volume are corrected. For details, please refer to step S207, which will not be repeated here.

[0093] This embodiment provides a real-time monitoring method for construction quantities. By collecting and scanning video in segments and correcting the estimated volume process data in each video content, it can accurately guide the construction site, precisely locate the area where the event occurs, monitor the construction progress of each section in real time, and promptly detect problems such as over-excavation and under-excavation. This provides data support for refined construction process management and machinery and equipment scheduling.

[0094] In an optional embodiment, step d3 above involves dividing the point cloud data into segmented point cloud data corresponding to each construction segment, and calculating the actual volume data of each construction segment within a preset time interval based on two consecutive segmented point cloud data of each construction segment. Specifically, dividing the point cloud data into segmented point cloud data corresponding to each construction segment includes: Step e1: Set up multiple secondary control points within each construction section and at the edges of each construction section.

[0095] After the secondary control points are set up, the coordinate information of each secondary control point in the reference coordinate system based on the above operations can be obtained.

[0096] For example, secondary control points can also be set up at the edge of the construction area, such as on piles used to distinguish station segments, to divide different areas.

[0097] Step e2: Based on the position of each secondary control point in the point cloud data and its coordinates in the reference coordinate system, the position of each point in the point cloud data is calibrated to obtain the coordinate data of each point in the point cloud data in the reference coordinate system.

[0098] After scanning the point cloud data, the point cloud data includes the point cloud data of secondary control points. Based on the position information and coordinate information of each secondary control point in the point cloud data, the position information of the overall point cloud data can be determined.

[0099] For example, when collecting point cloud data of a construction site, multiple point cloud data segments can be collected using a multi-station operation method to cover the complete point cloud data of the construction site. Then, the iterative nearest point algorithm can be used to stitch the multiple point cloud data segments into a complete point cloud data of the construction site.

[0100] As an example, the specific execution process of the iterative nearest-point algorithm is as follows: For two point clouds with overlapping regions, an optimal rigid transformation (including a rotation matrix R and a translation vector t) is iteratively calculated such that when this transformation is applied to the source point cloud, its alignment error with the target point cloud in the overlapping region is minimized. The two point clouds with overlapping regions are, respectively, the "source point cloud" P to be moved from one station. s ={p s1 , p s2 , ..., p sN} and a fixed "target point cloud" P from adjacent stations. t ={p t1 , p t2 , ..., p tM After each point cloud acquisition using lidar, at least three pairs of points with the same name are manually selected using point cloud post-processing software for rough registration. Among them, P... s For the source point cloud collection, P t For the target point cloud set, p sN p is the Nth 3D point in the source point cloud. tM Let M be the Mth 3D point in the target point cloud. Based on this initial registration result, the 3D point cloud matching algorithm starts from an initial transformation T. k (When k=0, the value is T0) Begin by repeatedly executing the following steps until the convergence condition is met, T. k This represents the total transformation from the original source point cloud to the current state after the k-th iteration.

[0101] For example, the above calculation process can be divided into: Step 1, find the corresponding point set. For each point after the current transformation T... k Each point p' in the subsequent source point cloud si = R k ×psi + t k In the target point cloud P t Find the nearest neighbor p in Euclidean distance. ti After completing this step, you will obtain a result consisting of (p') si , p ti The set of corresponding point pairs C is composed of ) k ={(p' si , p ti )}, where p si For source point cloud p s The i-th point in R k Let t be the rotation matrix at the k-th iteration. k Let p' be the translation vector at the k-th iteration. si Let p be the origin point. si After the current cumulative transformation t k The temporary location obtained afterwards; Step 2, calculate the optimal transformation. The goal of this step is to find a new transformation (R0). k' , t k' ), to minimize the corresponding point set C k The error function between the points is E(R, t). This invention defines the error function as the sum of squared Euclidean distances between corresponding point pairs, which can be expressed by the formula... The calculation is performed, where R and t represent the rotation matrix and translation vector, respectively. For points in the original source point cloud, for Zhongyu The corresponding target point; Step 3, update the total transformation matrix. The transformation matrix calculated in the previous step (Ri) is then updated. k' , t k' ) and the current total transformation T k Perform composition to update the total transformation matrix: T {k+1} = (R k' , t k' )×T k This means R {k+1} = R k' ×R k And t {k+1} =R k' ×t k +t k' , among which, T k Let T be the cumulative transformation matrix at the beginning of the k-th iteration. {k+1} Let R be the cumulative transformation matrix after the k-th iteration. k' , t k' ) is the cumulative transformation matrix at the beginning of the k-th iteration; Step 4, iterate until convergence. Repeat steps one through three until one or more of the following termination conditions are met: Error change convergence: The change in the error function E between two iterations is less than a preset small threshold ε. E Transformation parameter convergence: The change in the transformation matrix T (e.g., rotation angle and translation distance) is less than a preset small threshold ε. T Reaching the maximum number of iterations: The number of iterations k reaches the preset upper limit N. max This is to prevent infinite loops. When the iteration terminates, the algorithm outputs the final, optimal transformation matrix T. final = T {k+1} Apply this matrix to the original source point cloud P. s This will give you the target point cloud P. t Precisely aligned point cloud Ps aligned = R final ×P s + t final By sequentially stitching together the point clouds from all stations with adjacent point clouds, a single, complete, and high-precision point cloud model is finally formed, where ε E ε is the error convergence threshold. T N is the translation convergence threshold. max T is the preset maximum number of iterations. final Let T be the optimal transformation matrix at the time of algorithm termination. {k+1} Ps is the transformation obtained after the last successful iteration. aligned To align the source point cloud to the target coordinate system, R final For the final rotation matrix, t final This is the final translation vector.

[0102] For example, the process of matching coordinates to point cloud data can be as follows: The precise coordinates of ground control points {P} in a unified reference coordinate system... w1 , P w2 , ..., P wn}, the coordinates of the corresponding control points manually selected by point cloud post-processing software in the local coordinate system of the point cloud {P local1 , P local2 , ..., P localn By establishing connections between multiple pairs of non-collinear corresponding points, the optimal rigid transformation matrix is ​​solved. Through this rigid transformation, the point cloud model can be accurately registered to a unified reference coordinate system, generating a point cloud with absolute coordinates.

[0103] Step e3: Based on the coordinate data of the secondary control points at the edge of each construction section and the coordinate data of each point in the point cloud data in the reference coordinate system, the point cloud data is segmented to obtain the segmented point cloud data corresponding to each construction section.

[0104] After stitching together the complete point cloud data and obtaining the coordinate values ​​of each point cloud information in the reference coordinate system, in order to accurately obtain the point cloud data information in each construction section, the point cloud data is cut according to the coordinate data of the secondary control points deployed on the edge of each construction section, so as to obtain the segmented point cloud data corresponding to each construction section.

[0105] For example, after obtaining the segmented point cloud data corresponding to each construction section, it is necessary to calculate the volume change over a preset time interval using the segmented point cloud data corresponding to each construction section. The actual excavation volume or fill volume of each construction section within this period can be accurately calculated using the triangular mesh differential method or the grid volume method.

[0106] As an example, the specific calculation process of the triangular network differential method can be as follows: Step 1: Clip the point cloud according to the station number segment boundary space. Utilize the 3D spatial boundary of the construction segment to clip the PC. pre and PC post Spatial clipping is performed, retaining only the point cloud within the specified station segment, resulting in PCs. pre (D i ) and PC post (D i ), where D i For the i-th construction pile number segment, PC pre PC is used for preliminary point cloud preparation before construction. post For point cloud formation after construction; Step 2, construct the triangular mesh surface model. This will be applied to the PC... pre (D i ) and PC post (D i These two point cloud sets were loaded into professional point cloud processing software, and the Delaunay triangulation algorithm was applied to generate two continuous, non-overlapping triangular mesh surface models, namely S. pre and S post S pre For the surface of the model in the early stage of construction, S post For the surface of the model in the later stages of construction, point cloud processing software can be Trimble RealWorks; Step 3, calculate the surface differential volume. Let S pre As a reference plane, S is calculated using software. post Compared to S pre The elevation difference. When S post Located in S pre When the elevation difference is negative, the area is considered excavation. When S... post Located in S preWhen the elevation difference is positive, the area is fill. By calculating and integrating the volumes of all the tiny triangular prisms enclosed by these two surfaces, the software can directly obtain the total excavation volume V within this station segment. cut Total fill volume V fill .

[0107] As an example, the process of calculating the actual excavation or fill volume using the grid volume method can be as follows: Step 1: Trim the point cloud according to the station number segment boundaries, similar to Step 1 of the triangulation method, to obtain the PC. pre (D i ) and PC post (D i ); Step 2: Create a standard 2D grid. In station segment D... i Within the XY plane projection area, create a uniform, regular two-dimensional grid (e.g., 0.25 m × 0.25 m). Step 3: Calculate the average elevation of the grid cells, iterating through each grid cell (i, j): from PC pre (D i In the cell, all points whose XY coordinates fall within the cell are selected, and the average Z coordinate of these points is calculated, or inverse distance weighted interpolation is used to obtain the average elevation Z of the previous period's point cloud for that cell. pre (i, j), using the same method, from PC post (D i The average elevation Z of this unit in the current period is calculated using the method described above. post After completing this step, two elevation matrices with the same dimensions as the grid are obtained, where (i, j) are the row and column indices of the grid cells, and PC... pre (D i () represents the portion of the point cloud data from the early stages of construction within the i-th construction segment, PC post (D i Z represents the portion of the point cloud data in the i-th construction segment during the later stages of construction. pre (i, j) represents the average elevation of grid (i, j) during the early stages of construction, Z post (i, j) represents the average elevation of grid (i, j) during the later stages of construction; Step 4: Calculate and sum the volumes cell by cell. Iterate through each cell (i, j) again, calculating the volume change ΔV(i, j): ΔV(i, j) = (Z post (i, j) - Z pre (i, j)) × Cell Area Cell AreaThis is the area of ​​a single grid cell. If ΔV(i, j) < 0, it is included in the total excavation volume V. cut If ΔV(i, j) > 0, then it is included in the total fill volume V. fill Where ΔV(i, j) represents the change in earthwork volume in cell Z post (i, j) represents the average elevation during the later stages of construction, Z pre (i, j) represents the average elevation during the early stages of construction. Cell Area V represents the area of ​​a cell. cut V represents the total excavation volume. fill This represents the total fill volume. The final total cut and fill volumes are obtained by summing the calculation results of all grid cells.

[0108] This embodiment provides a method for real-time monitoring of construction quantities. This solution proposes a method to divide the point cloud data of the entire construction site according to the coordinate data of the secondary control points, thereby obtaining the point cloud data segments of each construction section. By first synchronizing the point cloud data to the reference coordinate system, and then dividing it according to the coordinate data of the secondary control points, the division of point cloud data segments becomes more accurate.

[0109] In an optional embodiment, step d2 above involves dividing the video monitoring data into segmented video monitoring data corresponding to each construction segment, analyzing the earthmoving machinery and equipment in each construction segment based on the segmented video monitoring data to obtain multiple estimated volume process data for each construction segment, and calculating the estimated volume data for each construction segment within a preset time interval based on the estimated volume process data. Specifically, dividing the video monitoring data into segmented video monitoring data corresponding to each construction segment includes: Step f1: Project the secondary control points at the edges of each construction section onto the two-dimensional plane where the video monitoring data is located to obtain the position of the secondary control points in the video monitoring data.

[0110] The video monitoring data needs to cover the secondary control points at the edges of each construction section in order to obtain the location of the secondary control points in the video monitoring data. Based on the secondary control points at the edges, the area of ​​each construction section can be accurately divided.

[0111] Step f2: Based on the position of the secondary control points at the edge of each construction section in the video monitoring data, the video monitoring data is segmented to obtain the segmented video monitoring data corresponding to each construction section.

[0112] Based on the secondary control points at the edges of each construction section, the video detection data can be segmented and distinguished into video detection data for different construction sections.

[0113] For example, obtaining segmented video monitoring data corresponding to each construction section can be achieved by transforming the reference coordinate system into the camera coordinate system; projecting the camera coordinate system onto the normalized image plane; projecting the normalized plane onto the distorted image plane; and finally completing pixel coordinate transformation in four steps, thus projecting the coordinates of the secondary control points at the edge of the construction section onto the real image plane. The implementation steps can be as follows: Step 1, rigid transformation (i.e., from world coordinate system to camera coordinate system). Use the extrinsic parameter matrix [R|t] to transform the world coordinate system P... w Convert to camera coordinates P c Specific formula: P c = R×P w +t. Its input is the world coordinates P of any 3D point. w =[X w ,Y w Z w ] T Output: The coordinates P of this point in the camera coordinate system. c = [X c , Y c Z c ] T , where P w P is a three-dimensional point in the world coordinate system. c It is a 3D point in the camera coordinate system, where R is the rotation matrix and t is the translation vector. T To indicate transpose, this represents a column vector; Step 2, Perspective Projection (Camera Coordinates to Normalized Image Plane). Project the 3D points onto the camera's 2D imaging plane. Project the camera coordinates onto the normalized plane to obtain the normalized coordinates p. n = [x n , y n ] T , where x n = X c / Z c , y_n = Y c / Z c Among them, Z c X is the depth value, representing the distance from the point to the camera's optical center along the optical axis. c Y c p represents the horizontal and vertical coordinates of a point in the camera coordinate system. n Represents the normalized image plane coordinates, x n , y n These are the coordinates of the point on the image; Step 3, distortion correction (normalization plane to distorted image plane). Specific formula: p=f distort (p',D). The distorted pixel coordinates p are input from step two.n = [x n , y n ] T And the distortion coefficients D=(k1, k2, p1, p2, k3). Calculate the mathematical model x for applying radial and tangential distortion correction to p'. dist = x n (1 + k1×r 2 + k2×r 4 + k3×r 6 ) + 2p1×x n ×y n + p2(r 2 + 2 x n2 ), y dist = y n (1 + k1×r 2 + k2×r 4 + k3×r 6 ) + p1(r 2 + 2 y n 2 ) + 2p2×x n ×y n Where r is the distance from the pixel to the principal point, k represents the radial distortion coefficient, p represents the tangential distortion coefficient, D represents the distortion coefficient, and x... corrected With y corrected These are the corrected, normalized coordinates; Step 4, Pixel coordinate transformation: Using the camera intrinsic parameter matrix K (including focal length f) x , f y and principal point c x , c y The distorted coordinates are converted into the final pixel coordinates (u, v): u = f x ×x dist + c x v = f y ×y dist + c y Through the above steps, the secondary control points at the edge of the construction section can be accurately projected into the video image, forming a polygonal area, thereby spatially segmenting the video monitoring data.

[0114] As an example, the intrinsic parameter matrix, extrinsic parameters, and distortion coefficients of a camera can be calculated as follows: Within the shared field of view of the camera and laser scanner, multiple known and distinctive targets (such as checkerboard patterns, spherical targets, ARUCO codes, etc.) are deployed. Using methods such as Zhang Zhengyou's calibration, the intrinsic parameter matrix K (focal length, principal point) and distortion coefficient D of each camera can be accurately calculated. By obtaining the three-dimensional coordinates of the target center, a set {P} is formed.w1 , P w2 , ..., P wn The three-dimensional coordinates can be extracted from the pre-defined point cloud data. Simultaneously, in the camera image, image processing algorithms (such as contour extraction and corner detection) are used to accurately extract the center pixel coordinates of each target with the same name in the image, forming a set {p1, p2, ..., p...}. n}, which are then integrated to form a structure containing multiple 3D-2D point pairs (P w Given a dataset of points {P, p), the camera pose in the reference coordinate system is inversely calculated by solving the PnP problem. w Given a 2D point set {p} and a camera intrinsic parameter matrix K, we use the iterative optimization Levenberg-Marquardt algorithm to find a rotation matrix R and a translation vector t such that the 3D point set {P} is transformed into a 3D point set {p}. w After transformation and projection using R and t, the position of the point {p} on the image is minimized by the reprojection error Σ || p. i - project(K, R, t, P wi Solving for ||², we obtain [R|t], which, as an extrinsic parameter, precisely describes the rigid transformation relationship of the camera coordinate system relative to the reference coordinate system.

[0115] For example, an online self-calibration mechanism can also be introduced to address the issue of minute displacements of the camera mount caused by wind loads, thermal expansion and contraction, etc. After initial calibration, fixed targets are used as stable feature points. The system monitors the pixel coordinates of these feature points in real time. When the system detects an overall drift in the pixel coordinates of these feature points that exceeds a preset threshold, it automatically recalculates and fine-tunes the camera's extrinsic parameter matrix [R|t] using these points, achieving real-time dynamic correction of the camera pose. Simultaneously, addressing the issue of monitoring being susceptible to weather (fog, haze, rain) and lighting conditions, before video analysis, all video frames undergo an image enhancement module, including a dehazing algorithm based on dark channel priors and a low-light enhancement algorithm based on Retinex theory or deep learning, to improve image quality and the robustness of intelligent video recognition.

[0116] This embodiment provides a method for real-time monitoring of construction quantities, which presents a method for projecting the monitoring video data of each construction section from three dimensions to a two-dimensional monitoring plane. The monitoring video data of each construction section is accurately divided, and combined with the point cloud data of each construction section in the above steps, the video data and point cloud data are matched in space.

[0117] This embodiment also provides a real-time monitoring device for construction quantities, which is used to implement the above embodiments and preferred embodiments; details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the device described in the following embodiments is preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0118] This embodiment provides a real-time monitoring device for construction quantities, such as... Figure 3 As shown, it includes: The data acquisition module 301 is used to collect initial video monitoring data and periodically collect initial point cloud data in the construction site in real time within a preset time interval. The coordinate establishment module 302 is used to set multiple primary control points and establish a reference coordinate system for the construction site based on the primary control points; The data fusion module 303 is used to establish the spatial mapping relationship between the initial point cloud data, the initial video monitoring data and the reference coordinate system, so as to obtain the point cloud data and video monitoring data in the reference coordinate system. The volume estimation module 304 is used to identify the operating behavior of earthmoving machinery based on video monitoring data, and to calculate the estimated volume data within a preset time interval based on the characteristics of the operating behavior. The volume calculation module 305 is used to determine the point cloud data corresponding to the video monitoring data space in the reference coordinate system, and to calculate the actual volume data within a preset time interval based on the difference between the point cloud data of adjacent time nodes. The volume correction module 306 is used to correct the volume of earthmoving machinery in a single operation by comparing the actual volume data with the estimated volume data, and to obtain the corrected volume process data.

[0119] The real-time monitoring device for construction quantities provided in this embodiment of the invention can execute the real-time monitoring method for construction quantities provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the various modules and units are the same as in the corresponding embodiments described above, and will not be repeated here.

[0120] Figure 4 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0121] The following is a detailed reference. Figure 4This diagram illustrates a structural schematic suitable for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 401, which can perform various appropriate actions and processes according to a program stored in read-only memory (ROM) 402 or a program loaded from memory 408 into random access memory (RAM) 403. The RAM 403 also stores various programs and data required for the operation of the electronic device. The processor 401, ROM 402, and RAM 403 are interconnected via a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0122] Typically, the following devices can be connected to I / O interface 405: input devices 406 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 407 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 408 including, for example, magnetic tapes, hard disks, etc.; and communication devices 409. Communication device 409 allows electronic devices to communicate wirelessly or wiredly with other devices to exchange data. Although Figure 4 Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0123] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 409, or installed from a memory 408, or installed from a ROM 402. When the computer program is executed by the processor 401, it performs the functions defined in the real-time monitoring method for construction quantities according to embodiments of the present invention.

[0124] Figure 4 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0125] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, the real-time monitoring method for construction quantity shown in the above embodiments is implemented.

[0126] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0127] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and all such modifications and variations fall within the scope defined by the appended claims.

Claims

1. A method for real-time monitoring of construction quantities, characterized in that, The method includes: Within a preset time interval, initial video monitoring data and initial point cloud data are collected in real time at the construction site and periodically. Multiple primary control points are set up, and a reference coordinate system for the construction site is established based on the primary control points; Establish the spatial mapping relationship between the initial point cloud data, the initial video monitoring data and the reference coordinate system to obtain the point cloud data and video monitoring data in the reference coordinate system; Based on the video monitoring data, the operating behavior of earthmoving machinery and equipment is identified, and the estimated volume data within a preset time interval is calculated based on the characteristics of the operating behavior. Within the reference coordinate system, point cloud data corresponding to the video monitoring data space is determined, and the actual volume data within a preset time interval is calculated based on the point cloud data difference between adjacent time nodes. By comparing the actual volume data with the estimated volume data, the volume of a single operation of the earthmoving machinery is corrected to obtain the corrected volume process data.

2. The method according to claim 1, characterized in that, The step of establishing the spatial mapping relationship between the initial point cloud data, the initial video monitoring data, and the reference coordinate system to obtain the point cloud data and video monitoring data in the reference coordinate system includes: Multiple secondary control points were set up within the construction site; Determine the coordinate information of each secondary control point within the construction site in the initial point cloud data; Based on the coordinate information of each secondary control point in the initial point cloud data and the coordinate information of each secondary control point in the reference coordinate system, the rigid transformation matrix of the initial point cloud data is calculated, thereby determining the spatial mapping relationship between the initial point cloud data and the reference coordinate system. The initial point cloud data is mapped to the reference coordinate system according to the mapping relationship to obtain the point cloud data.

3. The method according to claim 2, characterized in that, The step of establishing the spatial mapping relationship between the initial point cloud data, the initial video monitoring data, and the reference coordinate system to obtain the point cloud data and video monitoring data in the reference coordinate system includes: The coordinate information of the secondary control points in the construction site in the reference coordinate system is mapped to the camera coordinate system to obtain the coordinate information of each secondary control point in the camera coordinate system; The coordinate information of each secondary control point in the camera coordinate system is mapped to the initial video monitoring data to obtain the image pixel coordinates of each secondary control point in the initial video monitoring data. Based on the coordinate information of each secondary control point in the reference coordinate system and the image pixel coordinates of each secondary control point in the initial video monitoring data, the camera extrinsic parameter matrix of the video monitoring data is calculated, and combined with the camera intrinsic parameter model, the spatial mapping relationship between the initial video monitoring data and the reference coordinate system is determined. The initial video monitoring data is mapped to the reference coordinate system according to the mapping relationship to obtain the video monitoring data.

4. The method according to claim 1, characterized in that, The process of setting multiple primary control points and establishing a reference coordinate system for the construction site based on these primary control points includes: Multiple primary control points were set up outside the construction site; Take any one of the first-level control points as the origin of the reference coordinate system; Obtain the second-level control points other than the origin, and define the direction from the origin to the second-level control points as the horizontal axis; Obtain the third-level control point in addition to the origin and the second-level control point. Define the reference plane of the reference coordinate system based on the plane determined by the origin, the second-level control point and the third-level control point. Determine the vertical axis and the longitudinal axis according to the reference plane, thereby constructing the reference coordinate system.

5. The method according to claim 4, characterized in that, The method further includes: The construction site is divided into multiple construction sections; The video monitoring data is divided into segmented video monitoring data corresponding to each construction section. Based on the segmented video monitoring data, the earthmoving machinery and equipment of each construction section are analyzed to obtain multiple estimated volume process data of each construction section. Based on the estimated volume process data, the estimated volume data of each construction section within a preset time interval is calculated. The point cloud data is divided into segmented point cloud data corresponding to each construction segment. The actual volume data of each construction segment within a preset time interval is calculated based on the segmented point cloud data of two adjacent construction segments. Based on the actual volume data and the estimated volume data of each construction section, the volume correction coefficient for each construction section within the preset time interval is calculated, and the estimated volume process data is corrected according to the correction coefficient of each construction section to obtain the volume process data.

6. The method according to claim 5, characterized in that, The point cloud data is divided into segmented point cloud data corresponding to each construction section, including: Multiple secondary control points were set up within and at the edges of each construction section. The positions of each point in the point cloud data are calibrated based on the positions of each secondary control point in the point cloud data and their coordinates in the reference coordinate system, so as to obtain the coordinate data of each point in the point cloud data in the reference coordinate system. Based on the coordinate data of the secondary control points at the edge of each construction section and the coordinate data of each point in the point cloud data in the reference coordinate system, the point cloud data is segmented to obtain the segmented point cloud data corresponding to each construction section.

7. The method according to claim 5, characterized in that, The step of dividing the video monitoring data into segmented video monitoring data corresponding to each construction section includes: The secondary control points at the edges of each construction section are projected onto the two-dimensional plane where the video monitoring data is located, thus obtaining the position of the secondary control points in the video monitoring data; The video monitoring data is segmented based on the position of the secondary control points at the edge of each construction section in the video monitoring data to obtain segmented video monitoring data corresponding to each construction section.

8. A real-time monitoring device for construction quantities, characterized in that, The device includes: The data acquisition module is used to collect initial video monitoring data and periodically collect initial point cloud data in real time within a preset time interval. The coordinate establishment module is used to set multiple primary control points and establish a reference coordinate system for the construction site based on the primary control points; The data fusion module is used to establish the spatial mapping relationship between the initial point cloud data, the initial video monitoring data and the reference coordinate system, so as to obtain the point cloud data and video monitoring data in the reference coordinate system. The volume estimation module is used to identify the operating behavior of earthmoving machinery based on the video monitoring data, and to calculate the estimated volume data within a preset time interval based on the operating behavior characteristics. The volume calculation module is used to determine the point cloud data corresponding to the video monitoring data space in the reference coordinate system, and to calculate the actual volume data within a preset time interval based on the difference between the point cloud data of adjacent time nodes. The volume correction module is used to correct the volume of earthmoving machinery in a single operation by comparing the actual volume data with the estimated volume data, and to obtain the corrected volume process data.

9. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform a real-time monitoring method for construction quantities as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute a method for real-time monitoring of construction quantities according to any one of claims 1 to 7.

11. A computer program product, characterized in that, It includes computer instructions for causing a computer to execute a real-time monitoring method for construction quantities according to any one of claims 1 to 7.

Images