Building construction monitoring method and system based on oblique photography

Abstract

The invention discloses a building construction monitoring method and system based on oblique photography, and relates to the technical field of construction monitoring, and the method comprises the steps: obtaining a construction task executed at a preset time point in a target construction region, and obtaining a first target task; obtaining the construction state of the target construction area in the initial state of the first target task to obtain a first target state; obtaining an expected construction state of the target construction area after the first target task is completed to obtain a second target state; the construction progress and the constructed duration of the target construction area are obtained; matching a construction duration prediction model according to a task type corresponding to the first target task to obtain a target prediction model; inputting the construction progress, the constructed duration, the first target state and the second target state into a target prediction model to obtain a second target construction duration; and comparing the second target construction duration with the expected construction duration, and generating first feedback information according to a comparison result so as to judge whether the construction progress of the target construction area is abnormal or not.

Description

Technical Field

[0001] The present application relates to the technical field of construction monitoring, and in particular to a method and system for monitoring construction based on oblique photography. Background Art

[0002] Building construction refers to the construction, reconstruction or expansion of buildings according to the design documents of building projects. Buildings usually include roofs, beams, columns and walls to provide shelter and space for human habitation, work, education and entertainment. Before the start of construction, a construction schedule needs to be formulated according to the ultimate goal of the construction project. During the construction process, the actual construction data collected needs to be analyzed to determine whether the current construction progress meets the requirements of the construction schedule.

[0003] The application number is CN202210384245.3. A construction progress intelligent management method and system for a smart construction site, which determines the actual construction progress status information according to the monitoring video of the construction site, compares the actual construction progress status information with the pre-configured construction progress status information, and if the actual construction progress status information is less than the pre-configured construction progress status information, it is considered that there is an abnormal construction progress at the current construction site, and the degree of abnormal construction progress is determined according to the actual construction progress status information. Although this method can capture the abnormal state of the construction progress at the construction site. However, factors such as differences in the progress evaluation standards of different construction processes and the difficulty of evaluating the construction efficiency of the construction team will increase the difficulty of pre-configuring the construction progress status information, thereby reducing the accuracy of obtaining abnormal states during the construction progress. When the pre-configured construction progress status information exceeds the actual achievable construction progress status information, false alarms will occur during the monitoring of the construction progress, and when the pre-configured construction progress status information is lower than the actual achievable construction progress status information, missed alarms will occur during the monitoring of the construction progress. Summary of the invention

[0004] The purpose of the present invention is to solve the technical problem of how to improve the accuracy of obtaining abnormal construction progress, and to provide a construction monitoring method and system based on oblique photography.

[0005] According to a first aspect of the present invention, the present invention claims a method for monitoring construction based on oblique photography, comprising: Obtaining the construction tasks to be performed in the target construction area at a preset time point to obtain a first target task; Acquire the construction state of the target construction area under the initial state of the first target task to obtain a first target state; Acquire the expected construction state of the target construction area after the first target task is completed according to the construction design document and the construction plan, and obtain a second target state; Acquire the construction progress of the target construction area in the first target task to obtain a first construction progress; Obtaining the construction time of the target construction area in the first target task to obtain a first target construction time; According to the task type corresponding to the first target task, a corresponding construction duration prediction model is matched to obtain a target prediction model; wherein the construction duration prediction model is used to predict the total construction duration required to complete the first target task; Inputting the first construction progress, the first target construction duration, the first target state, and the second target state into the target prediction model to obtain a second target construction duration; The second target construction time is compared with the expected construction time. If the second target construction time is longer than the expected construction time, first feedback information is generated. The first feedback information includes feedback information indicating that there is an abnormality in the construction progress of the target construction area.

[0006] In one embodiment of the present application, the step of obtaining the construction progress of the target construction area in the first target task further includes: Acquire an actual construction image of the target construction area at the preset time point by oblique photography, and establish a current construction model of the target construction area according to the actual construction image to obtain a target construction model; Acquire a first reference construction model corresponding to the first target state; Acquire a second reference construction model corresponding to the second target state; calculating a similarity between the first reference construction model and the second reference construction model to obtain a first similarity; Calculating the similarity between the target construction model and the second reference construction model to obtain a second similarity; The first construction progress is obtained according to the first similarity and the second similarity.

[0007] In one embodiment of the present application, the first construction progress calculation method includes: ; Among them, P 1 represents the first construction progress, s 1 represents the first similarity, s 2 represents the second similarity.

[0008] In one embodiment of the present application, the first similarity and the second similarity are obtained based on elevation information and color similarity, the elevation similarity is used to represent the similarity between the elevation information of the highest points of all positions in the target construction area under different construction conditions, and the color similarity is used to represent the similarity between point cloud data in the construction model corresponding to the target construction area under different construction conditions, and the point cloud data includes color data corresponding to the spatial coordinates corresponding to the construction model.

[0009] In one embodiment of the present application, the elevation information includes contour lines.

[0010] In one embodiment of the present application, the method for calculating the elevation similarity includes: Acquire contour images of the construction models to be compared respectively, and obtain a first contour image and a second contour image; Dividing the first contour line image according to the heights corresponding to the contour lines to obtain a first contour line sub-image set, and dividing the second contour line image according to the heights corresponding to the contour lines to obtain a second contour line sub-image set; Obtain a closed region of contour lines in each first contour line sub-image to obtain a corresponding first closed region; Obtain a closed region of contour lines in each second contour line sub-image to obtain a corresponding second closed region; Matching the first closed area and the second closed area according to the height of the contour line, and if the match is successful, calculating the intersection-over-union ratio of the first closed area and the second closed area to obtain the contour line similarity of the corresponding height; The mean of the contour similarities corresponding to all heights is calculated to obtain the elevation similarity.

[0011] In an embodiment of the present application, the number of the target construction areas is not less than 2, and if the second target construction duration is not greater than the corresponding expected construction duration, the step of comparing the second target construction duration with the expected construction duration further includes: Calculate the average of each of the second target construction durations and the corresponding first target construction duration to obtain a third target construction duration; calculate the average duration of all the third target construction durations; respectively calculate the distance between each of the third target construction durations and the average duration to obtain a corresponding duration difference; respectively compare each of the duration differences with a first preset threshold, and if there is a duration difference greater than the first preset threshold, generate second feedback information, and the second feedback information includes a target construction area for indicating that there is an optimized construction arrangement.

[0012] In one embodiment of the present application, the process types include foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, main steel bar binding, main formwork installation, concrete pouring, door and window installation and outdoor decoration.

[0013] In one embodiment of the present application, when the process type corresponding to the first target task belongs to one of foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, main steel bar binding, main formwork installation and concrete pouring, the weight of the elevation similarity is greater than the weight of the color similarity. When the process type corresponding to the first target task belongs to one of door and window installation and outdoor decoration, the weight of the elevation similarity is less than the weight of the color similarity.

[0014] According to a second aspect of the present invention, the present invention claims protection for a construction monitoring system based on oblique photography, comprising: A first acquisition module, the first acquisition module is used to acquire the construction tasks to be performed in the target construction area at a preset time point to obtain a first target task; A second acquisition module, the second acquisition module is used to acquire the construction state of the target construction area under the initial state of the first target task to obtain a first target state; A third acquisition module, the third acquisition module is used to acquire the expected construction state of the target construction area after the first target task is completed according to the construction design document and the construction plan, and obtain a second target state; A fourth acquisition module, the fourth acquisition module is used to acquire the construction progress of the target construction area in the first target task to obtain a first construction progress; A fifth acquisition module, the fifth acquisition module is used to acquire the construction time of the target construction area during the first target task, and obtain a first target construction time; A first query module, the first query module is used to match the corresponding construction duration prediction model according to the task type corresponding to the first target task to obtain a target prediction model; wherein the construction duration prediction model is used to predict the total construction duration required to complete the first target task; A first processing module, the first processing module is used to input the first construction progress, the first target construction duration, the first target state and the second target state into the target prediction model to obtain a second target construction duration; The first judgment module is used to compare the second target construction time with the expected construction time. If the second target construction time is longer than the expected construction time, a first feedback information is generated. The first feedback information includes feedback information indicating that there is an abnormality in the construction progress of the target construction area.

[0015] In an embodiment of the present application, the fourth acquisition module further includes: A first acquisition submodule, the first acquisition submodule is used to acquire an actual construction image of the target construction area at the preset time point through oblique photography, and establish a current construction model of the target construction area according to the actual construction image to obtain a target construction model; a second acquisition submodule, the second acquisition submodule being used to acquire a first reference construction model corresponding to the first target state; a third acquisition submodule, the third acquisition submodule being used to acquire a second reference construction model corresponding to the second target state; A first processing submodule, the first processing submodule is used to calculate the similarity between the first reference construction model and the second reference construction model to obtain a first similarity; A second processing submodule, the second processing submodule is used to calculate the similarity between the target construction model and the second reference construction model to obtain a second similarity; A third processing submodule is used to obtain the first construction progress according to the first similarity and the second similarity.

[0016] In one embodiment of the present application, the first construction progress calculation method includes: ; Among them, P 1 represents the first construction progress, s 1 represents the first similarity, s 2 represents the second similarity.

[0017] In one embodiment of the present application, the first similarity and the second similarity are obtained based on elevation information and color similarity, the elevation similarity is used to represent the similarity between the elevation information of the highest points of all positions in the target construction area under different construction conditions, and the color similarity is used to represent the similarity between point cloud data in the construction model corresponding to the target construction area under different construction conditions, and the point cloud data includes color data corresponding to the spatial coordinates corresponding to the construction model.

[0018] In one embodiment of the present application, the elevation information includes contour lines.

[0019] In one embodiment of the present application, the method for calculating the elevation similarity includes: Acquire contour images of the construction models to be compared respectively, and obtain a first contour image and a second contour image; Dividing the first contour line image according to the heights corresponding to the contour lines to obtain a first contour line sub-image set, and dividing the second contour line image according to the heights corresponding to the contour lines to obtain a second contour line sub-image set; Obtain a closed region of contour lines in each first contour line sub-image to obtain a corresponding first closed region; Obtain a closed region of contour lines in each second contour line sub-image to obtain a corresponding second closed region; Matching the first closed area and the second closed area according to the height of the contour line, and if the match is successful, calculating the intersection-over-union ratio of the first closed area and the second closed area to obtain the contour line similarity of the corresponding height; The mean of the contour similarities corresponding to all heights is calculated to obtain the elevation similarity.

[0020] In an embodiment of the present application, the number of the target construction areas is not less than 2, and if the second target construction duration is not greater than the corresponding expected construction duration, the step of comparing the second target construction duration with the expected construction duration further includes: Calculate the average of each of the second target construction durations and the corresponding first target construction duration to obtain a third target construction duration; calculate the average duration of all the third target construction durations; respectively calculate the distance between each of the third target construction durations and the average duration to obtain a corresponding duration difference; respectively compare each of the duration differences with a first preset threshold, and if there is a duration difference greater than the first preset threshold, generate second feedback information, and the second feedback information includes a target construction area for indicating that there is an optimized construction arrangement.

[0021] In one embodiment of the present application, the process types include foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, main steel bar binding, main formwork installation, concrete pouring, door and window installation and outdoor decoration.

[0022] In one embodiment of the present application, when the process type corresponding to the first target task belongs to one of foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, main steel bar binding, main formwork installation and concrete pouring, the weight of the elevation similarity is greater than the weight of the color similarity. When the process type corresponding to the first target task belongs to one of door and window installation and outdoor decoration, the weight of the elevation similarity is less than the weight of the color similarity.

[0023] This application has the following beneficial effects: 1. When the second target construction time is longer than the expected construction time, it means that the probability of completing the first target task within the expected construction time according to the current construction arrangement is small, that is, there is an abnormality in the construction progress of the target construction area. When the second target construction time is not longer than the expected construction time, it means that the probability of completing the first target task within the expected construction time according to the current construction arrangement is large, that is, there is no abnormality in the construction progress of the target construction area, so as to judge whether there is an abnormality in the construction progress of the target construction area according to the prediction results, thereby reducing the probability of false alarm or missed alarm due to unreasonable manual setting of the construction progress threshold.

[0024] 2. The first similarity is used to evaluate the total construction volume corresponding to the first target task, that is, the first target task requires the construction team to change the similarity between the construction status of the target construction area and the second target construction status from the first similarity to 100%, and the second similarity is used to evaluate the construction volume completed by the construction team. The construction progress of the construction team is obtained according to the ratio of the construction volume completed by the construction team in the first target task to the total construction volume corresponding to the first target task, thereby realizing the monitoring of the construction progress of the target construction area and improving the objectivity of the construction progress evaluation.

[0025] 3. In actual construction scenarios, different construction processes have different degrees of influence on the elevation information and color information of building construction. For example, for construction processes such as foundation pit excavation and concrete pouring, the elevation information of the building before construction and the elevation information of the building after construction are quite different. However, for construction processes such as door and window installation and outdoor decoration, the elevation information of the building before construction and the elevation information of the building after construction are relatively small, but the building point cloud data containing color information before construction and the building point cloud data containing color information after construction are quite different. The model similarity is calculated based on the elevation similarity and color similarity to adapt to the construction progress evaluation of different construction processes.

[0026] 4. For special-shaped buildings, irregular shapes such as curves, arcs, tilts or twists are usually used to give the buildings a unique appearance and structure, which makes it difficult to evaluate the construction progress of special-shaped buildings. By establishing a target construction model of the target construction area, judging the construction progress of the target construction area according to the elevation information of the highest point corresponding to each position in the target construction area can effectively evaluate the construction progress of special-shaped buildings.

[0027] 5. For large-scale construction projects, the construction area is large, and the calculation of the elevation information corresponding to the highest point of each location in the construction area requires a lot of calculation. By comparing the similarity of contour lines in different states, the amount of calculation of the system can be reduced.

[0028] 6. Calculate the average duration required for construction of different flow construction sections, and compare the distance between the corresponding third target construction duration and the average duration. When the distance between the third target construction duration and the average duration is greater than the first preset threshold, it means that the construction rhythm of the flow construction section is significantly different from that of other flow construction sections, and the total construction volume and / or construction arrangement of the flow construction section or other flow construction sections can be optimized and adjusted. If the value of the first preset threshold is 0, when the second feedback information is generated, it means that the construction rhythm of the flow construction section is different from that of other flow construction sections, so as to realize the monitoring of the construction status of fixed-rhythm flow construction. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present disclosure and, together with the description, serve to explain the principles of the present disclosure.

[0030] Figure 1 This is a flow chart of a construction monitoring method based on oblique photography according to an embodiment of the present application; Figure 2 This is a flow chart of a method for calculating a first similarity involved in an embodiment of the present application; Figure 3 A flowchart of a construction monitoring method based on oblique photography according to another embodiment of the present application; Figure 4 A structural diagram of a construction monitoring system based on oblique photography according to an embodiment of the present application Figure 5 This is a schematic diagram of the structure of an electronic device involved in an embodiment of the present application. DETAILED DESCRIPTION

[0031] The present invention provides a method and system for monitoring construction based on oblique photography. In order to make the above-mentioned purposes, features and advantages of the present application more obvious and understandable, the technical solutions in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all embodiments. The components of the embodiments of the present application described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, with reference to the terms "one embodiment", "some embodiments", "implementation method", "embodiment", "illustrative embodiment", "example", "specific example" or "some examples", the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the present application for protection, but only indicates that the specific features, structures or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. Moreover, the specific features, structures or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without making creative work belong to the scope of protection of the present application.

[0032] It should be noted that similar reference numerals and letters represent similar items in the following figures, so once an item is defined in one figure, it does not need to be further defined and explained in the subsequent figures. At the same time, in the description of this application, the terms "first", "second" and other relational terms are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations.

[0033] According to a first aspect of the present invention, the present invention claims a method for monitoring construction based on oblique photography, referring to the attached Figure 1 As shown, including: S1: Obtain the construction tasks to be performed in the target construction area at a preset time point to obtain a first target task.

[0034] It should be noted that the number of the target construction areas can be one or more. For construction projects of large-scale building complexes, the construction area is usually divided into multiple construction sub-areas, and construction is carried out in multiple construction sub-areas at the same time. The number of the target construction areas is set according to the number of construction sub-areas, so as to monitor and capture abnormal construction progress in different construction sub-areas at the same time.

[0035] It should be noted that the construction tasks include process types and specific construction contents, but they are not limited to these. The process types are used to indicate construction process types, such as foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, ground engineering, main steel bar binding, main formwork installation, concrete pouring, door and window installation, and outdoor decoration, but they are not limited to these.

[0036] S2: Obtain the construction status of the target construction area in the initial state of the first target task to obtain the first target state; obtain the expected construction status of the target construction area after the first target task is completed according to the construction design document and the construction plan to obtain the second target state. The construction design document includes construction drawings, etc., but it is not limited to this. The construction plan includes construction process, construction method and construction schedule, etc., but it is not limited to this.

[0037] It should be noted that the construction status is information used to describe the characteristics of the construction area. The first target status can be obtained based on the actual construction status of the construction site after the previous construction task is completed and before the first target task begins, or it can be obtained based on the expected construction status corresponding to the previous construction task obtained from the construction design document and the construction plan.

[0038] S3: Obtain the construction progress of the target construction area in the first target task to obtain a first construction progress.

[0039] It should be noted that the construction progress can be obtained by manually judging the construction information at the construction site, or by analyzing the construction progress through establishing a BIM model.

[0040] In this embodiment, step S3 also includes the following sub-steps: S31, obtaining the actual construction image of the target construction area at the preset time point through oblique photography, and establishing the current construction model of the target construction area according to the actual construction image to obtain the target construction model. The actual construction image can be processed by three-dimensional modeling software such as smart 3D to obtain the target construction model. S32, obtaining the first reference construction model corresponding to the first target state. If the first target state is the actual construction state before the start of the target construction task, the corresponding first reference construction model can be established according to oblique photography; if the first target state is the expected construction state corresponding to the previous construction task, the expected construction model corresponding to the previous construction task can be constructed according to the construction design file and the construction plan to obtain the first reference construction model. Obtain the second reference construction model corresponding to the second target state. The expected construction model corresponding to the target construction task can be constructed according to the construction design file and the construction plan to obtain the second reference construction model. S33, calculating the similarity between the first reference construction model and the second reference construction model to obtain the first similarity. S34, calculating the similarity between the target construction model and the second reference construction model to obtain the second similarity. S35. Obtain the first construction progress according to a ratio of the first similarity to the second similarity.

[0041] It should be noted that in step S31, each drone is equipped with multiple image acquisition devices at the same time, and images of the target construction area are acquired from different angles at the same time. Image acquisition angles include vertical downward and tilt angles, and the tilt angles include angles of 30 degrees, 45 degrees and / or 60 degrees with the vertical downward direction. After planning the flight parameters of the drone, the drone performs the aerial survey task according to the flight parameters to acquire the actual construction image of the target construction area. Among them, the flight parameters include route, flight altitude, heading overlap rate, lateral overlap rate, flight speed and camera exposure, etc., of course, they are not limited to this. The actual construction image acquisition task can be acquired by one drone, or it can be completed by multiple drones in collaboration, and this application does not further limit the number of drones.

[0042] It should be noted that, refer to the attached Figure 2As shown, in step S33 and step S34, the neural network model can be used to extract feature vectors of the first reference construction model, the second participating construction model and the target construction model respectively. The first reference construction model, the second participating construction model and the target construction model can be converted into point cloud data respectively, and the neural network model extracts feature vectors from the corresponding point cloud data to obtain feature vectors of the corresponding models. The first similarity is obtained by calculating the similarity between the feature vector of the first reference construction model and the feature vector of the second reference construction model. The second similarity is obtained by calculating the similarity between the feature vector of the target construction model and the feature vector of the second reference construction model. Among them, the point cloud data includes the position information and corresponding color data of each point in the construction model. The similarity can be selected as cosine similarity.

[0043] It should be noted that the first similarity is used to evaluate the total construction volume corresponding to the first target task, that is, the first target task requires the construction team to change the similarity between the construction status of the target construction area and the second target construction status from the first similarity to 100%, and the second similarity is used to evaluate the construction volume completed by the construction team. The construction progress of the construction team is obtained based on the ratio of the construction volume completed by the construction team in the first target task to the total construction volume corresponding to the first target task.

[0044] In this embodiment, refer to the attached Figure 2 As shown, step S33 also includes: S331, obtaining the elevation information of the highest point corresponding to all positions in the target construction area in the initial state according to the first reference construction model, and obtaining the first reference elevation information. S332, obtaining the expected elevation information of the highest point corresponding to all positions in the target construction area according to the second reference construction model, and obtaining the second reference elevation information. S333, obtaining the first similarity according to the similarity between the first reference elevation information and the second reference elevation information. Step S34 also includes: S341, obtaining the elevation information of the highest point corresponding to all positions in the target construction area at the preset time point according to the target construction model, and obtaining the target elevation information. S342, obtaining the second similarity according to the similarity between the target elevation information and the second reference elevation information.

[0045] It should be noted that weights can be set for elevation information and color information according to their importance, and the elevation similarity and point cloud similarity are linearly added in a weighted manner to obtain the corresponding similarity. The first similarity calculation method includes: ; Among them, ω 1The weight representing the elevation similarity between the elevation information of the first reference construction model and the elevation information of the second construction model, s 1，1 represents the elevation similarity between the elevation information of the first reference construction model and the elevation information of the second reference construction model, ω 2 The weight representing the color similarity between the point cloud data of the first reference construction model and the point cloud data of the second reference construction model, s 1，2 The color similarity between the point cloud data of the first reference construction model and the point cloud data of the second reference construction model is represented. The calculation method of the second similarity is similar to the calculation method of the first similarity, and will not be described in detail here.

[0046] It should be noted that when the process type corresponding to the first target task belongs to one of foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, main steel bar binding, main formwork installation and concrete pouring, the weight of the elevation similarity is greater than the weight of the color similarity. When the process type corresponding to the first target task belongs to one of door and window installation and outdoor decoration, the weight of the elevation similarity is less than the weight of the color similarity.

[0047] It should be noted that in actual construction scenarios, different construction processes have different degrees of influence on the elevation information and color information of building construction. For example, for construction processes such as foundation pit excavation and concrete pouring, the elevation information of the building before construction and the elevation information of the building after construction are quite different, but for construction processes such as door and window installation and outdoor decoration, the elevation information of the building before construction and the elevation information of the building after construction are relatively small, but the building point cloud data containing color information before construction and the building point cloud data containing color information after construction are quite different. The model similarity is calculated based on the elevation similarity and color similarity to adapt to the construction progress evaluation of different construction processes. At the same time, for special-shaped buildings, irregular forms such as curves, arcs, tilts or twists are usually used to give the building a unique appearance and structure, which makes it difficult to evaluate the construction progress of special-shaped buildings. According to the establishment of the target construction model of the target construction area, judging the construction progress of the target construction area according to the elevation information of the highest point corresponding to each position in the target construction area can effectively evaluate the construction progress of special-shaped buildings.

[0048] In this embodiment, in step S35, the first construction progress P 1 The calculation methods include: ; Among them, s 1 represents the first similarity, s 2 represents the second similarity.

[0049] It should be noted that the difference between the first reference construction model and the second reference construction model is used to measure the amount of construction tasks in the target construction area. When the similarity between the target construction model and the second reference construction model is 100%, the value of the first construction progress is 100%, indicating that the first target task in the target construction area has been completed. When the similarity between the target construction model and the second reference construction model is equal to the similarity between the first reference construction model and the second reference construction model, the value of the first construction progress is 0%, that is, the first target task has not yet started, thereby realizing the monitoring of the construction progress of the target construction area and improving the objectivity of the construction progress evaluation.

[0050] S4: Obtain the construction time of the target construction area in the first target task to obtain a first target construction time.

[0051] S5: Matching a corresponding construction duration prediction model according to the process type corresponding to the first target task to obtain a target prediction model; wherein the target prediction model is used to predict the total construction duration required to complete the first target task.

[0052] It should be noted that the construction duration prediction model can be constructed based on a neural network model and a fitting model. The neural network model is used to extract feature vectors of the first target state, the second target state, the first construction progress, and the first target construction duration corresponding to the target construction area. The fitting model is used to fit the total construction duration based on the extracted feature vectors.

[0053] S6: Input the first construction progress, the first target construction duration, the first target state, and the second target state into the target prediction model to obtain a second target construction duration.

[0054] S7: Compare the second target construction time with the expected construction time, and if the second target construction time is longer than the expected construction time, generate first feedback information, the first feedback information including feedback information indicating that the construction progress of the target construction area is abnormal. The expected construction time can be obtained according to the construction plan.

[0055] It should be noted that the difference between the first target state and the second target state is used to evaluate the total construction volume corresponding to the first target task, the first construction progress is used to evaluate the construction volume completed by the construction team, and the first target construction duration is used to indicate the time taken by the construction team to complete the current construction volume. The target prediction model determines the time required to complete the total construction volume according to the total construction volume, the currently completed construction volume, and the time taken, that is, the second target construction duration is obtained, and the first feedback information is generated according to the comparison result between the second target construction duration and the expected construction duration. When the second target construction duration is greater than the expected construction duration, it indicates that the probability of completing the first target task within the expected construction duration according to the current construction arrangement is small, that is, there is an abnormality in the construction progress of the target construction area. When the second target construction duration is not greater than the expected construction duration, it indicates that the probability of completing the first target task within the expected construction duration according to the current construction arrangement is large, that is, there is no abnormality in the construction progress of the target construction area, so as to realize the judgment of whether there is an abnormality in the construction progress of the target construction area according to the prediction result, and reduce the probability of false alarm or missed alarm due to the unreasonable artificial setting of the construction progress threshold.

[0056] In a feasible embodiment, the elevation information includes contour lines. The first reference construction model is converted into a contour image of the target construction area in the first target state to obtain a first reference contour image. The second reference construction model is converted into a contour image of the target construction area in the first target state to obtain a second reference contour image. The elevation similarity between the first reference construction model and the second reference construction model is obtained based on the similarity between the first reference contour image and the second reference contour image. The target construction model is converted into a contour image of the target construction area at the preset time point to obtain a target contour image. The elevation similarity between the target construction model and the second reference construction model is obtained based on the similarity between the target contour image and the second reference contour image.

[0057] It should be noted that after the actual construction image is imported into smart 3D, the air triangulation parameters are set. The air triangulation check is performed according to the set air triangulation parameters. When the air triangulation check is passed, the modeling parameters are set according to the effective coverage range of the actual construction image. The modeling parameters include the modeling range and the coordinate system. The actual construction image is reconstructed according to the modeling parameters to obtain the target construction model, which is composed of point cloud data. The target construction model output by the smart 3D software is imported into the ArcMap software to obtain the LAS data set, and the LAS data set is converted into a raster file. The raster file is converted into a contour image, i.e., the contour image, by the Spatial Analyst tool built into the ArcMap software. Among them, the contour line spacing is preset manually. By adding fields in the contour attribute table, the height corresponding to each contour line in the contour image is matched with the contour line one by one using the field calculator, so as to obtain the corresponding target contour image. The acquisition method of the first contour image and the second contour image is similar to the method, and will not be described in detail here.

[0058] It should be noted that when calculating the elevation similarity between the first reference construction model and the second reference construction model, the first reference contour image can be used as the first contour image, and the second reference contour image can be used as the second contour image. The first contour image is divided according to the heights corresponding to the contours to obtain a first contour sub-image set. The second contour image is divided according to the heights corresponding to the contours to obtain a second contour sub-image set. The closed area of ​​the contours in each first contour sub-image is obtained to obtain the corresponding first closed area. The closed area of ​​the contours in each second contour sub-image is obtained to obtain the corresponding second closed area. The first closed area and the second closed area are matched according to the heights of the contours. If the match is successful, that is, the height of the contour corresponding to the first closed area is the same as the height of the contour corresponding to the second closed area, the intersection-over-union ratio of the first closed area and the second closed area is calculated to obtain the contour similarity of the corresponding height. If the match fails, the contour similarity of the corresponding height is 0. The mean of the contour similarities corresponding to all heights is calculated to obtain the elevation similarity between the first reference construction model and the second reference construction model. The elevation similarity between the target construction model and the second reference construction model is similar to the above method and will not be described in detail here.

[0059] It should be noted that if the similarity between the contour image of the target construction model and the contour image of the second reference construction model is closer to the similarity between the contour image of the first reference construction model and the contour image of the second reference construction model, it means that the completion amount of the first target task is closer to the expected total construction amount, and the construction progress is closer to 100%. For example, in the process of earth excavation, the closer the similarity between the contour lines of the area requiring earth excavation and the expected contour line distribution after the earth excavation is successful is to 100%, the closer the construction progress of the earth excavation is to 100%. For large-scale construction projects, due to the large scope of the construction area, the amount of calculation required to calculate the elevation information corresponding to the highest point of each position in the construction area is large. By comparing the similarity of contour lines in different states, the amount of calculation of the system can be reduced.

[0060] In a possible implementation, refer to the attached Figure 3 As shown, the number of the target construction areas is not less than 2. If the second target construction duration is not greater than the corresponding expected construction duration, step S7 also includes: S71. Calculate the average of each of the second target construction durations and the corresponding first target construction duration to obtain a third target construction duration. The third target construction duration is used to indicate the duration required for construction of the target construction area corresponding to the first target task from the preset time point. S72. Calculate the average duration of all the third target construction durations. S73. Calculate the distance between each of the third target construction durations and the average duration to obtain the corresponding duration difference. S74. Compare each of the duration differences with the first preset threshold value. If there is a duration difference greater than the first preset threshold value, generate second feedback information. If there is a duration difference not greater than the first preset threshold value, do not generate second feedback information.

[0061] It should be noted that the first preset threshold may be obtained by artificially preset, for example, the value of the first preset threshold is 0. The second feedback information includes a target construction area for indicating that there is an optimized construction arrangement, but it is certainly not limited thereto.

[0062] It should be noted that the average duration required for construction of different flow construction sections is calculated, and the distance between the corresponding third target construction duration and the average duration is compared. When the distance between the third target construction duration and the average duration is greater than the first preset threshold, it means that the construction rhythm of the flow construction section is significantly different from the construction rhythm of other flow construction sections, and the total construction volume and / or construction arrangement of the flow construction section or other flow construction sections can be optimized and adjusted. If the value of the first preset threshold is 0, when the second feedback information is generated, it means that the construction rhythm of the flow construction section is different from the construction rhythm of other flow construction sections, so as to realize the monitoring of the construction status of fixed-beat flow construction.

[0063] According to a second aspect of the present invention, the present invention claims a construction monitoring system based on oblique photography, referring to the attached Figure 4 As shown, including: A first acquisition module, the first acquisition module is used to acquire the construction tasks to be performed in the target construction area at a preset time point to obtain a first target task; A second acquisition module, the second acquisition module is used to acquire the construction state of the target construction area under the initial state of the first target task to obtain a first target state; A third acquisition module, the third acquisition module is used to acquire the expected construction state of the target construction area after the first target task is completed according to the construction design document and the construction plan, and obtain a second target state; A fourth acquisition module, the fourth acquisition module is used to acquire the construction progress of the target construction area in the first target task to obtain a first construction progress; A fifth acquisition module, the fifth acquisition module is used to acquire the construction time of the target construction area during the first target task, and obtain a first target construction time; A first query module, the first query module is used to match the corresponding construction duration prediction model according to the task type corresponding to the first target task to obtain a target prediction model; wherein the construction duration prediction model is used to predict the total construction duration required to complete the first target task; A first processing module, the first processing module is used to input the first construction progress, the first target construction duration, the first target state and the second target state into the target prediction model to obtain a second target construction duration; The first judgment module is used to compare the second target construction time with the expected construction time. If the second target construction time is longer than the expected construction time, a first feedback information is generated. The first feedback information includes feedback information indicating that there is an abnormality in the construction progress of the target construction area.

[0064] In a feasible implementation manner, the fourth acquisition module further includes: A first acquisition submodule, the first acquisition submodule is used to acquire an actual construction image of the target construction area at the preset time point through oblique photography, and establish a current construction model of the target construction area according to the actual construction image to obtain a target construction model; a second acquisition submodule, the second acquisition submodule being used to acquire a first reference construction model corresponding to the first target state; a third acquisition submodule, the third acquisition submodule being used to acquire a second reference construction model corresponding to the second target state; A first processing submodule, the first processing submodule is used to calculate the similarity between the first reference construction model and the second reference construction model to obtain a first similarity; A second processing submodule, the second processing submodule is used to calculate the similarity between the target construction model and the second reference construction model to obtain a second similarity; A third processing submodule is used to obtain the first construction progress according to the first similarity and the second similarity.

[0065] In a feasible implementation manner, the first construction progress calculation method includes: ; Among them, P 1 represents the first construction progress, s 1 represents the first similarity, s 2 represents the second similarity.

[0066] In a feasible implementation, the first similarity and the second similarity are obtained based on elevation information and color similarity, the elevation similarity is used to represent the similarity between the elevation information of the highest points of all positions in the target construction area under different construction conditions, and the color similarity is used to represent the similarity between point cloud data in the construction model corresponding to the target construction area under different construction conditions, and the point cloud data includes color data corresponding to the spatial coordinates corresponding to the construction model.

[0067] In a feasible implementation manner, the elevation information includes contour lines.

[0068] In a feasible implementation, the method for calculating the elevation similarity includes: Acquire contour images of the construction models to be compared respectively, and obtain a first contour image and a second contour image; Dividing the first contour line image according to the heights corresponding to the contour lines to obtain a first contour line sub-image set, and dividing the second contour line image according to the heights corresponding to the contour lines to obtain a second contour line sub-image set; Obtain a closed region of contour lines in each first contour line sub-image to obtain a corresponding first closed region; Obtain a closed region of contour lines in each second contour line sub-image to obtain a corresponding second closed region; Matching the first closed area and the second closed area according to the height of the contour line, and if the match is successful, calculating the intersection-over-union ratio of the first closed area and the second closed area to obtain the contour line similarity of the corresponding height; The mean of the contour similarities corresponding to all heights is calculated to obtain the elevation similarity.

[0069] In a feasible implementation manner, the number of the target construction areas is not less than 2, and if the second target construction duration is not greater than the corresponding expected construction duration, the step of comparing the second target construction duration with the expected construction duration further includes: Calculate the average of each of the second target construction durations and the corresponding first target construction duration to obtain a third target construction duration; calculate the average duration of all the third target construction durations; respectively calculate the distance between each of the third target construction durations and the average duration to obtain a corresponding duration difference; respectively compare each of the duration differences with a first preset threshold, and if there is a duration difference greater than the first preset threshold, generate second feedback information, and the second feedback information includes a target construction area for indicating that there is an optimized construction arrangement.

[0070] In a feasible implementation manner, the process types include foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, main steel bar binding, main formwork installation, concrete pouring, door and window installation and outdoor decoration.

[0071] In a feasible implementation, when the process type corresponding to the first target task belongs to one of foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, main steel bar binding, main formwork installation and concrete pouring, the weight of the elevation similarity is greater than the weight of the color similarity. When the process type corresponding to the first target task belongs to one of door and window installation and outdoor decoration, the weight of the elevation similarity is less than the weight of the color similarity.

[0072] Refer to the attached Figure 5As shown, an embodiment of the present application provides an electronic device, including: a processor and a memory, the processor and the memory are interconnected and communicate with each other through a communication bus and / or other forms of connection mechanisms (not shown), the memory stores a computer program executable by the processor, and when the computing device is running, the processor executes the computer program to execute the system in any optional implementation of the above embodiments.

[0073] The embodiment of the present application provides a storage medium, and when the computer program is executed by the processor, the system in any optional implementation of the above embodiment is executed. The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic storage, flash memory, disk or optical disk.

[0074] In the embodiments provided in the present application, it should be understood that the disclosed system can be implemented in other ways. The system embodiments described above are merely schematic. For example, the division of the modules is only a logical function division, and can be implemented in another way. For example, multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some communication interface, system or unit, which can be electrical, mechanical or other forms.

[0075] In addition, the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0076] Furthermore, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.

[0077] Flowcharts are used herein to illustrate the steps of the method of the embodiments of the present disclosure. It should be understood that the preceding or following steps are not necessarily performed precisely in order. On the contrary, various steps may be evaluated in reverse order or simultaneously. At the same time, other operations may also be added to these processes.

[0078] Unless otherwise defined, all terms used herein have the same meaning as commonly understood by those of ordinary skill in the art to which the present disclosure belongs. It should also be understood that terms such as those defined in common dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology, and should not be interpreted in an idealized or highly formal sense, unless explicitly defined as such herein.

[0079] The above is a detailed introduction to a construction monitoring method and system based on oblique photography. This article uses specific examples to illustrate the principles and implementation methods of this application. The description of the above embodiments is only an embodiment of this application, which is only used to help understand the construction monitoring method and system based on oblique photography of this application, and is not used to limit the scope of protection of this application. At the same time, for those skilled in the art, this application can have various changes and variations. Any modifications and equivalent substitutions made within the spirit and principles of this application should be included in the scope of protection of this application.

Claims

1. A construction monitoring method based on oblique photography, characterized in that: include: Obtaining the construction tasks to be performed in the target construction area at a preset time point to obtain a first target task; Acquire the construction state of the target construction area under the initial state of the first target task to obtain a first target state; Obtaining the expected construction state of the target construction area after the first target task is completed according to the construction design document and the construction plan, and obtaining a second target state; Acquire the construction progress of the target construction area in the first target task to obtain a first construction progress; Obtaining the construction time of the target construction area in the first target task to obtain a first target construction time; According to the task type corresponding to the first target task, a corresponding construction duration prediction model is matched to obtain a target prediction model; wherein the construction duration prediction model is used to predict the total construction duration required to complete the first target task; Inputting the first construction progress, the first target construction duration, the first target state, and the second target state into the target prediction model to obtain a second target construction duration; The second target construction time is compared with the expected construction time. If the second target construction time is longer than the expected construction time, first feedback information is generated. The first feedback information includes feedback information indicating that there is an abnormality in the construction progress of the target construction area.

2. The method for monitoring construction based on oblique photography according to claim 1, characterized in that: The step of obtaining the construction progress of the target construction area in the first target task also includes: Acquire an actual construction image of the target construction area at the preset time point by oblique photography, and establish a current construction model of the target construction area according to the actual construction image to obtain a target construction model; Acquire a first reference construction model corresponding to the first target state; Acquire a second reference construction model corresponding to the second target state; calculating a similarity between the first reference construction model and the second reference construction model to obtain a first similarity; Calculating the similarity between the target construction model and the second reference construction model to obtain a second similarity; The first construction progress is obtained according to the first similarity and the second similarity.

3. The method for monitoring construction based on oblique photography according to claim 2, characterized in that: The first construction progress calculation method includes: ； Among them, P1 represents the first construction progress, s1 represents the first similarity, and s2 represents the second similarity.

4. The method for monitoring construction based on oblique photography according to claim 2, characterized in that: The first similarity and the second similarity are obtained based on elevation information and color similarity. The elevation similarity is used to represent the similarity between the elevation information of the highest points of all positions in the target construction area under different construction conditions. The color similarity is used to represent the similarity between point cloud data in the construction model corresponding to the target construction area under different construction conditions. The point cloud data includes color data corresponding to the spatial coordinates corresponding to the construction model.

5. The method for monitoring construction based on oblique photography according to claim 4, characterized in that: The elevation information includes contour lines.

6. The calculation method of the elevation similarity includes: Acquire contour images of the construction models to be compared respectively, and obtain a first contour image and a second contour image; Dividing the first contour line image according to the heights corresponding to the contour lines to obtain a first contour line sub-image set, and dividing the second contour line image according to the heights corresponding to the contour lines to obtain a second contour line sub-image set; Obtain a closed region of contour lines in each first contour line sub-image to obtain a corresponding first closed region; Obtain a closed region of contour lines in each second contour line sub-image to obtain a corresponding second closed region; Matching the first closed area and the second closed area according to the height of the contour line, and if the match is successful, calculating the intersection-over-union ratio of the first closed area and the second closed area to obtain the contour line similarity of the corresponding height; The mean of the contour similarities corresponding to all heights is calculated to obtain the elevation similarity.

7. A construction monitoring method based on oblique photography according to any one of claims 2 to 6, characterized in that: The number of target construction areas is not less than 2, and if the second target construction duration is not greater than the corresponding expected construction duration, the step of comparing the second target construction duration with the expected construction duration also includes: Calculate the average of each of the second target construction durations and the corresponding first target construction duration to obtain a third target construction duration; calculate the average duration of all the third target construction durations; respectively calculate the distance between each of the third target construction durations and the average duration to obtain a corresponding duration difference; respectively compare each of the duration differences with a first preset threshold, and if there is a duration difference greater than the first preset threshold, generate second feedback information, and the second feedback information includes a target construction area for indicating that there is an optimized construction arrangement.

8. A construction monitoring method based on oblique photography according to any one of claims 4 to 6, characterized in that: The process types include foundation pit excavation, foundation pit support, backfilling, pile foundation construction, foundation reinforcement binding, foundation formwork installation, foundation concrete pouring, main body reinforcement binding, main body formwork installation, concrete pouring, door and window installation and outdoor decoration.

9. The method for monitoring construction based on oblique photography according to claim 8, characterized in that: When the process type corresponding to the first target task belongs to one of foundation pit excavation, foundation pit support, earth backfilling, pile foundation construction, foundation steel bar binding, foundation formwork installation, foundation concrete pouring, main steel bar binding, main formwork installation and concrete pouring, the weight of the elevation similarity is greater than the weight of the color similarity. When the process type corresponding to the first target task belongs to one of door and window installation and outdoor decoration, the weight of the elevation similarity is less than the weight of the color similarity.

10. A construction monitoring system based on oblique photography, characterized in that: include: A first acquisition module, the first acquisition module is used to acquire the construction tasks to be performed in the target construction area at a preset time point to obtain a first target task; A second acquisition module, the second acquisition module is used to acquire the construction state of the target construction area under the initial state of the first target task to obtain a first target state; A third acquisition module, the third acquisition module is used to acquire the expected construction state of the target construction area after the first target task is completed according to the construction design document and the construction plan, and obtain a second target state; A fourth acquisition module, the fourth acquisition module is used to acquire the construction progress of the target construction area in the first target task to obtain a first construction progress; A fifth acquisition module, the fifth acquisition module is used to acquire the construction time of the target construction area during the first target task, and obtain a first target construction time; A first query module, the first query module is used to match the corresponding construction duration prediction model according to the task type corresponding to the first target task to obtain a target prediction model; wherein the construction duration prediction model is used to predict the total construction duration required to complete the first target task; A first processing module, the first processing module is used to input the first construction progress, the first target construction duration, the first target state and the second target state into the target prediction model to obtain a second target construction duration; The first judgment module is used to compare the second target construction time with the expected construction time. If the second target construction time is longer than the expected construction time, a first feedback information is generated. The first feedback information includes feedback information indicating that there is an abnormality in the construction progress of the target construction area.

Images