Bridge construction progress monitoring method based on BIM real scene model

Abstract

The invention relates to the technical field of data processing, in particular to a BIM live-action model-based bridge construction progress monitoring method, which comprises the following steps of: extracting feature points of a bridge region in a construction bridge grayscale image and a bridge BIM model image, and matching to obtain a plurality of groups of feature matching points; obtaining the matching accuracy of each group of feature matching points according to the position difference of the bridge local area to which each group of feature matching points belong and the gray difference between the surrounding pixel points; screening all groups of feature matching points according to the matching accuracy to obtain a plurality of groups of successfully matched feature points; according to the number of the successfully matched feature points and the difference between the actual consumed material amount of the bridge and the planned consumed material amount of the bridge, the bridge construction progress degree is obtained; and performing construction monitoring on the bridge based on the bridge construction progress degree. The accuracy of the monitoring result of the bridge construction progress is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method for monitoring the progress of bridge construction based on a BIM real-scene model. Background Art

[0002] With the continuous development of bridge construction technology, bridge structures are becoming more and more complex, and the construction difficulty and precision requirements are also increasing. Traditional construction progress monitoring methods are often unable to meet the needs of complex bridge construction, and more advanced and efficient technical means need to be introduced. Building Information Modeling (BIM) has been widely used in bridge construction as a technical means that integrates multiple functions such as 3D modeling, data integration and construction management. The BIM real-life model can intuitively display the situation of the bridge construction site, providing strong support for construction progress monitoring. For the monitoring of bridge construction progress, relevant units often send professionals to collect grayscale images of the bridge construction site through drones, and then judge the construction progress of the bridge based on the matching results between the BIM real-life model and the grayscale image of the bridge construction site. However, due to the errors in the matching results between the BIM real-life model and the grayscale image of the bridge construction site, the matching of bridge information at the detailed position is missing, and the construction progress cannot be accurately evaluated. Summary of the invention

[0003] In order to solve the above problems, the present invention provides a bridge construction progress monitoring method based on a BIM real-life model, the method comprising: Obtaining grayscale images of the bridge under construction and images of the bridge BIM model, as well as the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge; Acquire several support column areas in the bridge area in the grayscale image of the bridge under construction and the bridge BIM model image; divide the bridge area according to the positions of the support column areas to obtain several local bridge areas; extract and match the feature points of the bridge area in the grayscale image of the bridge under construction and the bridge BIM model image to obtain several groups of feature matching points; obtain the matching accuracy of each group of feature matching points based on the position difference of the local bridge area to which each group of feature matching points belongs and the grayscale difference between the surrounding pixel points; screen all groups of feature matching points according to the matching accuracy to obtain several groups of successfully matched feature points; The progress of the bridge construction is obtained according to the number of successfully matched feature points and the difference between the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge; and the construction of the bridge is monitored based on the progress of the bridge construction.

[0004] Preferably, the bridge area is divided according to the positions of the support column areas to obtain a plurality of bridge local areas, including the specific method of: For any one of the grayscale image of the construction bridge and the BIM model image of the bridge, the symmetry axis of each supporting column area in the bridge area in the any one of the images is used as a dividing line, and the bridge area in the any one of the images is divided and segmented using the dividing line to obtain a number of local bridge areas.

[0005] Preferably, the matching accuracy of each group of feature matching points is obtained according to the position difference of the local area of ​​the bridge to which each group of feature matching points belongs and the grayscale difference between the surrounding pixels, including the specific method of: For any set of feature matching points, the feature points of the grayscale image of the construction bridge in the set of feature matching points are recorded as the bridge feature points in the set of feature matching points; the feature points of the BIM model image of the bridge in the set of feature matching points are recorded as the model feature points in the set of feature matching points; Preset a window parameter In the grayscale image of the bridge under construction, the bridge feature point in the set of feature matching points is used as the window center, and the window size is obtained as The window is recorded as the neighborhood range of the bridge feature point in the group of feature matching points; in the bridge BIM model image, the model feature point in the group of feature matching points is used as the window center, and the window size is obtained. The window is recorded as the neighborhood range of the model feature points in the group of feature matching points; According to the grayscale difference of the pixel points in the neighborhood range between the model feature point and the bridge feature point in the group of feature matching points, the color difference consistency of the group of feature matching points is obtained; According to the position distribution difference between the model feature points and the bridge feature points in the group of feature matching points, obtaining the position difference consistency of the group of feature matching points; A normalized value of the product of the color difference consistency of the group of feature matching points and the position difference consistency of the group of feature matching points is used as the matching accuracy of the group of feature matching points.

[0006] Preferably, the color difference consistency of the group of feature matching points is obtained according to the grayscale difference of the pixel points in the neighborhood range between the model feature points and the bridge feature points in the group of feature matching points, and the specific method includes: The first pixel point and the model feature point in the set of feature matching points in the neighborhood range of The absolute value of the difference in grayscale values ​​between pixels is recorded as the first pixel in the neighborhood between the model feature point and the bridge feature point in the set of feature matching points. The inverse of the variance of the first difference of all pixels in the neighborhood between the model feature point and the bridge feature point in the group of feature matching points is used as the color difference consistency of the group of feature matching points.

[0007] Preferably, the obtaining of the position difference consistency of the group of feature matching points according to the position distribution difference between the model feature points and the bridge feature points in the group of feature matching points includes the following specific methods: The inverse proportional value of the Euclidean distance between the centroid position of the local area of ​​the bridge in the grayscale image of the construction bridge of the bridge feature point in the group of feature matching points and the centroid position of the local area of ​​the bridge in the BIM model image of the bridge of the model feature point in the group of feature matching points is taken as the position difference consistency of the group of feature matching points.

[0008] Preferably, the method of screening all groups of feature matching points according to the matching accuracy to obtain several groups of successful matching feature points includes the following specific methods: Preset a first threshold parameter , The matching accuracy of the group feature matching points is greater than the first threshold parameter , will A group of feature matching points is recorded as a group of successful matching feature points; if the The matching accuracy of the group feature matching points is less than or equal to the first threshold parameter , will The group of feature matching points is recorded as a group of inaccurately matched feature points; Preset a neighborhood parameter For any set of inaccurately matched feature points, in the grayscale image of the bridge under construction, the bridge feature point in the set of inaccurately matched feature points is used as the window center to obtain the window size The window is recorded as the target neighborhood range of the bridge feature point in the group of inaccurate matching feature points; in the bridge BIM model image, the model feature point in the group of inaccurate matching feature points is used as the window center, and the window size is obtained. The window is recorded as the target neighborhood range of the model feature points in the group of inaccurately matched feature points; Obtaining the corrected matching accuracy of each group of inaccurately matched feature points according to the matching accuracy of surrounding feature matching points of each group of inaccurately matched feature points; Preset a second threshold parameter , The corrected matching accuracy of the group matching inaccurate feature points is greater than the second threshold parameter , will A group of inaccurately matched feature points is recorded as a group of successfully matched feature points.

[0009] Preferably, the method of obtaining the corrected matching accuracy of each group of inaccurately matched feature points according to the matching accuracy of the surrounding feature matching points of each group of inaccurately matched feature points includes the following specific methods: For any group of feature matching points between the target neighborhood range of the model feature points in the group of inaccurate matching feature points and the target neighborhood range of the bridge feature points in the group of inaccurate matching feature points, they are all recorded as comparison group feature matching points within the target neighborhood range of the group of inaccurate matching feature points; the absolute value of the difference in grayscale values ​​between the model feature points in the comparison group of feature matching points and the bridge feature points in the comparison group of feature matching points is recorded as the grayscale difference value of the comparison group of feature matching points; the ratio of the matching accuracy of the comparison group of feature matching points to the grayscale difference value of the comparison group of feature matching points is recorded as the first ratio of the comparison group of feature matching points; the normalized value of the mean of the first ratios of all comparison group feature matching points within the target neighborhood range of the group of inaccurate matching feature points is used as the corrected matching accuracy of the group of inaccurate matching feature points.

[0010] Preferably, the method of obtaining the bridge construction progress according to the number of successfully matched feature points and the difference between the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge includes the following specific methods: According to the number of successfully matched feature points, the actual progress factor and the planned progress factor are obtained; The difference between the planned progress factor and the actual progress factor is recorded as the progress difference; the ratio of the progress difference to the planned progress factor is recorded as the progress ratio factor; the ratio of the planned material consumption of the bridge to the planned progress factor is recorded as the planned consumption ratio; the ratio of the actual material consumption of the bridge to the actual progress factor is recorded as the actual consumption ratio; the ratio between the planned consumption ratio and the actual consumption ratio is recorded as the progress consumption ratio factor; the normalized value of the product of the progress ratio factor and the progress consumption ratio factor is taken as the degree of bridge construction progress.

[0011] Preferably, the actual progress factor and the planned progress factor are obtained according to the number of successfully matched feature points, including the specific method of: The ratio between the number of bridge feature points in all groups of successfully matched feature points and the number of all pixel points in the bridge area in the grayscale image of the construction bridge is recorded as the actual ratio; the product of the mean of the matching accuracy of all groups of successfully matched feature points and the actual ratio is taken as the actual progress factor; The ratio between the number of model feature points in all groups of successfully matched feature points and the number of all pixel points in the bridge area in the bridge BIM model image is recorded as the model ratio; the product of the mean of the matching accuracy of all groups of successfully matched feature points and the model ratio is used as the planning progress factor.

[0012] Preferably, the bridge construction monitoring based on the bridge construction progress includes the following specific methods: Preset a threshold range , if the bridge construction progress is within the threshold range In the process, the bridge construction progress is recorded as normal; if the bridge construction progress is not within the threshold range In the process, the bridge construction progress is recorded as abnormal.

[0013] The beneficial effects of the technical solution of the present invention are as follows: the present invention obtains the matching accuracy of each group of feature matching points according to the position difference of the local area of ​​the bridge to which each group of feature matching points belongs and the grayscale difference between the surrounding pixel points; screens all groups of feature matching points according to the matching accuracy to obtain several groups of successfully matched feature points; obtains the degree of bridge construction progress according to the number of successfully matched feature points and the difference between the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge; monitors the bridge construction based on the degree of bridge construction progress; analyzes the speed of the actual bridge construction progress and the planned construction progress, thereby reducing the error of the matching result between the BIM real-scene model and the grayscale image of the bridge construction site, improving the matching of bridge information at the detailed position, and then accurately evaluating the construction progress, thereby improving the accuracy of the monitoring result of the bridge construction progress. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0015] Figure 1 It is a flow chart of the steps of the bridge construction progress monitoring method based on the BIM real scene model of the present invention; Figure 2 It is a characteristic relationship flow chart of the bridge construction progress monitoring method based on the BIM real-scene model of the present invention. DETAILED DESCRIPTION

[0016] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following is a detailed description of the bridge construction progress monitoring method based on the BIM real scene model proposed by the present invention, its specific implementation method, structure, characteristics and effects, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment. In addition, specific features, structures or characteristics in one or more embodiments may be combined in any suitable form.

[0017] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0018] The specific scheme of the bridge construction progress monitoring method based on the BIM real-scene model provided by the present invention is described in detail below with reference to the accompanying drawings.

[0019] See also Figure 1 , which shows a flow chart of a method for monitoring the progress of bridge construction based on a BIM real-life model provided by an embodiment of the present invention, the method comprising the following steps: Step S001: Obtain a grayscale image of a bridge under construction and a BIM model image of the bridge, as well as the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge.

[0020] It should be noted that during the construction of the bridge, it is necessary to have a certain control over the overall progress of the bridge project to help formulate corresponding project plans and indicators; therefore, by analyzing the similarity between the actual bridge image and the BIM model, the actual speed of the bridge construction progress can be determined.

[0021] Specifically, it is necessary to first collect the grayscale image of the bridge under construction and the BIM model image of the bridge, as well as the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge. The specific process is as follows: Inputting relevant information such as design drawings and construction plans of the bridge into BIM software to construct a BIM model of the bridge in the construction plan; using the BIM model of the bridge to obtain a BIM model image of the bridge; Use a drone to photograph a bridge under construction to obtain an image of the bridge under construction, and perform median filtering, denoising and grayscale operations on the image of the bridge under construction to obtain a grayscale image of the bridge under construction; The planned material consumption of the bridge is obtained according to the bridge design drawings, bill of quantities and construction plan; the actual material consumption of the bridge is obtained through on-site construction records, material purchase orders and actual usage.

[0022] Among them, the acquisition angle and size of the construction bridge grayscale image and the bridge BIM model image need to be consistent. Median filtering and grayscale operations are existing technologies and will not be described in detail in this embodiment.

[0023] At this point, the grayscale image of the constructed bridge and the BIM model image of the bridge, as well as the actual material consumption of the bridge and the planned material consumption of the bridge are obtained through the above method.

[0024] Step S002: Acquire several support column areas in the bridge area in the grayscale image of the bridge under construction and the bridge BIM model image; divide the bridge area according to the positions of the support column areas to obtain several local bridge areas; extract and match the feature points of the bridge area in the grayscale image of the bridge under construction and the bridge BIM model image to obtain several groups of feature matching points; acquire the matching accuracy of each group of feature matching points based on the position difference of the local bridge area to which each group of feature matching points belongs and the grayscale difference between the surrounding pixel points; screen all groups of feature matching points based on the matching accuracy to obtain several groups of successfully matched feature points.

[0025] It should be noted that during the construction of the bridge, the construction progress may not be carried out according to the prescribed plan due to emergencies such as weather conditions. For the staff, it is necessary to accurately understand the progress of the bridge construction and grasp the speed of the bridge construction so that they can discuss solutions with relevant personnel in a timely manner and adjust the construction progress; then it is necessary to analyze the grayscale image of the construction bridge, compare the grayscale image of the construction bridge with the bridge BIM model image, and judge the adaptability of the bridge in the two images, that is, according to the characteristic information shown on the bridge, perform feature point matching, and further confirm and correct the feature point matching results to obtain accurate matching results.

[0026] 1. Divide the bridge area in the grayscale image of the construction bridge and the bridge BIM model image to obtain several local bridge areas.

[0027] It should be noted that the construction process of a bridge generally involves first completing the construction of the bridge support columns, and then gradually completing the construction of the bridge deck and other projects on this basis; bridges, especially large bridges, often have repetitive structural elements, such as beams, railings, etc. These similar structures may produce a large number of similar feature points in the image, thereby increasing the risk of pixel mismatching on the image; and the image captured by the drone includes the entire part of the bridge, so it is necessary to divide the bridge area based on the position of the bridge support columns.

[0028] Preferably, in some implementations of the embodiments of the present invention, the specific method for obtaining a plurality of support column regions in the bridge region in the grayscale image of the construction bridge and the bridge BIM model image is: Input the grayscale image of the bridge under construction and the bridge BIM model image into the trained neural network to obtain several support column areas in the bridge area in the grayscale image of the bridge under construction and the bridge BIM model image; the neural network used in this embodiment is YOLOv3, and the method for obtaining the data set for training the neural network is: A large number of grayscale images of bridges under construction and images of bridge BIM models are collected, and a bounding box is artificially marked in each grayscale image of bridges under construction and image of bridge BIM model, that is, a number of supporting column areas in the bridge area in the grayscale image of bridges under construction and image of bridge BIM model, and the marking result is recorded as a label of each grayscale image of bridges under construction and image of bridge BIM model; a large number of grayscale images of bridges under construction and images of bridge BIM model and their corresponding labels are collected to form a data set; the neural network is trained using the data set, and the loss function used in the training process is a mean square error loss function; the specific training process is a well-known content of the neural network, and the specific training process is not repeated in this embodiment.

[0029] Preferably, in some implementations of the embodiments of the present invention, since the bridge support columns are all vertical in shape, and combined with the fact that the support columns are mostly symmetrical in pairs and vertically upward, the bridge area is divided according to the positions of the support column areas to obtain a specific method of obtaining several bridge local areas: For any one of the grayscale image of the construction bridge and the BIM model image of the bridge, the symmetry axis of each supporting column area in the bridge area in the any one of the images is used as a dividing line, and the bridge area in the any one of the images is divided and segmented using the dividing line to obtain a number of local bridge areas.

[0030] At this point, several local areas of the bridge are obtained.

[0031] Preferably, the SIFT algorithm is used to extract all feature points in the bridge area in the grayscale image of the construction bridge and the bridge BIM model image; and all feature points in the bridge area in the grayscale image of the construction bridge are matched with all feature points in the bridge area in the bridge BIM model image to obtain several groups of feature matching points.

[0032] 2. Obtain several groups of successfully matched feature points.

[0033] It should be noted that since the bridge has many similar shape structures, there may be many feature similarities in the image, resulting in mismatched feature points in the two images. For bridge images, there is color consistency in its continuous area during the construction process. In the normal matching process, the pixels should be matched with each other in the same area. Based on this, the results of feature matching are analyzed to determine the matching accuracy of each group of feature matching points.

[0034] Preferably, in some implementations of the embodiments of the present invention, since there may be a certain color difference between the bridge color in the grayscale image of the construction bridge and the bridge color in the bridge BIM model image, resulting in differences in the grayscale values ​​of the pixels of the two, but for adjacently distributed pixels, since they are in the same area on the bridge, their color differences in the two images should be relatively the same; therefore, according to the position difference of the local area of ​​the bridge to which each group of feature matching points belongs, and the grayscale difference between the surrounding pixels, the specific method for obtaining the matching accuracy of each group of feature matching points is as follows: For any set of feature matching points, the feature points of the grayscale image of the construction bridge in the set of feature matching points are recorded as the bridge feature points in the set of feature matching points; the feature points of the BIM model image of the bridge in the set of feature matching points are recorded as the model feature points in the set of feature matching points; Preset a window parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation; In the grayscale image of the bridge under construction, the bridge feature point in the set of feature matching points is used as the window center, and the window size is obtained as The window is recorded as the neighborhood range of the bridge feature point in the group of feature matching points; in the bridge BIM model image, the model feature point in the group of feature matching points is used as the window center, and the window size is obtained. The window is recorded as the neighborhood range of the model feature points in the group of feature matching points; The first pixel point and the model feature point in the set of feature matching points in the neighborhood range of The absolute value of the difference in grayscale values ​​between pixels is recorded as the first pixel in the neighborhood between the model feature point and the bridge feature point in the set of feature matching points. The inverse of the variance of the first difference of all pixels in the neighborhood between the model feature point and the bridge feature point in the group of feature matching points is used as the color difference consistency of the group of feature matching points; The inverse proportional value of the Euclidean distance between the centroid position of the local area of ​​the bridge in the grayscale image of the bridge under construction of the bridge feature point in the group of feature matching points and the centroid position of the local area of ​​the bridge in the bridge BIM model image of the model feature point in the group of feature matching points is used as the position difference consistency of the group of feature matching points; Taking the normalized value of the product of the color difference consistency of the group of feature matching points and the position difference consistency of the group of feature matching points as the matching accuracy of the group of feature matching points; The specific formula is: In the formula, Indicates The matching accuracy of the group feature matching points; Indicates that the The centroid position of the bridge feature point in the group of feature matching points in the bridge construction grayscale image is The Euclidean distance between the centroid positions of the model feature points in the group feature matching points and the local area of ​​the bridge in the bridge BIM model image; Indicates The variance of the first difference of all pixels in the neighborhood between the model feature point and the bridge feature point in the group feature matching point; represents the linear normalization function; represents an exponential function with a natural constant as the base, and the embodiment adopts The model shows an inverse proportional relationship. As the input of the model, implementers can choose the inverse proportional function according to actual conditions.

[0035] It should be noted that The larger the value, the The larger the difference between the two image feature matching points, the The smaller the probability that the group feature matching point is a successful match, Indicates The position difference consistency of the group feature matching points; The smaller the value, the The more consistent the regions where the feature matching points are located on the two images, and the more consistent the color differences are, that is, the The more likely the group feature matching point is to be a successful match; Indicates The color difference consistency of the group feature matching points.

[0036] Preferably, in some implementations of the embodiments of the present invention, the specific method of screening all groups of feature matching points according to the matching accuracy to obtain several groups of successfully matched feature points is: Preset a first threshold parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation; Jordi The matching accuracy of the group feature matching points is greater than the first threshold parameter , will A group of feature matching points is recorded as a group of successful matching feature points; if the The matching accuracy of the group feature matching points is less than or equal to the first threshold parameter , will The group of feature matching points is recorded as a group of inaccurately matched feature points; It should be noted that for the inaccurately matched feature points between the two images, there may be some uncontrollable factors that cause some imperfections in the captured image, resulting in errors in the calculated matching accuracy, but the matching results of the surrounding pixels will not change. Therefore, it is necessary to re-calculate the inaccurately matched feature points to obtain the corrected matching accuracy of the inaccurately matched feature points.

[0037] Preferably, in some implementations of the embodiments of the present invention, the specific method for obtaining the corrected matching accuracy of each group of inaccurately matched feature points according to the matching accuracy of the surrounding feature matching points of each group of inaccurately matched feature points is: Preset a neighborhood parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation; For any set of inaccurately matched feature points, in the grayscale image of the bridge under construction, the bridge feature point in the set of inaccurately matched feature points is used as the window center to obtain the window size: The window is recorded as the target neighborhood range of the bridge feature point in the group of inaccurate matching feature points; in the bridge BIM model image, the model feature point in the group of inaccurate matching feature points is used as the window center, and the window size is obtained. The window is recorded as the target neighborhood range of the model feature points in the group of inaccurately matched feature points; Any set of feature matching points between the target neighborhood range of the model feature points in the group of inaccurate matching feature points and the target neighborhood range of the bridge feature points in the group of inaccurate matching feature points are recorded as comparison group feature matching points within the target neighborhood range of the group of inaccurate matching feature points; the absolute value of the difference in grayscale value between the model feature points in the comparison group of feature matching points and the bridge feature points in the comparison group of feature matching points is recorded as the grayscale difference value of the comparison group of feature matching points; the ratio of the matching accuracy of the comparison group of feature matching points to the grayscale difference value of the comparison group of feature matching points is recorded as the first ratio of the comparison group of feature matching points; the normalized value of the mean of the first ratios of all the comparison group of feature matching points within the target neighborhood range of the group of inaccurate matching feature points is taken as the corrected matching accuracy of the group of inaccurate matching feature points; The specific formula is: In the formula, Indicates Correction of inaccurate feature points in group matching to improve matching accuracy; Indicates the number of inaccurate feature points in all groups; Indicates The target neighborhood of the group matching inaccurate feature points The matching accuracy of feature matching points in the comparison group; Indicates The target neighborhood of the group matching inaccurate feature points Grayscale value of the model feature point in the feature matching points of the comparison group; Indicates The target neighborhood of the group matching inaccurate feature points Gray value of the bridge feature point in the feature matching points of the comparison group; Indicates taking the absolute value; represents the linear normalization function.

[0038] Preset a second threshold parameter , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation; Jordi The corrected matching accuracy of the group matching inaccurate feature points is greater than the second threshold parameter , will A group of inaccurately matched feature points is recorded as a group of successfully matched feature points.

[0039] Among them, for the successfully matched feature points screened out for the second time, it is necessary to use the corrected matching accuracy as the matching accuracy of these successfully matched feature points.

[0040] So far, several groups of successfully matched feature points are obtained through the above method.

[0041] Step S003: Obtain the bridge construction progress according to the number of successfully matched feature points and the difference between the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge; and monitor the bridge construction based on the bridge construction progress.

[0042] It should be noted that the difference in project progress between the two images can be analyzed based on the percentage of successfully matched feature points on the image and the presence of bridge areas on each image. However, if the analysis is based on the acquired images, only the situation on the surface of the bridge can be obtained, and the situation inside the bridge cannot be analyzed. However, for bridge construction, the various materials consumed in the project are calculated in the plan. Therefore, the progress of the bridge project under actual conditions can be determined by combining the material usage and image information.

[0043] Preferably, in some implementations of the embodiments of the present invention, the specific method for obtaining the bridge construction progress according to the number of successfully matched feature points is: The ratio between the number of bridge feature points in all groups of successfully matched feature points and the number of all pixel points in the bridge area in the grayscale image of the construction bridge is recorded as the actual ratio; the product of the mean of the matching accuracy of all groups of successfully matched feature points and the actual ratio is taken as the actual progress factor; The ratio between the number of model feature points in all groups of successfully matched feature points and the number of all pixel points in the bridge area in the bridge BIM model image is recorded as the model ratio; the product of the mean of the matching accuracy of all groups of successfully matched feature points and the model ratio is used as the planning progress factor; It should be noted that for the bridge area, the more successfully matched feature points there are, the closer the actual progress of the bridge is to the planned progress. However, it may be necessary to divide it into the actual situation exceeding the plan, or the actual situation falling short of the plan, so the analysis is based on the grayscale image of the construction bridge.

[0044] Preferably, in some implementations of the embodiments of the present invention, the specific method for obtaining the bridge construction progress degree according to the actual progress factor, the planned progress factor, and the planned consumable materials and the actual consumable materials is: The difference between the planned progress factor and the actual progress factor is recorded as the progress difference; the ratio of the progress difference to the planned progress factor is recorded as the progress ratio factor; the ratio of the planned material consumption of the bridge to the planned progress factor is recorded as the planned consumption ratio; the ratio of the actual material consumption of the bridge to the actual progress factor is recorded as the actual consumption ratio; the ratio between the planned consumption ratio and the actual consumption ratio is recorded as the progress consumption ratio factor; the normalized value of the product of the progress ratio factor and the progress consumption ratio factor is taken as the degree of bridge construction progress.

[0045] It should be noted that when the bridge construction progress is positive, it means that the actual bridge progress is faster than the planned progress; when the bridge construction progress is negative, it means that the actual bridge progress is slower than the planned progress.

[0046] Preferably, in some implementations of the embodiments of the present invention, the specific method for monitoring the construction of a bridge based on the progress of the bridge construction is: Preset a threshold range , wherein this embodiment is based on This example is described as an example, and this embodiment is not specifically limited. Depends on the specific implementation situation; If the bridge construction progress is within the threshold range In the process, the bridge construction progress is recorded as normal; if the bridge construction progress is not within the threshold range In the process, the bridge construction progress is recorded as abnormal and an alarm reminder is required.

[0047] At this point, the bridge construction is monitored based on the degree of bridge construction progress.

[0048] See also Figure 2 , which shows a characteristic relationship flow chart of a bridge construction progress monitoring method based on a BIM real-life model; At this point, this embodiment is completed.

[0049] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A bridge construction progress monitoring method based on BIM real-scene model, characterized in that: The method comprises the following steps: Obtaining grayscale images of the bridge under construction and images of the bridge BIM model, as well as the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge; Acquire several support column areas in the bridge area in the grayscale image of the bridge under construction and the bridge BIM model image; divide the bridge area according to the positions of the support column areas to obtain several local bridge areas; extract and match the feature points of the bridge area in the grayscale image of the bridge under construction and the bridge BIM model image to obtain several groups of feature matching points; obtain the matching accuracy of each group of feature matching points based on the position difference of the local bridge area to which each group of feature matching points belongs and the grayscale difference between the surrounding pixel points; screen all groups of feature matching points according to the matching accuracy to obtain several groups of successfully matched feature points; The progress of the bridge construction is obtained according to the number of successfully matched feature points and the difference between the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge; and the construction of the bridge is monitored based on the progress of the bridge construction.

2. The bridge construction progress monitoring method based on BIM real scene model according to claim 1 is characterized in that: The method of dividing the bridge area according to the position of the support column area to obtain a plurality of bridge local areas includes: For any one of the grayscale image of the construction bridge and the BIM model image of the bridge, the symmetry axis of each supporting column area in the bridge area in the any one of the images is used as a dividing line, and the bridge area in the any one of the images is divided and segmented using the dividing line to obtain a number of local bridge areas.

3. The bridge construction progress monitoring method based on BIM real scene model according to claim 1 is characterized in that: The specific method of obtaining the matching accuracy of each group of feature matching points according to the position difference of the local area of ​​the bridge to which each group of feature matching points belongs and the grayscale difference between the surrounding pixels is as follows: For any set of feature matching points, the feature points of the grayscale image of the construction bridge in the set of feature matching points are recorded as the bridge feature points in the set of feature matching points; the feature points of the BIM model image of the bridge in the set of feature matching points are recorded as the model feature points in the set of feature matching points; Preset a window parameter In the grayscale image of the bridge under construction, the bridge feature point in the set of feature matching points is used as the window center, and the window size is obtained as The window is recorded as the neighborhood range of the bridge feature point in the group of feature matching points; in the bridge BIM model image, the model feature point in the group of feature matching points is used as the window center, and the window size is obtained. The window is recorded as the neighborhood range of the model feature points in the group of feature matching points; According to the grayscale difference of the pixel points in the neighborhood range between the model feature point and the bridge feature point in the group of feature matching points, the color difference consistency of the group of feature matching points is obtained; According to the position distribution difference between the model feature points and the bridge feature points in the group of feature matching points, obtaining the position difference consistency of the group of feature matching points; A normalized value of the product of the color difference consistency of the group of feature matching points and the position difference consistency of the group of feature matching points is used as the matching accuracy of the group of feature matching points.

4. The bridge construction progress monitoring method based on BIM real scene model according to claim 3 is characterized in that: The method of obtaining the color difference consistency of the group of feature matching points according to the grayscale difference of the pixel points in the neighborhood range between the model feature points and the bridge feature points in the group of feature matching points includes: The first pixel point and the model feature point in the set of feature matching points in the neighborhood range of The absolute value of the difference in grayscale values ​​between pixels is recorded as the first pixel in the neighborhood between the model feature point and the bridge feature point in the set of feature matching points. The inverse of the variance of the first difference of all pixels in the neighborhood between the model feature point and the bridge feature point in the group of feature matching points is used as the color difference consistency of the group of feature matching points.

5. The bridge construction progress monitoring method based on BIM real scene model according to claim 3 is characterized in that: The specific method of obtaining the position difference consistency of the group of feature matching points according to the position distribution difference between the model feature points and the bridge feature points in the group of feature matching points is as follows: The inverse proportional value of the Euclidean distance between the centroid position of the local area of ​​the bridge in the grayscale image of the construction bridge of the bridge feature point in the group of feature matching points and the centroid position of the local area of ​​the bridge in the BIM model image of the bridge of the model feature point in the group of feature matching points is taken as the position difference consistency of the group of feature matching points.

6. The bridge construction progress monitoring method based on BIM real scene model according to claim 3 is characterized in that: The specific method of screening all groups of feature matching points according to the matching accuracy to obtain several groups of successful matching feature points includes: Preset a first threshold parameter , The matching accuracy of the group feature matching points is greater than the first threshold parameter , will The group of feature matching points is recorded as a group of successfully matched feature points; Jordi The matching accuracy of the group feature matching points is less than or equal to the first threshold parameter , will The group of feature matching points is recorded as a group of inaccurately matched feature points; Preset a neighborhood parameter For any set of inaccurately matched feature points, in the grayscale image of the bridge under construction, the bridge feature point in the set of inaccurately matched feature points is used as the window center to obtain the window size The window is recorded as the target neighborhood range of the bridge feature point in the group of inaccurate matching feature points; in the bridge BIM model image, the model feature point in the group of inaccurate matching feature points is used as the window center, and the window size is obtained. The window is recorded as the target neighborhood range of the model feature points in the group of inaccurately matched feature points; Obtaining the corrected matching accuracy of each group of inaccurately matched feature points according to the matching accuracy of surrounding feature matching points of each group of inaccurately matched feature points; Preset a second threshold parameter , The corrected matching accuracy of the group matching inaccurate feature points is greater than the second threshold parameter , will A group of inaccurately matched feature points is recorded as a group of successfully matched feature points.

7. The bridge construction progress monitoring method based on BIM real scene model according to claim 6 is characterized in that: The method of obtaining the corrected matching accuracy of each group of inaccurately matched feature points according to the matching accuracy of the surrounding feature matching points of each group of inaccurately matched feature points includes the following specific methods: For any group of feature matching points between the target neighborhood range of the model feature points in the group of inaccurate matching feature points and the target neighborhood range of the bridge feature points in the group of inaccurate matching feature points, they are all recorded as comparison group feature matching points within the target neighborhood range of the group of inaccurate matching feature points; the absolute value of the difference in grayscale values ​​between the model feature points in the comparison group of feature matching points and the bridge feature points in the comparison group of feature matching points is recorded as the grayscale difference value of the comparison group of feature matching points; the ratio of the matching accuracy of the comparison group of feature matching points to the grayscale difference value of the comparison group of feature matching points is recorded as the first ratio of the comparison group of feature matching points; the normalized value of the mean of the first ratios of all comparison group feature matching points within the target neighborhood range of the group of inaccurate matching feature points is used as the corrected matching accuracy of the group of inaccurate matching feature points.

8. The bridge construction progress monitoring method based on BIM real scene model according to claim 3 is characterized in that: The specific method of obtaining the progress of bridge construction according to the number of successfully matched feature points and the difference between the actual amount of material consumed by the bridge and the planned amount of material consumed by the bridge is as follows: According to the number of successfully matched feature points, the actual progress factor and the planned progress factor are obtained; The difference between the planned progress factor and the actual progress factor is recorded as the progress difference; The ratio of the progress difference to the planned progress factor is recorded as the progress ratio factor; The ratio of the planned consumption of materials for the bridge to the planned progress factor is recorded as the planned consumption ratio; the ratio of the actual consumption of materials for the bridge to the actual progress factor is recorded as the actual consumption ratio; The ratio between the planned consumption ratio and the actual consumption ratio is recorded as the progress consumption ratio factor; The normalized value of the product of the progress ratio factor and the progress consumption ratio factor is taken as the progress degree of the bridge construction.

9. The bridge construction progress monitoring method based on BIM real scene model according to claim 8 is characterized in that: The specific method of obtaining the actual progress factor and the planned progress factor according to the number of successfully matched feature points is as follows: The ratio between the number of bridge feature points in all groups of successfully matched feature points and the number of all pixel points in the bridge area in the grayscale image of the bridge under construction is recorded as the actual ratio; The product of the mean of the matching accuracy of all groups of successfully matched feature points and the actual ratio is used as the actual progress factor; The ratio between the number of model feature points in all groups of successfully matched feature points and the number of all pixel points in the bridge area in the bridge BIM model image is recorded as the model ratio; the product of the mean of the matching accuracy of all groups of successfully matched feature points and the model ratio is used as the planning progress factor.

10. The bridge construction progress monitoring method based on BIM real scene model according to claim 1 is characterized in that: The specific method of monitoring the bridge construction based on the progress of the bridge construction includes: Preset a threshold range , if the bridge construction progress is within the threshold range In the process, the bridge construction progress is recorded as normal; if the bridge construction progress is not within the threshold range In the process, the bridge construction progress is recorded as abnormal.

Images