Comprehensive management and control methods, devices, equipment and media of existing park pipe networks based on BIM

Abstract

The present invention relates to the field of park pipe network modeling technology, and in particular to a method, device, equipment and medium for comprehensive management and control of existing park pipe networks based on BIM. The method of the present invention first obtains multiple real-life images; then identifies the multiple real-life images to obtain multiple target real-life images and multiple pipeline shape and position parameters; then, the multiple target real-life images are grouped into multiple image groups according to image acquisition positions, and multiple pipeline node positions are determined according to the pipeline shape and position parameters of multiple images in the image group and the image acquisition positions of multiple images in the image group; finally, a pipeline path is constructed according to multiple pipeline node positions. The present invention identifies pipelines based on real-life images, extracts shape and position parameters of pipelines in real-life images, locates pipeline node positions based on shape and position parameters of pipelines and shooting positions, and finally constructs pipeline paths according to multiple pipeline node positions. The present invention constructs a pipeline network path model through pipeline real-life images, has fewer links in manual survey and modeling, and is highly efficient.

Description

Technical Field

[0001] The present invention relates to the technical field of park pipe network modeling, and in particular to a BIM-based integrated management and control method, device, equipment and medium for an existing park pipe network. Background Art

[0002] Some park pipeline information is old, and traditional 2D CAD drawings cannot accurately express park information. Moreover, it is highly professional and non-professionals cannot quickly understand it, and the drawing information is not intuitive enough. In addition, after many years of operation, some parks have undergone many renovations of their pipelines, and the original pipeline drawings are no longer applicable.

[0003] In the face of the above problems, some parks have combined two-dimensional drawings and pipeline inspections to carry out three-dimensional modeling of park pipelines. The advantage of three-dimensional modeling is that it can more vividly show the direction of park pipelines and building information.

[0004] However, the above modeling method requires more human resources investment and the modeling efficiency is relatively low.

[0005] Based on this, it is necessary to develop and design a comprehensive management and control method for existing park pipelines based on BIM. Summary of the invention

[0006] The embodiments of the present invention provide a method, device, equipment and medium for comprehensive management and control of an existing park pipe network based on BIM, which is used to solve the problem in the prior art that a large amount of human resources are required to improve the information of an existing park pipe network.

[0007] In a first aspect, an embodiment of the present invention provides a method for comprehensive management and control of an existing park pipe network based on BIM, comprising:

[0008] Acquire multiple real scene images, wherein each real scene image corresponds to an image acquisition position;

[0009] Identify the multiple real-scene images to obtain multiple target real-scene images and multiple pipeline shape and position parameters, wherein each pipeline shape and position parameter corresponds to a target real-scene image, and the pipeline shape and position parameter represents the shape and position characteristics of the pipeline image in the target real-scene image;

[0010] The multiple target real scene images are grouped into multiple image groups according to the image acquisition positions, and multiple pipeline node positions are determined according to the pipeline shape and position parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group, wherein each pipeline node position corresponds to one image group;

[0011] A pipeline path is constructed according to the plurality of pipeline node positions.

[0012] In a possible implementation manner, the identifying the multiple real scene images includes:

[0013] For each real scene, perform the following steps:

[0014] Adjusting multiple pixel values ​​of the real scene image to a preset distribution range to obtain a first intermediate real scene image;

[0015] Performing edge characterization processing on the first intermediate real scene image to obtain an edge feature image;

[0016] Segmenting the edge feature map once to obtain a plurality of first image blocks;

[0017] Perform secondary segmentation on each first image block, and construct the obtained multiple second image blocks into a second image block set;

[0018] Inputting the plurality of second image block sets into the recognition model respectively to obtain a plurality of recognition results, wherein each recognition result corresponds to a first image block;

[0019] The pipeline shape parameters are determined according to the positions and areas occupied by the plurality of pipeline image blocks in the edge feature map, wherein the pipeline image block is the first image block whose recognition result is a pipeline.

[0020] In a possible implementation manner, performing edge characterization processing on the first intermediate real scene image to obtain an edge feature image includes:

[0021] Performing color inversion processing on the first intermediate real scene image to obtain a first color inversion image;

[0022] For each pixel in the first inverted color image, a minimum value search is performed with 1 pixel as a radius, and the obtained minimum value is used to replace the pixel value to obtain a second inverted color image;

[0023] Sum each pixel value in the first inverted color image and the pixel value at the corresponding position taken from the second inverted color image, and construct a sum image using the obtained sum;

[0024] Setting the pixel values ​​in the sum image that are greater than the first threshold value as the maximum value to obtain an extreme value sum image;

[0025] The extreme value and the island pixels in the image are set to the maximum value to obtain an edge feature map, wherein the island pixels are pixels without edge pixels within a preset radius, and the edge pixels are pixel values ​​lower than the second threshold.

[0026] In a possible implementation, the recognition model is constructed based on a plurality of samples, including:

[0027] An initial model and a plurality of image block samples are obtained, wherein each image block sample includes a plurality of image blocks and image content labels, and the initial model is:

[0028]

[0029] In the formula, The output of the model is is the number of rows of hidden nodes, The output node coefficients, For the Line The first column node coefficients, For the Line The output of the middle node of the column, For the input variables, is the total number of input variables, is the total number of columns of intermediate nodes, is a natural constant, is the total number of semantic feature vector elements, To obtain the maximum value function, For the Input image patches;

[0030] Erratically extract samples from the plurality of image block samples and input them into the initial model;

[0031] Determining a fitting residual of the initial model according to an output of the initial model and an image content label of an image block sample;

[0032] If the fitting residual is greater than the fitting deviation threshold, a back propagation method is used to adjust multiple coefficients of the initial model, and the process jumps to the step of traversally taking samples from the multiple image block samples and inputting them into the initial model;

[0033] Otherwise, the initial model is used as the recognition model.

[0034] In a possible implementation, the pipeline shape and position parameters include: the image position and image area of ​​the pipeline image in the target real scene image, and the determining of the multiple pipeline node positions according to the pipeline shape and position parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group includes:

[0035] For each image group, perform the following steps:

[0036] Extract the image position, image area and image acquisition position of each image and construct them into an image array;

[0037] Randomly select an image array from multiple image arrays as a reference array;

[0038] Determine a plurality of position change arrays according to the reference array and other plurality of image arrays, wherein the change arrays include image position change values, image area change values, and image acquisition position change values;

[0039] The reference array and the plurality of position change arrays are input into a positioning equation, and the position of the pipeline node is determined according to the solution of the positioning equation.

[0040] In one possible implementation, the positioning equation is:

[0041]

[0042] In the formula, is the first dimension coordinate of the middle position, is the first dimension change value of the image acquisition position, is the first dimension coordinate of the reference image, is the first dimension coordinate of the pipeline node position, is the second dimension coordinate of the middle position, is the second dimensional change value of the image acquisition position, is the second dimension coordinate of the reference image, is the second dimension coordinate of the pipeline node position, is the third-dimensional coordinate of the middle position, is the third-dimensional change value of the image acquisition position, is the third-dimensional coordinate of the reference image, is the third-dimensional coordinate of the pipeline node position, is the image area change value, is the maximum number of the first index, For the The first coefficient, is the first bias coefficient, is the first dimension change value of the image position, is the maximum number of the second index, For the The second coefficient, is the second bias coefficient, is the second dimension change value of the image position, is the maximum number of the third index, For the The third coefficient, is the third bias coefficient.

[0043] In a possible implementation manner, constructing a pipeline path according to the plurality of pipeline node positions includes:

[0044] Get the pipeline category of each pipeline node;

[0045] The pipeline node positions belonging to the same pipeline category are grouped into a node position set;

[0046] A plurality of pipeline paths are constructed according to the plurality of node position sets, wherein each pipeline path corresponds to a node position set.

[0047] In a second aspect, an embodiment of the present invention provides an existing park pipe network integrated control device based on BIM, which is used to implement the existing park pipe network integrated control method based on BIM as described in the first aspect or any possible implementation of the first aspect above, and the existing park pipe network integrated control device based on BIM includes:

[0048] A real scene image acquisition module is used to acquire multiple real scene images, wherein each real scene image corresponds to an image acquisition position;

[0049] A pipeline recognition module, used to recognize the multiple real-scene images, obtain multiple target real-scene images and multiple pipeline shape and position parameters, wherein each pipeline shape and position parameter corresponds to a target real-scene image, and the pipeline shape and position parameter represents the shape and position characteristics of the pipeline image in the target real-scene image;

[0050] A pipeline position determination module, used to group the multiple target real scene images into multiple image groups according to the image acquisition positions, and determine multiple pipeline node positions according to the pipeline shape and position parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group, wherein each pipeline node position corresponds to one image group;

[0051] as well as,

[0052] The pipeline path planning module is used to construct a pipeline path according to the multiple pipeline node positions.

[0053] In a third aspect, an embodiment of the present invention provides an electronic device, comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the steps of the method described in the first aspect or any possible implementation method of the first aspect.

[0054] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described in the first aspect or any possible implementation of the first aspect are implemented.

[0055] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0056] The present invention provides an implementation method for the comprehensive management and control of an existing park pipeline network based on BIM, which first obtains a plurality of real-life images, wherein each real-life image corresponds to an image acquisition position; then the plurality of real-life images are identified to obtain a plurality of target real-life images and a plurality of pipeline shape and position parameters, wherein each pipeline shape and position parameter corresponds to a target real-life image, and the pipeline shape and position parameters characterize the shape and position characteristics of the pipeline image in the target real-life image; then the plurality of target real-life images are grouped into a plurality of image groups according to the image acquisition position, and a plurality of pipeline node positions are determined according to the pipeline shape and position parameters of the plurality of images in the image group and the image acquisition positions of the plurality of images in the image group, wherein each pipeline node position corresponds to an image group; finally, a pipeline path is constructed according to the plurality of pipeline node positions. The implementation manner of the present invention identifies pipelines based on real-life images, extracts shape and position parameters of the pipelines in the real-life images, locates pipeline node positions based on the shape and position parameters of the pipelines in multiple real-life images and the shooting positions, and finally constructs pipeline paths based on multiple pipeline node positions. The implementation manner of the present invention constructs a pipeline network path model through the pipeline real-life images, has fewer manual survey and modeling links, and is highly efficient. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, 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 labor.

[0058] Figure 1 It is a flow chart of a comprehensive management and control method of an existing park pipe network based on BIM provided by an embodiment of the present invention;

[0059] Figure 2 It is a schematic diagram of the process of identifying pipelines through real-view images provided by an embodiment of the present invention;

[0060] Figure 3 It is a functional block diagram of an existing park pipe network comprehensive control device based on BIM provided by an embodiment of the present invention;

[0061] Figure 4 It is a functional block diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In the following description, specific details such as specific system structures and technologies are provided for the purpose of illustration rather than limitation so as to provide a thorough understanding of the embodiments of the present invention. However, it should be clear to those skilled in the art that the present invention may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, and methods are omitted so as not to obscure the description of the present invention with unnecessary details.

[0063] In order to make the purpose, technical solutions and advantages of the present invention more clear, a specific implementation method will be described below in conjunction with the accompanying drawings.

[0064] The following is a detailed description of an embodiment of the present invention. This example is implemented based on the technical solution of the present invention, and provides a detailed implementation method and a specific operation process, but the protection scope of the present invention is not limited to the following embodiments.

[0065] Figure 1 A flow chart of a comprehensive management and control method for an existing park pipeline network based on BIM provided in an embodiment of the present invention.

[0066] like Figure 1 As shown, it shows a flowchart of the implementation method of the BIM-based integrated management and control method of the existing park pipe network provided by the embodiment of the present invention, which is described in detail as follows:

[0067] In step 101, a plurality of real scene images are obtained, wherein each real scene image corresponds to an image acquisition position.

[0068] In step 102, the multiple real scene images are identified to obtain multiple target real scene images and multiple pipeline shape and position parameters, wherein each pipeline shape and position parameter corresponds to a target real scene image, and the pipeline shape and position parameter represents the shape and position characteristics of the pipeline image in the target real scene image.

[0069] In some implementations, identifying the multiple real-life images includes:

[0070] For each real scene, perform the following steps:

[0071] Adjusting multiple pixel values ​​of the real scene image to a preset distribution range to obtain a first intermediate real scene image;

[0072] Performing edge characterization processing on the first intermediate real scene image to obtain an edge feature image;

[0073] Segmenting the edge feature map once to obtain a plurality of first image blocks;

[0074] Perform secondary segmentation on each first image block, and construct the obtained multiple second image blocks into a second image block set;

[0075] Inputting the plurality of second image block sets into the recognition model respectively to obtain a plurality of recognition results, wherein each recognition result corresponds to a first image block;

[0076] The pipeline shape parameters are determined according to the positions and areas occupied by the plurality of pipeline image blocks in the edge feature map, wherein the pipeline image block is the first image block whose recognition result is a pipeline.

[0077] In some implementations, performing edge characterization processing on the first intermediate real scene image to obtain an edge feature image includes:

[0078] Performing color inversion processing on the first intermediate real scene image to obtain a first color inversion image;

[0079] For each pixel in the first inverted color image, a minimum value search is performed with 1 pixel as a radius, and the obtained minimum value is used to replace the pixel value to obtain a second inverted color image;

[0080] Sum each pixel value in the first inverted color image and the pixel value at the corresponding position taken from the second inverted color image, and construct a sum image using the obtained sum;

[0081] Setting the pixel values ​​in the sum image that are greater than the first threshold value as the maximum value to obtain an extreme value sum image;

[0082] The extreme value and the island pixels in the image are set to the maximum value to obtain an edge feature map, wherein the island pixels are pixels without edge pixels within a preset radius, and the edge pixels are pixel values ​​lower than the second threshold.

[0083] In some embodiments, the recognition model is constructed based on multiple samples, including:

[0084] An initial model and a plurality of image block samples are obtained, wherein each image block sample includes a plurality of image blocks and image content labels, and the initial model is:

[0085]

[0086] In the formula, The output of the model is is the number of rows of hidden nodes, The output node coefficients, For the Line The first column node coefficients, For the Line The output of the middle node of the column, For the input variables, is the total number of input variables, is the total number of columns of intermediate nodes, is a natural constant, is the total number of semantic feature vector elements, To obtain the maximum value function, For the Input image patches;

[0087] Erratically extract samples from the plurality of image block samples and input them into the initial model;

[0088] Determining a fitting residual of the initial model according to an output of the initial model and an image content label of an image block sample;

[0089] If the fitting residual is greater than the fitting deviation threshold, a back propagation method is used to adjust multiple coefficients of the initial model, and the process jumps to the step of traversally taking samples from the multiple image block samples and inputting them into the initial model;

[0090] Otherwise, the initial model is used as the recognition model.

[0091] Exemplarily, the present invention uses a real-life image with a shooting position mark to identify the pipeline, and then locates the pipeline through the position and size of the pipeline image in the real-life image combined with the shooting position mark. The pipeline position actually obtained is the position of the pipeline node. After the pipeline node position is marked, the pipeline nodes are classified according to the pipeline type, and the pipeline nodes of each class are connected to obtain the path of the pipeline.

[0092] To realize the above concept, the embodiment of the present invention identifies the pipeline in the real scene image. In the identification method, the pixel value of the real scene image is first adjusted so that the pixel value of the real scene image is distributed in a predetermined interval. In an application scenario, the real scene image is a grayscale image, and after the pixel value is adjusted, the distribution intervals of different grayscale values ​​conform to the predetermined interval.

[0093] Then, the real scene image after the pixel value is adjusted is subjected to edge processing, in other words, the edges contained in the real scene image are extracted to obtain an edge image. During the edge processing, the real scene image with the pixel value adjusted is first subjected to inversion processing to obtain an inversion image. Then, traversally, for each pixel in the first inversion image, a minimum value search is performed with a radius of 1 pixel, and the pixel value is replaced by the minimum value obtained by the search, thereby obtaining a second inversion image. Next, traversally, each pixel value in the first inversion image is summed with the pixel value corresponding to the pixel position of the first inversion image taken from the second inversion image, thereby obtaining a sum image (the first inversion image and the second inversion image pixel values ​​are summed one by one, and the image is obtained). Then, the pixel values ​​in the sum image that are greater than the first threshold are set to the maximum value to obtain an extreme value sum image. For example, if the first threshold is 200, then all pixel values ​​greater than 200 are set to 255. Finally, the extreme values ​​and island pixels in the image are set to the maximum value to obtain the final edge feature map. Island pixels are pixels without edge pixels within the preset radius, and edge pixels are pixel values ​​below the second threshold. For example, for pixel values ​​below 50, search with a radius of 3 pixels. If there are no pixels with pixel values ​​below 50 within the radius, then the pixel is set to the maximum value of 255.

[0094] After the real scene image is edged, it can be processed as follows Figure 2 The schematic diagram of the process of identifying pipelines through a real-life image is shown to identify the pipelines in the real-life image.

[0095] Specifically, first, the edge feature map 201 is segmented once to obtain multiple first image blocks 202; then each first image block 202 is segmented twice, and the multiple second image blocks obtained are constructed into a second image block set 203; then, the multiple second image block sets 203 are respectively input into the recognition model 204 to obtain multiple recognition results. It can be seen from the figure that each recognition result corresponds to a first image block 202; finally, according to the positions and areas occupied by the multiple pipeline image blocks in the edge feature map 201, the pipeline shape and position parameters are determined, and the pipeline image block is the first image block whose recognition result is a pipeline.

[0096] Here we have to talk about the construction of the recognition model. The recognition model is based on the initial model and is obtained by modifying the model parameters through sample iteration. The initial model is:

[0097]

[0098] In the formula, The output of the model is is the number of rows of hidden nodes, The output node coefficients, For the Line The first column node coefficients, For the Line The output of the middle node of the column, For the input variables, is the total number of input variables, is the total number of columns of intermediate nodes, is a natural constant, is the total number of semantic feature vector elements, To obtain the maximum value function, For the An input image patch.

[0099] In terms of samples, the image block samples include multiple image blocks and image content labels. When using image block samples to modify model parameters, firstly, samples are traversed from multiple image block samples and input into the initial model. Then, the fitting residual of the initial model is determined according to the output of the initial model and the image content label of the image block sample; if the fitting residual is greater than the fitting deviation threshold, the back propagation method is used to adjust multiple coefficients of the initial model, and jump to the step of traversing samples from the multiple image block samples and inputting them into the initial model; otherwise, the initial model is used as the recognition model. The construction of the recognition model is realized through the above steps.

[0100] In step 103, the multiple target real scene images are grouped into multiple image groups according to the image acquisition positions, and multiple pipeline node positions are determined according to the pipeline shape parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group, wherein each pipeline node position corresponds to an image group.

[0101] In some embodiments, the pipeline shape and position parameters include: the image position and image area of ​​the pipeline image in the target real scene image, and the determining of the multiple pipeline node positions according to the pipeline shape and position parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group includes:

[0102] For each image group, perform the following steps:

[0103] Extract the image position, image area and image acquisition position of each image and construct them into an image array;

[0104] Randomly select an image array from multiple image arrays as a reference array;

[0105] Determine a plurality of position change arrays according to the reference array and other plurality of image arrays, wherein the change arrays include image position change values, image area change values, and image acquisition position change values;

[0106] The reference array and the plurality of position change arrays are input into a positioning equation, and the position of the pipeline node is determined according to the solution of the positioning equation.

[0107] In some embodiments, the positioning equation is:

[0108]

[0109] In the formula, is the first dimension coordinate of the middle position, is the first dimension change value of the image acquisition position, is the first dimension coordinate of the reference image, is the first dimension coordinate of the pipeline node position, is the second dimension coordinate of the middle position, is the second dimensional change value of the image acquisition position, is the second dimension coordinate of the reference image, is the second dimension coordinate of the pipeline node position, is the third-dimensional coordinate of the middle position, is the third-dimensional change value of the image acquisition position, is the third-dimensional coordinate of the reference image, is the third-dimensional coordinate of the pipeline node position, is the image area change value, is the maximum number of the first index, For the The first coefficient, is the first bias coefficient, is the first dimension change value of the image position, is the maximum number of the second index, For the The second coefficient, is the second bias coefficient, is the second dimension change value of the image position, is the maximum number of the third index, For the The third coefficient, is the third bias coefficient.

[0110] Exemplarily, in the embodiment of the present invention, the location of the pipeline node is determined by the pipeline image position, pipeline image area and image acquisition position of the image. Specifically, firstly, multiple target real scene images are grouped into multiple image groups according to the image acquisition position, that is, the shooting positions of the real scene images in the image group are relatively close.

[0111] In fact, the implementation mode of the present invention is to construct multiple arrays based on multiple images in an image group, input the arrays into the positioning equation, and obtain the position of the pipeline node according to the solution of the equation.

[0112] The positioning equation is:

[0113]

[0114] In the formula, is the first dimension coordinate of the middle position, is the first dimension change value of the image acquisition position, is the first dimension coordinate of the reference image, is the first dimension coordinate of the pipeline node position, is the second dimension coordinate of the middle position, is the second dimensional change value of the image acquisition position, is the second dimension coordinate of the reference image, is the second dimension coordinate of the pipeline node position, is the third-dimensional coordinate of the middle position, is the third-dimensional change value of the image acquisition position, is the third-dimensional coordinate of the reference image, is the third-dimensional coordinate of the pipeline node position, is the image area change value, is the maximum number of the first index, For the The first coefficient, is the first bias coefficient, is the first dimension change value of the image position, is the maximum number of the second index, For the The second coefficient, is the second bias coefficient, is the second dimension change value of the image position, is the maximum number of the third index, For the The third coefficient, is the third bias coefficient.

[0115] In the above formula, the coefficients are set according to the camera parameters. One solution is to set an initial value based on the camera parameters, and then adjust it according to the sample to obtain a more accurate value.

[0116] It can be seen that the image group requires at least three real-life images with the same pipeline. We randomly select a real-life image from this image group, use the image array of this real-life image as the reference array, and perform data subtraction operations on the image arrays of other real-life images in other image groups and the reference array. The difference array obtained is the position change array. In other words, the position change array includes the image position change value, the image area change value, and the image acquisition position change value. Input the reference array and the position change array into the above equation, solve the equation, and get the position of the pipeline node.

[0117] In step 104, a pipeline path is constructed according to the plurality of pipeline node positions.

[0118] In some embodiments, constructing a pipeline path according to the plurality of pipeline node positions includes:

[0119] Get the pipeline category of each pipeline node;

[0120] The pipeline node positions belonging to the same pipeline category are grouped into a node position set;

[0121] A plurality of pipeline paths are constructed according to the plurality of node position sets, wherein each pipeline path corresponds to a node position set.

[0122] Exemplarily, finally, according to the pipeline category of the pipeline node, the pipeline node positions are grouped into a node position set, and the pipeline path is constructed according to the node positions of the pipeline position set.

[0123] The present invention provides an implementation method for the comprehensive management and control of an existing park pipeline network based on BIM, which first obtains a plurality of real-life images, wherein each real-life image corresponds to an image acquisition position; then the plurality of real-life images are identified to obtain a plurality of target real-life images and a plurality of pipeline shape and position parameters, wherein each pipeline shape and position parameter corresponds to a target real-life image, and the pipeline shape and position parameters characterize the shape and position characteristics of the pipeline image in the target real-life image; then the plurality of target real-life images are grouped into a plurality of image groups according to the image acquisition position, and a plurality of pipeline node positions are determined according to the pipeline shape and position parameters of the plurality of images in the image group and the image acquisition positions of the plurality of images in the image group, wherein each pipeline node position corresponds to an image group; finally, a pipeline path is constructed according to the plurality of pipeline node positions. The implementation manner of the present invention identifies pipelines based on real-life images, extracts shape and position parameters of the pipelines in the real-life images, locates pipeline node positions based on the shape and position parameters of the pipelines in multiple real-life images and the shooting positions, and finally constructs pipeline paths based on multiple pipeline node positions. The implementation manner of the present invention constructs a pipeline network path model through the pipeline real-life images, has fewer manual survey and modeling links, and is highly efficient.

[0124] It should be understood that the size of the serial numbers of the steps in the above implementation does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the implementation method of the present invention.

[0125] The following is an implementation of the device of the present invention. For details not described in detail, reference may be made to the corresponding method implementation described above.

[0126] Figure 3 This is a functional block diagram of the BIM-based integrated management and control device for an existing park network provided by an embodiment of the present invention, referring to Figure 3 The BIM-based integrated management and control device for the existing park pipe network includes: a real-view image acquisition module 301, a pipe identification module 302, a pipe position determination module 303, and a pipe path planning module 304, wherein:

[0127] A real scene image acquisition module 301 is used to acquire multiple real scene images, wherein each real scene image corresponds to an image acquisition position;

[0128] The pipeline recognition module 302 is used to recognize the multiple real-scene images, obtain multiple target real-scene images and multiple pipeline shape and position parameters, wherein each pipeline shape and position parameter corresponds to a target real-scene image, and the pipeline shape and position parameter represents the shape and position characteristics of the pipeline image in the target real-scene image;

[0129] The pipeline position determination module 303 is used to group the multiple target real scene images into multiple image groups according to the image acquisition positions, and determine multiple pipeline node positions according to the pipeline shape and position parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group, wherein each pipeline node position corresponds to one image group;

[0130] The pipeline path planning module 304 is used to construct a pipeline path according to the multiple pipeline node positions.

[0131] Figure 4 is a functional block diagram of an electronic device provided by an embodiment of the present invention. Figure 4 As shown, the electronic device 4 of this embodiment includes: a processor 400 and a memory 401, wherein the memory 401 stores a computer program 402 that can be run on the processor 400. When the processor 400 executes the computer program 402, the steps in the above-mentioned BIM-based existing park pipe network comprehensive management and control method and implementation method are implemented, for example Figure 1 Steps 101 to 104 are shown.

[0132] Exemplarily, the computer program 402 may be divided into one or more modules / units, and the one or more modules / units are stored in the memory 401 and executed by the processor 400 to implement the present invention.

[0133] The electronic device 4 may be a computing device such as a desktop computer, a notebook, a PDA, or a cloud server. The electronic device 4 may include, but is not limited to, a processor 400 and a memory 401. Those skilled in the art will appreciate that Figure 4 It is only an example of the electronic device 4 and does not constitute a limitation of the electronic device 4. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the electronic device 4 may also include input and output devices, network access devices, buses, etc.

[0134] The processor 400 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0135] The memory 401 may be an internal storage unit of the electronic device 4, such as a hard disk or memory of the electronic device 4. The memory 401 may also be an external storage device of the electronic device 4, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the electronic device 4. Further, the memory 401 may also include both an internal storage unit and an external storage device of the electronic device 4. The memory 401 is used to store the computer program 402 and other programs and data required by the electronic device 4. The memory 401 may also be used to temporarily store data that has been output or is to be output.

[0136] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the implementation method can be integrated into a processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method implementation method, which will not be repeated here.

[0137] In the above-mentioned embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0138] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of the present invention.

[0139] In the embodiments provided by the present invention, it should be understood that the disclosed devices / electronic devices and methods can be implemented in other ways. For example, the device / electronic device embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units 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 through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0140] 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 present embodiment.

[0141] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0142] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned implementation method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by the processor, the steps of the above-mentioned various methods and device implementation methods can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device that can carry the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium.

[0143] The above-described embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A comprehensive management and control method for existing park pipe networks based on BIM, characterized in that: include: Acquire multiple real scene images, wherein each real scene image corresponds to an image acquisition position; Identify the multiple real-scene images to obtain multiple target real-scene images and multiple pipeline shape and position parameters, wherein each pipeline shape and position parameter corresponds to a target real-scene image, and the pipeline shape and position parameter represents the shape and position characteristics of the pipeline image in the target real-scene image; The multiple target real scene images are grouped into multiple image groups according to the image acquisition positions, and multiple pipeline node positions are determined according to the pipeline shape and position parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group, wherein each pipeline node position corresponds to one image group; Constructing a pipeline path according to the plurality of pipeline node positions; in, The identifying of the multiple real scene images includes: For each real scene, perform the following steps: Adjusting multiple pixel values ​​of the real scene image to a preset distribution range to obtain a first intermediate real scene image; Performing edge characterization processing on the first intermediate real scene image to obtain an edge feature image; Segmenting the edge feature map once to obtain a plurality of first image blocks; Perform secondary segmentation on each first image block, and construct the obtained multiple second image blocks into a second image block set; Inputting the plurality of second image block sets into the recognition model respectively to obtain a plurality of recognition results, wherein each recognition result corresponds to a first image block; Determine the pipeline shape and position parameters according to the positions and areas occupied by the plurality of pipeline image blocks in the edge feature map, wherein the pipeline image block is the first image block whose recognition result is a pipeline; in, The recognition model is constructed based on multiple samples, including: An initial model and a plurality of image block samples are obtained, wherein each image block sample includes a plurality of image blocks and image content labels, and the initial model is: In the formula, The output of the model is is the number of rows of hidden nodes, The output node coefficients, For the Line The first column node coefficients, For the Line The output of the middle node of the column, For the input variables, is the total number of input variables, is the total number of columns of intermediate nodes, is a natural constant, is the total number of semantic feature vector elements, To obtain the maximum value function, For the Input image patches; Erratically extract samples from the plurality of image block samples and input them into the initial model; Determining a fitting residual of the initial model according to an output of the initial model and an image content label of an image block sample; If the fitting residual is greater than the fitting deviation threshold, a back propagation method is used to adjust multiple coefficients of the initial model, and the process jumps to the step of traversally taking samples from the multiple image block samples and inputting them into the initial model; Otherwise, the initial model is used as the recognition model.

2. The BIM-based comprehensive management and control method for existing park pipe networks according to claim 1 is characterized in that: The performing edge feature processing on the first intermediate real scene image to obtain an edge feature image includes: Performing color inversion processing on the first intermediate real scene image to obtain a first color inversion image; For each pixel in the first inverted color image, a minimum value search is performed with 1 pixel as a radius, and the obtained minimum value is used to replace the pixel value to obtain a second inverted color image; Sum each pixel value in the first inverted color image and the pixel value at the corresponding position taken from the second inverted color image, and construct a sum image using the obtained sum; Setting the pixel values ​​in the sum image that are greater than the first threshold value as the maximum value to obtain an extreme value sum image; The extreme value and the island pixels in the image are set to the maximum value to obtain an edge feature map, wherein the island pixels are pixels without edge pixels within a preset radius, and the edge pixels are pixel values ​​lower than the second threshold.

3. The BIM-based comprehensive management and control method for existing park pipe networks according to claim 1 is characterized in that: The pipeline shape and position parameters include: the image position and image area of ​​the pipeline image in the target real scene image. The determining of the multiple pipeline node positions according to the pipeline shape and position parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group includes: For each image group, perform the following steps: Extract the image position, image area and image acquisition position of each image and construct them into an image array; Randomly select an image array from multiple image arrays as a reference array; Determine a plurality of position change arrays according to the reference array and other plurality of image arrays, wherein the change arrays include image position change values, image area change values, and image acquisition position change values; The reference array and the plurality of position change arrays are input into a positioning equation, and the position of the pipeline node is determined according to the solution of the positioning equation.

4. The BIM-based comprehensive management and control method for existing park pipe networks according to claim 3 is characterized in that: The positioning equation is: In the formula, is the first dimension coordinate of the middle position, is the first dimension change value of the image acquisition position, is the first dimension coordinate of the reference image, is the first dimension coordinate of the pipeline node position, is the second dimension coordinate of the middle position, is the second dimensional change value of the image acquisition position, is the second dimension coordinate of the reference image, is the second dimension coordinate of the pipeline node position, is the third-dimensional coordinate of the middle position, is the third-dimensional change value of the image acquisition position, is the third-dimensional coordinate of the reference image, is the third-dimensional coordinate of the pipeline node position, is the image area change value, is the maximum number of first indices, For the The first coefficient, is the first bias coefficient, is the first dimension change value of the image position, is the maximum number of the second index, For the The second coefficient, is the second bias coefficient, is the second dimension change value of the image position, is the maximum number of the third index, For the The third coefficient, is the third bias coefficient.

5. The BIM-based comprehensive management and control method for existing park pipe networks according to any one of claims 1 to 4, characterized in that: The step of constructing a pipeline path according to the plurality of pipeline node positions includes: Get the pipeline category of each pipeline node; The pipeline node positions belonging to the same pipeline category are grouped into a node position set; A plurality of pipeline paths are constructed according to the plurality of node position sets, wherein each pipeline path corresponds to a node position set.

6. A BIM-based integrated management and control device for existing park pipe networks, characterized in that: Used to implement the BIM-based integrated management and control method for an existing park pipe network as described in any one of claims 1 to 5, the BIM-based integrated management and control device for an existing park pipe network comprises: A real scene image acquisition module is used to acquire multiple real scene images, wherein each real scene image corresponds to an image acquisition position; A pipeline recognition module, used to recognize the multiple real-scene images, obtain multiple target real-scene images and multiple pipeline shape and position parameters, wherein each pipeline shape and position parameter corresponds to a target real-scene image, and the pipeline shape and position parameter represents the shape and position characteristics of the pipeline image in the target real-scene image; A pipeline position determination module, used to group the multiple target real scene images into multiple image groups according to the image acquisition positions, and determine multiple pipeline node positions according to the pipeline shape and position parameters of the multiple images in the image group and the image acquisition positions of the multiple images in the image group, wherein each pipeline node position corresponds to one image group; as well as, The pipeline path planning module is used to construct a pipeline path according to the multiple pipeline node positions.

7. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images