Underground pipe gallery visualization method and device for intelligent pipe gallery monitoring

Abstract

The invention relates to the technical field of image processing, in particular to an underground pipe gallery visualization method and device for intelligent pipe gallery monitoring, and the method comprises the steps: determining the point cloud data of a target region of a pipeline structure of a current layer in an underground pipe gallery; determining point cloud data outliers in the point cloud data of the target area and corresponding outlier data sequences of the layer; determining an adjacent pipeline structure layer of the pipeline structure and a corresponding adjacent conventional data sequence; determining a fusion error estimation value of the point cloud data of the upper surface and the lower surface of the point cloud data of the target area by using the outlier data sequence of the layer and the adjacent conventional data sequence; and adjusting the matching range scale of the point cloud data fusion of the upper and lower surfaces by using the fusion error estimation value. Through the underground pipe gallery visualization method for intelligent pipe gallery monitoring, the integrity and accuracy of underground pipe gallery visualization imaging are improved, and the difficulty of underground pipe gallery maintenance and troubleshooting is reduced.

Description

Technical Field

[0001] The present invention relates to the field of image processing technology, and in particular to an underground pipe gallery visualization method and device for smart pipe gallery monitoring. Background Art

[0002] The smart tunnel monitoring system is an important part of modern urban infrastructure. Its main goal is to use technical means to conduct real-time monitoring, data collection, analysis and early warning of the equipment and environment in the underground tunnel. The design of visualization methods and devices can help managers understand the operation status of underground tunnels more intuitively, thereby improving the efficiency of maintenance and emergency response.

[0003] The underground pipe gallery visualization device monitors the pipe gallery facilities in real time through spatial imaging technology. However, due to the poor lighting conditions inside the pipe gallery and the complex pipeline layout, there are often occlusions between key nodes, which leads to blanks or distortions in the imaging process, thus affecting the integrity and accuracy of the visualization imaging, making it more difficult to accurately locate the source of the pipe gallery fault, thereby increasing the difficulty of maintenance and troubleshooting. Summary of the invention

[0004] In order to solve the technical problem of low imaging integrity and accuracy of underground pipe corridors during imaging, the purpose of the present invention is to provide an underground pipe corridor visualization method and device for intelligent pipe corridor monitoring. The technical solutions adopted are as follows: The present invention provides an underground pipe gallery visualization method for smart pipe gallery monitoring, the method comprising: Determine the target area point cloud data of the pipeline structure on this layer in the underground pipeline gallery; Determine the outlier points of the point cloud data in the target area and their corresponding outlier data sequences in the current layer; Determine the adjacent pipeline structure layer of the pipeline structure at this layer and its corresponding adjacent conventional data sequence; Using the outlier data sequence of this layer and the adjacent regular data sequence, the fusion error estimation value of the upper and lower surface point cloud data of the target area point cloud data is determined; Using the fusion error estimate, adjust the matching range scale of the upper and lower surface point cloud data fusion; Among them, the point cloud data of the target area is obtained based on laser scanning.

[0005] Furthermore, the step of determining the outliers of the point cloud data in the target area point cloud data includes: Determine the curvature of the point cloud plane at the target data point in the point cloud data of the target area; Determine the mean distance between the target data point and the adjacent data points in the point cloud data of the target area; The point cloud plane curvature and the mean distance are used to determine the outliers in the point cloud data of the target area.

[0006] Furthermore, the step of determining the curvature of the point cloud plane at the target data point in the point cloud data of the target area includes: Determine the normal direction angle difference between the target data point and the adjacent data points in the point cloud data of the target area; The curvature of the point cloud plane at the target data point is determined by using the angle difference of the normal direction.

[0007] Further, the step of determining the outliers of the point cloud data in the point cloud data of the target area by using the point cloud plane curvature and the distance mean includes: The noise coefficient of the target data point is calculated using the point cloud plane curvature and distance mean; The noise coefficient is compared with a preset threshold to determine whether the target data point is an outlier point in the point cloud data.

[0008] Furthermore, the step of determining the outlier points of the point cloud data in the target area and the corresponding outlier data sequences of the current layer includes: All point cloud data outliers are chained to obtain a point cloud data outlier set with a chain structure; The distances between the outlier points in the point cloud data outlier point set with a chain structure are obtained to obtain the outlier data sequence of this layer.

[0009] Furthermore, the step of determining the adjacent pipeline structure layer of the pipeline structure at this layer and its corresponding adjacent regular data sequence includes: Determine the lower surface of the adjacent upper layer pipeline structure of the current layer pipeline structure and the corresponding adjacent lower surface conventional data sequence; Determine the upper surface of the adjacent lower layer pipeline structure of the current layer pipeline structure and the corresponding adjacent upper surface conventional data sequence.

[0010] Further, the step of determining the fusion error estimation value of the upper and lower surface point cloud data of the target area point cloud data by using the outlier data sequence of the current layer and the adjacent regular data sequence includes: Determine a first data difference between an upper surface outlier data sequence and an adjacent upper surface regular data sequence in the outlier data sequence of the current layer; Determine a second data difference between a lower surface outlier data sequence and an adjacent lower surface regular data sequence in the outlier data sequence of the current layer; The first data difference and the second data difference are used to calculate the estimated value of the fusion error of the upper and lower surface point cloud data of the target area point cloud data.

[0011] Further, the step of adjusting the matching range scale of the upper and lower surface point cloud data fusion using the fusion error estimation value includes: Determine the regional point cloud coverage factor of the target area; The regional point cloud fusion correction scale is calculated using the fusion error estimate and the regional point cloud coverage coefficient. The regional point cloud fusion correction scale is used to adjust the initial matching range scale of the upper and lower surface point cloud data fusion to obtain the corrected matching range scale.

[0012] Furthermore, the step of determining the regional point cloud coverage factor of the target area includes: Determine a set of all pipeline structure areas adjacent to the target area; Determine the target area point cloud density of the target area and the average of the area point cloud density of all pipeline structure area sets; The regional point cloud coverage coefficient of the target area point cloud data is calculated using the target area point cloud density and the regional point cloud density mean.

[0013] The present invention also provides an underground pipe gallery visualization device for smart pipe gallery monitoring, the device is used to implement the underground pipe gallery visualization method for smart pipe gallery monitoring as described in any one of the above items; the device comprises: Data platform, IoT platform, tunnel security integrated management cloud platform and user interface module; Among them, the tunnel safety integrated management platform is used for: Determine the target area point cloud data of the pipeline structure on this layer in the underground pipeline gallery; Determine the outlier points of the point cloud data in the target area and their corresponding outlier data sequences in the current layer; Determine the adjacent pipeline structure layer of the pipeline structure at this layer and its corresponding adjacent conventional data sequence; Using the outlier data sequence of this layer and the adjacent regular data sequence, the fusion error estimation value of the upper and lower surface point cloud data of the target area point cloud data is determined; The matching range scale of the upper and lower surface point cloud data fusion is adjusted using the fusion error estimate.

[0014] The present invention has the following beneficial effects: The present invention analyzes the collected point cloud data to evaluate the possible errors that may be generated when the point cloud data is fused at different angles in the pipeline area. By identifying and quantifying the systematic errors and random errors caused by factors such as the environment and angle, the present invention proposes a regional point cloud data fusion correction scale. Using this correction scale, the matching range of the upper and lower surface point cloud data points can be adjusted, that is, when matching the upper surface point cloud data points with the lower surface point cloud data points, the matching range is appropriately expanded, thereby improving the accuracy of the fusion result, thereby improving the integrity and accuracy of the visualization imaging of the underground pipe gallery, and reducing the difficulty of underground pipe gallery maintenance and troubleshooting. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are 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.

[0016] Figure 1 A flowchart of the steps of an underground pipe gallery visualization method for smart pipe gallery monitoring provided by one embodiment of the present invention; Figure 2 A detailed flow chart of step S2 in an underground pipe gallery visualization method for smart pipe gallery monitoring provided by one embodiment of the present invention; Figure 3 A detailed flow chart of step S5 in a method for visualizing an underground pipe gallery for intelligent pipe gallery monitoring provided by one embodiment of the present invention; Figure 4 A schematic diagram of the normal direction of point cloud data involved in an underground pipe gallery visualization method for smart pipe gallery monitoring provided by one embodiment of the present invention; Figure 5 It is a structural schematic diagram of the hardware operating environment of an underground pipe gallery visualization device for smart pipe gallery monitoring involved in an embodiment of the present invention; Figure 6 This is a schematic diagram of the framework structure of an underground tunnel visualization device for smart tunnel monitoring involved in an embodiment of the present invention. DETAILED DESCRIPTION

[0017] 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 specific implementation method, structure, features and effects of an underground corridor visualization method for intelligent corridor monitoring proposed by the present invention 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.

[0018] 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.

[0019] The following is a detailed description of a specific solution of an underground pipe gallery visualization method for smart pipe gallery monitoring provided by the present invention in conjunction with the accompanying drawings.

[0020] Embodiment 1: For the underground pipe gallery visualization method for intelligent pipe gallery monitoring provided by the present invention, please refer to Figure 1 , which shows a flowchart of the steps of an underground tunnel visualization method for smart tunnel monitoring provided by an embodiment of the present invention.

[0021] The method comprises: Step S1, determining the target area point cloud data of the pipeline structure of this layer in the underground pipe gallery; The laser scanner can be first installed between two adjacent pipe structures, such as between upper and lower adjacent pipe structures. In this way, the laser scanner can scan the lower surface of the upper adjacent pipe structure and the upper surface of the lower adjacent pipe structure, and use the upper and lower surfaces here as the boundaries of the pipe structure of this layer.

[0022] The sensor network deploys a laser scanner matrix in each layer of the pipeline structure in the underground pipeline gallery. A single laser scanner can collect point cloud data on the upper and lower surfaces respectively; Taking a single laser scanner as an example, the laser scanner emits laser pulses and measures the flight time of the reflected echo to obtain the distance data (point cloud) of the surface of an object within a certain scanning range. Through multiple scans, a high-density three-dimensional point cloud is generated to obtain the point cloud data of the target area of ​​the pipeline structure at this layer. Then, combined with all laser scanners at this layer, the point cloud data of all pipeline structure areas at this layer can be obtained, and the spatial geometry and size of the pipeline structure can be further accurately reconstructed.

[0023] Furthermore, the point cloud data can be stored in time series, and the data can be classified and labeled to facilitate subsequent analysis and query; Provide corresponding visualization interface to display real-time monitoring data, historical monitoring data, etc.; Use filter filtering, denoising, simplification and other data preprocessing methods to ensure data security and integrity, perform encrypted storage, and prevent data loss or leakage; Use tools such as LabelMe and VGG Image Annotator to annotate the dataset at the pixel level and mark the pipeline area; The labeled dataset is used to train the U-Net semantic segmentation model to extract pipeline structures and remove irrelevant background to reduce the computational burden of the system. The platform stores the processed point cloud data of the pipeline structure area as data for subsequent analysis.

[0024] Step S2, determining the outlier points of the point cloud data in the target area and their corresponding outlier data sequences in the current layer; For details, please refer to Figure 2 , the step of determining the outliers of the point cloud data in the target area point cloud data comprises: Step S21, determining the point cloud plane curvature at the target data point in the target area point cloud data; More specifically, the step S21 includes: Determine the normal direction angle difference between the target data point and the adjacent data points in the point cloud data of the target area; The curvature of the point cloud plane at the target data point is determined by using the angle difference of the normal direction.

[0025] The following combination Figure 4 For relevant instructions: Due to the interval arrangement of pipelines, when the laser scanner collects data from a single angle, it may pass through the gaps between pipelines, resulting in point cloud noise from the lower surface of the upper pipeline or the upper surface of the lower pipeline relative to the current layer of pipeline being mixed into the point cloud data, thus affecting the accuracy and integrity of the data; The essence of point cloud noise is that the laser penetrates the gap of the pipe in this layer and is reflected by the lower surface of the upper pipe and the upper surface of the lower pipe. As a result, the normal direction of these point clouds is quite different from that of the point cloud in this layer, and finally manifests as different surface curvatures. For each data point in the target area point cloud data, obtain its normal direction angle ; In the formula, Represents the point cloud data of the target area data points, namely, as the target data points; Representative The set of adjacent data points of a data point, represent The collection data points, Representative The normal direction angle of the data point, Representative The normal direction angle of the data point, Representative The curvature of the point cloud plane at the data point.

[0026] When the normal direction of the target data point is significantly different from that of the adjacent data points, it indicates that there is a large curvature change on the point cloud surface in this area. Such changes may be caused by changes in the pipeline structure (such as bends, etc.), or point cloud noise caused by uneven illumination or reflection on the pipeline surface.

[0027] Step S22, determining the mean distance between the target data point and the adjacent data points in the point cloud data of the target area; Step S23, using the point cloud plane curvature and the distance mean, determine the point cloud data outliers in the target area point cloud data.

[0028] More specifically, the step S23 includes: The noise coefficient of the target data point is calculated using the point cloud plane curvature and distance mean; The noise coefficient is compared with a preset threshold to determine whether the target data point is an outlier point in the point cloud data.

[0029] Furthermore, since the noise of the point cloud layer formed by the upper and lower structures comes from surfaces at different levels, it is quite different from the actual geometric features of the point cloud layer, resulting in the deviation of the direction and position of the point cloud data, that is, the point cloud data outliers.

[0030] Outliers appear as points that are far away from the main data set or the regular data set; Get the distance between the target data point and each adjacent data point in the target area point cloud data , and then calculate the mean distance between the target data point and all adjacent data points , regarded as the outlier parameter of the point cloud data points in the target area; In the formula, Representative The curvature of the point cloud plane at the data point, Representative The outlier parameter of the data point, Representative The noise factor of each data point.

[0031] Based on the above process, the noise coefficient of each data point in the point cloud data of the target area is obtained. , while The values ​​are normalized; Preset thresholds can be set , iteratively judge the threshold value of the point cloud data points in the target area, and The normalized values ​​of the values ​​greater than the threshold are marked as outliers in the point cloud data, otherwise they are not marked. All data points in the point cloud data of the target area are iterated to count all outliers in the point cloud data of the target area.

[0032] In a specific embodiment, the step S2 includes: All point cloud data outliers are chained to obtain a point cloud data outlier set with a chain structure; The distances between the outlier points in the point cloud data outlier point set with a chain structure are obtained to obtain the outlier data sequence of this layer.

[0033] For the point cloud data of the upper and lower surfaces of the pipeline collected by the laser scanner at different angles, due to the differences in the collection environment and angles, the collection errors of the point cloud data of the upper and lower surfaces are different, resulting in mismatching in the fusion process; Get all outliers in the point cloud data of the target area and the Euclidean distance between them; All point cloud outliers are linked in a chain. The specific linking method can be: the target point cloud outlier is linked to the nearest point cloud outlier, and it is iterated until the point cloud outliers in the point cloud data of the target area are connected into a chain structure; Record the distances between the outliers in the link point cloud within the chain structure, thus forming the outlier data sequence of this layer ,in Represents the last point cloud outlier.

[0034] Step S3, determining the adjacent pipeline structure layer of the pipeline structure at this layer and its corresponding adjacent regular data sequence; Specifically, the step S3 includes: Determine the lower surface of the adjacent upper layer pipeline structure of the current layer pipeline structure and the corresponding adjacent lower surface conventional data sequence; Determine the upper surface of the adjacent lower layer pipeline structure of the current layer pipeline structure and the corresponding adjacent upper surface conventional data sequence.

[0035] When performing point cloud data fusion of the upper and lower surfaces of the target area, obtain the outlier data sequence of the current layer corresponding to the upper and lower surfaces of the current layer of pipeline structure, and at the same time obtain the conventional point cloud data of the upper and lower two layers of pipeline structure surfaces adjacent to the current layer, specifically, including the point cloud data of the lower surface of the upper layer of the pipeline structure and its conventional data sequence, and the point cloud data of the upper surface of the lower layer of the pipeline structure and its conventional data sequence, the acquisition method of the conventional data sequence and the above-mentioned outlier data sequence of the current layer The acquisition method is similar, data sequence The outliers are connected based on distance, while the regular data series connects the normal points (that is, non-outliers) based on distance.

[0036] It should be noted that point cloud data can be divided into regular data and outlier data.

[0037] Step S4, using the outlier data sequence of the current layer and the adjacent regular data sequence, determining the fusion error estimation value of the upper and lower surface point cloud data of the target area point cloud data; Specifically, the step S4 includes: Determine a first data difference between an upper surface outlier data sequence and an adjacent upper surface regular data sequence in the outlier data sequence of the current layer; Determine a second data difference between a lower surface outlier data sequence and an adjacent lower surface regular data sequence in the outlier data sequence of the current layer; The first data difference and the second data difference are used to calculate the estimated value of the fusion error of the upper and lower surface point cloud data of the target area point cloud data.

[0038] The above process can be expressed as: In the formula, Represents the target area of ​​this layer, Representative The surface point cloud data of the pipeline area Sequence data (outlier data sequence on the lower surface among outlier data sequences on this layer), Representative The surface point cloud data of the pipeline area Sequence data (outlier data sequence on the upper surface of the outlier data sequence in this layer), Representative The lower surface point cloud data of the upper structure adjacent to the pipeline area Sequence data (conventional data sequence of adjacent lower surfaces), Representative The upper surface point cloud data of the lower structure adjacent to the layer pipeline area Sequence data (sequence of regular data on adjacent upper surfaces), Represents the mean square error calculation expression, Representative The fusion error estimation value of the upper and lower point cloud data in the layer pipeline area.

[0039] It should be noted that the acquisition methods of the above data sequences and the above outlier data sequences at this layer The acquisition method is similar and will not be repeated here. Before calculating the mean square error, a pre-processing step can be performed to truncate the above data sequences to the same length, and then calculate the mean square error of the truncated sequences.

[0040] MSE measures the difference or error between two sets of data points. In point cloud data, it usually measures the error of spatial matching of two point cloud data sequences; the difference between the two sets of data sequences in the denominator is the first data difference, and the difference between the two sets of data sequences in the numerator is the second data difference.

[0041] when The closer the value of is to 1, the smaller the error is when the upper and lower surface point cloud data are fused in the target pipeline area, and the traditional matching method can be used. On the contrary, it indicates that there is a large error when the upper and lower surface point cloud data are fused in the target pipeline area. At this time, the matching scale needs to be further adjusted or corrected to improve the fusion accuracy.

[0042] Step S5, using the fusion error estimation value, adjusting the matching range scale of the upper and lower surface point cloud data fusion; For details, please refer to Figure 3 , the step S5 comprises: Step S51, determining the regional point cloud coverage coefficient of the target area; More specifically, the step S51 includes: Determine a set of all pipeline structure areas adjacent to the target area; Determine the target area point cloud density of the target area and the average of the area point cloud density of all pipeline structure area sets; The regional point cloud coverage coefficient of the target area point cloud data is calculated using the target area point cloud density and the regional point cloud density mean.

[0043] The complex and mutually occluded environment in the underground pipeline gallery will cause varying degrees of data missing when the laser scanner collects the point cloud of the local pipeline structure. It is necessary to count the complete coverage of the regional point cloud data of each area.

[0044] Retrieve point cloud data of all pipeline structure areas adjacent to the target area, that is, a collection of all pipeline structure areas; Since the laser beam cannot completely reach the blocked area of ​​the pipeline structure, the point cloud density in this area is low and the point cloud distribution is sparse; calculate the point cloud density in the target pipeline structure area , to measure the point cloud imaging accuracy of the target area; In the formula, represents the target local pipeline structure area (referred to as the target area), Representative The point cloud density of the region, Represents the set of all pipeline structure areas adjacent to the target area. Representative Area Correspondence The mean point cloud density in the collection area, Representative The point cloud coverage factor of a region.

[0045] If the point cloud density of a certain area is significantly lower than that of the surrounding areas, it indicates that the point cloud data coverage of this area is poor.

[0046] Step S52, using the fusion error estimation value and the regional point cloud coverage coefficient, calculate and obtain the regional point cloud fusion correction scale; Step S53, using the regional point cloud fusion correction scale, adjusting the initial matching range scale of the upper and lower surface point cloud data fusion to obtain a corrected matching range scale.

[0047] Point cloud coverage factor combined with point cloud data of target pipeline area And the error estimate when the upper and lower surface point cloud data are fused , get the regional point cloud fusion correction scale: In the formula, represents the regional point cloud fusion correction scale, Represents the normalization function.

[0048] In the process of traditional pipeline area upper and lower surface point cloud data fusion, the correspondence between the upper and lower surface point cloud data points is usually matched. However, due to different acquisition environments, angles and other factors, the matching between corresponding point cloud data points often deviates; correcting the scale through regional point cloud fusion , adjusting the initial matching range of the upper and lower surface point cloud data points (i.e. expanding the range of the upper surface point cloud data points when matching the lower surface point cloud data points) can improve the accuracy of the fusion result: in, represents the initial matching range scale, Represents the corrected matching range scale.

[0049] After obtaining the corrected matching range scale, the point cloud data can be fused through the ICP (Iterative Closest Point) algorithm; a key parameter in ICP is the search radius, that is, when looking for matching points, the algorithm searches the neighborhood range, and the above matching range scale refers to the search radius. If the search radius is too small, it may lead to incomplete matching because there are not enough point cloud pairs to match, so the matching range can be expanded in a targeted manner. After obtaining more complete and accurate point cloud data for each layer of the pipeline structure, further, a user visualization interface can be provided to facilitate users to make different decisions for different operating conditions of the underground pipeline corridor.

[0050] The registered point cloud data can be converted into a three-dimensional mesh model or other visualization forms through computer graphics algorithms to help users view the structure of the pipeline corridor.

[0051] Common modeling methods include but are not limited to the following: Meshing: Convert point cloud data into a triangular mesh model to form a surface model.

[0052] Volume reconstruction: Use point cloud data to perform 3D modeling of the internal structure of the tunnel and identify pipelines, walls and other facilities.

[0053] The present invention analyzes the collected point cloud data to evaluate the possible errors that may be generated when the point cloud data is fused at different angles in the pipeline area. By identifying and quantifying the systematic errors and random errors caused by factors such as the environment and angle, the present invention proposes a regional point cloud data fusion correction scale. Using this correction scale, the matching range of the upper and lower surface point cloud data points can be adjusted, that is, when matching the upper surface point cloud data points with the lower surface point cloud data points, the matching range is appropriately expanded, thereby improving the accuracy of the fusion result, thereby improving the integrity and accuracy of the visualization imaging of the underground pipe gallery, and reducing the difficulty of underground pipe gallery maintenance and troubleshooting.

[0054] Embodiment 2: The embodiment of the present invention also provides an underground pipe gallery visualization device for smart pipe gallery monitoring. The underground pipe gallery visualization device for smart pipe gallery monitoring can be a data processing device such as a computer or a server, a signal detection and analysis device, or a combination of multiple devices.

[0055] like Figure 5 As shown, Figure 5 It is a structural diagram of the hardware operating environment of the underground tunnel visualization device for smart tunnel monitoring involved in the embodiment of the present invention.

[0056] like Figure 5As shown, the underground corridor visualization device for intelligent corridor monitoring may include: a processor 1001, such as a CPU, a network interface 1004, a user interface 1003, a memory 1005, and a communication bus 1002. Among them, the communication bus 1002 is used to realize the connection and communication between these components. The user interface 1003 may include a display (Display), an input unit such as a control panel, and the optional user interface 1003 may also include a standard wired interface and a wireless interface. The network interface 1004 may optionally include a standard wired interface and a wireless interface (such as a WIFI interface). The memory 1005 may be a high-speed RAM memory or a stable memory (non-volatile memory), such as a disk memory. The memory 1005 may also be a storage device independent of the aforementioned processor 1001. The memory 1005 as a computer storage medium may include an underground corridor visualization program for intelligent corridor monitoring.

[0057] Those skilled in the art will understand that Figure 5 The hardware structure shown in the figure does not constitute a limitation of the device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0058] Continue to refer to Figure 5 , Figure 5 The memory 1005 as a computer-readable storage medium may include an operating device, a user interface module, a network communication module, and an underground corridor visualization program for smart corridor monitoring.

[0059] exist Figure 5 In the embodiment, the network communication module is mainly used to connect to the server and can communicate data with the server; and the processor 1001 can call the underground corridor visualization program for smart corridor monitoring stored in the memory 1005, and execute the steps in the above embodiments.

[0060] Based on the hardware structure of the above-mentioned underground pipeline corridor visualization device for smart pipeline corridor monitoring, it is used to implement various embodiments of the underground pipeline corridor visualization method for smart pipeline corridor monitoring of the present invention.

[0061] In addition, the present invention also provides an underground pipe gallery visualization device for intelligent pipe gallery monitoring, please refer to Figure 6 , the underground pipe gallery visualization device for intelligent pipe gallery monitoring includes: Data platform, IoT platform, tunnel security integrated management cloud platform and user interface module; The underground corridor visualization device of smart corridor monitoring is essentially an integrated technical system. Through a variety of sensor network technologies and data analysis technologies, it converts the internal status information of the corridor, including the point cloud data of the pipeline structure, into visual image data.

[0062] The data platform is responsible for collecting, storing, processing and displaying data from various sensors, devices and monitoring systems; By deploying Internet of Things (IOT) devices, cameras, and laser scanners to form a sensor network, real-time imaging data of pipeline structures at different angles in the pipeline corridor can be collected; The sensor network deploys a laser scanner matrix in each layer of the pipeline structure in the underground pipeline gallery. A single laser scanner can collect point cloud data on the upper and lower surfaces of each layer of the pipeline structure (the camera and laser scanner are deployed in the same way); Store data in time series, and classify and label the data to facilitate subsequent analysis and query; Provide a visual interface to display real-time monitoring data, historical monitoring data, etc.; Use known data preprocessing methods such as filtering, denoising, and simplification to ensure data security and integrity, and perform encrypted storage to prevent data loss or leakage; Among them, the Internet of Things (IoT) platform is responsible for connecting, managing, and monitoring all devices, and transmitting and controlling data through the network; Ensure that all types of data on the data platform are stably transmitted to the tunnel safety integrated management cloud platform through wired (such as Ethernet, optical fiber, etc.) or wireless (5G, Wi-Fi, etc.) networks, and support data aggregation of large-scale equipment; Support sensor and device access, handle communication protocol differences between different devices, and achieve data interconnection and interoperability across devices; Among them, the tunnel safety comprehensive management cloud platform is the core component of the entire visualization device. It is mainly responsible for processing and analyzing the point cloud data of various areas of the underground tunnel, and providing data support for the subsequent visualization modeling of the underground tunnel structure.

[0063] The comprehensive management platform integrates multiple data processing modules, including point cloud coverage detection, error estimation and point cloud fusion modules, which are used to: detect the missing and occlusion of regional point cloud data; evaluate the errors in the point cloud acquisition process; achieve accurate registration and fusion of point cloud data in different directions in the same area; and through the collaborative work of these modules, ensure high-precision three-dimensional visualization of the corridor structure.

[0064] Specifically, the core purpose of the point cloud coverage detection module is to identify areas with missing, occluded or incomplete data in real time by analyzing regional point cloud data to ensure the integrity and accuracy of the point cloud data.

[0065] The error estimation module analyzes the collected point cloud data, evaluates the possible errors in the fusion process of point cloud data at different angles in the pipeline area, and identifies and quantifies the systematic errors and random errors caused by factors such as environment and angle.

[0066] The core goal of the point cloud fusion module is to achieve accurate registration and fusion of point cloud data collected in different directions or from different perspectives in the same area.

[0067] In addition, the user interface extracts important operating data during the operation of the underground utility corridor and provides a user visualization interface to facilitate users to make different decisions based on the different operating conditions of the underground utility corridor.

[0068] The underground utility gallery visualization device may also include: data storage, big data analysis, communication interface, risk warning system, linkage warning system, emergency response system and other functional or physical modules.

[0069] The specific implementation methods of the underground pipe gallery visualization device for smart pipe gallery monitoring of the present invention are basically the same as the above-mentioned embodiments of the underground pipe gallery visualization method for smart pipe gallery monitoring, and will not be repeated here.

[0070] In addition, the present invention also provides a computer-readable storage medium. The computer-readable storage medium of the present invention stores an underground pipe gallery visualization program for smart pipe gallery monitoring, wherein when the underground pipe gallery visualization program for smart pipe gallery monitoring is executed by a processor, the steps of the underground pipe gallery visualization method for smart pipe gallery monitoring as described above are implemented.

[0071] Among them, the method implemented when the underground pipeline corridor visualization program for smart pipeline corridor monitoring is executed can refer to the various embodiments of the underground pipeline corridor visualization method for smart pipeline corridor monitoring of the present invention, and will not be repeated here.

[0072] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0073] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0074] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, devices, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0075] The above description is only a preferred embodiment of the present invention, and does not limit the protection scope of the present invention. All equivalent structural / method transformations made by using the contents of the present invention specification and drawings under the inventive concept of the present invention, or direct / indirect application in other related technical fields are included in the protection scope of the present invention.

Claims

1. A method for visualizing an underground pipe gallery for intelligent pipe gallery monitoring, characterized in that: The method comprises: Determine the target area point cloud data of the pipeline structure on this layer in the underground pipeline gallery; Determine the outlier points of the point cloud data in the target area and their corresponding outlier data sequences in the current layer; Determine the adjacent pipeline structure layer of the pipeline structure at this layer and its corresponding adjacent conventional data sequence; Using the outlier data sequence of this layer and the adjacent regular data sequence, the fusion error estimation value of the upper and lower surface point cloud data of the target area point cloud data is determined; Using the fusion error estimate, adjust the matching range scale of the upper and lower surface point cloud data fusion; Among them, the point cloud data of the target area is obtained based on laser scanning.

2. The underground pipe gallery visualization method for intelligent pipe gallery monitoring according to claim 1 is characterized in that: The steps of determining outliers in the point cloud data of the target area include: Determine the curvature of the point cloud plane at the target data point in the point cloud data of the target area; Determine the mean distance between the target data point and the adjacent data points in the point cloud data of the target area; The point cloud plane curvature and the mean distance are used to determine the outliers in the point cloud data of the target area.

3. The underground pipe gallery visualization method for intelligent pipe gallery monitoring according to claim 2 is characterized in that: The step of determining the curvature of the point cloud plane at the target data point in the point cloud data of the target area includes: Determine the normal direction angle difference between the target data point and the adjacent data points in the point cloud data of the target area; The curvature of the point cloud plane at the target data point is determined by using the angle difference of the normal direction.

4. The underground pipe gallery visualization method for intelligent pipe gallery monitoring according to claim 2 is characterized in that: The steps of determining the outliers of the point cloud data in the point cloud data of the target area by using the point cloud plane curvature and the distance mean include: The noise coefficient of the target data point is calculated using the point cloud plane curvature and distance mean; The noise coefficient is compared with a preset threshold to determine whether the target data point is an outlier point in the point cloud data.

5. The underground pipe gallery visualization method for intelligent pipe gallery monitoring according to claim 1 is characterized in that: The step of determining the outlier points of the point cloud data in the target area and the corresponding outlier data sequence of the current layer includes: All point cloud data outliers are chained to obtain a point cloud data outlier set with a chain structure; The distances between the outlier points in the point cloud data outlier point set with a chain structure are obtained to obtain the outlier data sequence of this layer.

6. The underground pipe gallery visualization method for intelligent pipe gallery monitoring according to claim 1 is characterized in that: The step of determining the adjacent pipeline structure layer of the pipeline structure at the current layer and the corresponding adjacent conventional data sequence comprises: Determine the lower surface of the adjacent upper layer pipeline structure of the current layer pipeline structure and the corresponding adjacent lower surface conventional data sequence; Determine the upper surface of the adjacent lower layer pipeline structure of the current layer pipeline structure and the corresponding adjacent upper surface conventional data sequence.

7. The underground pipe gallery visualization method for intelligent pipe gallery monitoring according to claim 6 is characterized in that: The step of determining the fusion error estimation value of the upper and lower surface point cloud data of the target area point cloud data by using the outlier data sequence of the current layer and the adjacent regular data sequence comprises: Determine a first data difference between an upper surface outlier data sequence and an adjacent upper surface regular data sequence in the outlier data sequence of the current layer; Determine a second data difference between a lower surface outlier data sequence and an adjacent lower surface regular data sequence in the outlier data sequence of the current layer; The first data difference and the second data difference are used to calculate the estimated value of the fusion error of the upper and lower surface point cloud data of the target area point cloud data.

8. The underground pipe gallery visualization method for intelligent pipe gallery monitoring according to claim 1 is characterized in that: The steps of adjusting the matching range scale of the upper and lower surface point cloud data fusion using the fusion error estimate include: Determine the regional point cloud coverage factor of the target area; The regional point cloud fusion correction scale is calculated using the fusion error estimate and the regional point cloud coverage coefficient. The regional point cloud fusion correction scale is used to adjust the initial matching range scale of the upper and lower surface point cloud data fusion to obtain the corrected matching range scale.

9. The underground pipe gallery visualization method for intelligent pipe gallery monitoring according to claim 8 is characterized in that: The steps of determining the area point cloud coverage factor of the target area include: Determine a set of all pipeline structure areas adjacent to the target area; Determine the target area point cloud density of the target area and the average of the area point cloud density of all pipeline structure areas; The regional point cloud coverage coefficient of the target area point cloud data is calculated using the target area point cloud density and the regional point cloud density mean.

10. An underground pipe gallery visualization device for smart pipe gallery monitoring, characterized in that: The device is used to implement the underground pipe gallery visualization method for smart pipe gallery monitoring according to any one of claims 1 to 9; the device includes: Data platform, IoT platform, tunnel security integrated management cloud platform and user interface module; Among them, the tunnel safety integrated management platform is used for: Determine the target area point cloud data of the pipeline structure on this layer in the underground pipeline gallery; Determine the outlier points of the point cloud data in the target area and their corresponding outlier data sequences in the current layer; Determine the adjacent pipeline structure layer of the pipeline structure at this layer and its corresponding adjacent conventional data sequence; Using the outlier data sequence of this layer and the adjacent regular data sequence, the fusion error estimation value of the upper and lower surface point cloud data of the target area point cloud data is determined; The fusion error estimate is used to adjust the matching range scale of the upper and lower surface point cloud data fusion.

Images