Subway tunnel structure safety prediction method and system

Abstract

The invention relates to a subway tunnel structure safety prediction method and system. The method comprises the following steps: correcting laser point cloud data to obtain corrected laser point cloud data; collecting image data on the subway tunnel; extracting feature points on the image data; registering the feature points on the image data with the laser points on the corrected laser point cloud data to obtain registered laser point cloud data; and when the value of the registered laser point cloud data is not in a preset range, giving an alarm. Through real-time acquisition and processing of the laser point cloud and the image data, the structure change of the tunnel can be quickly identified and analyzed, and potential safety hazards can be found in time.

Description

Technical Field

[0001] The present invention relates to the technical field of tunnel safety early warning, and in particular to a subway tunnel structure safety prediction method and system. Background Art

[0002] With the acceleration of urbanization, subways have been widely used around the world as an efficient and environmentally friendly public transportation method. Subway tunnels are one of the core structures of the subway system, and their safety and stability are directly related to the safety of subway operations and the safety of passengers' lives and property. Therefore, ensuring the safety of subway tunnel structures is an important issue in the current construction and operation of urban rail transit.

[0003] At present, the structural safety monitoring of subway tunnels mainly relies on manual inspection, which makes it difficult to comprehensively and timely identify and predict the potential dangers of subway tunnels. Summary of the invention

[0004] To solve the above problems, an object of the embodiments of the present invention is to provide a method and system for predicting the safety of subway tunnel structures.

[0005] A subway tunnel structure safety prediction method, comprising: Step 1: Collect laser point cloud data on the subway tunnel; Step 2: Correcting the laser point cloud data to obtain corrected laser point cloud data; Step 3: Collect image data on the subway tunnel; Step 4: Extract feature points from the image data; Step 5: Align the feature points on the image data with the laser points on the corrected laser point cloud data to obtain the aligned laser point cloud data; Step 6: When the value of the registered laser point cloud data is not within the preset range, an alarm is issued.

[0006] Preferably, the step 2: performing correction processing on the laser point cloud data to obtain corrected laser point cloud data comprises: Step 2.1: Obtain the reflection intensity of each laser point cloud data; Step 2.2: Using a preset reflection intensity threshold, the laser point cloud data is divided into a target group and a non-target group; Step 2.3: Calculate the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities; Step 2.4: Construct an objective function based on the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities; Step 2.5: Solve the objective function, and use the reflection intensity threshold corresponding to the solution of the objective function as the optimal threshold; Step 2.6: Using the optimal threshold, the laser point cloud data is reclassified into a new target group and a new non-target group; Step 2.7: Extract the laser point cloud data of the new target group as the corrected laser point cloud data.

[0007] Preferably, in step 2.3, the probability calculation formula for the appearance of laser point cloud data under different reflection intensities is:

[0008] in, k Indicates the preset reflection intensity threshold, represents the number of laser points with reflection intensity i, Represents the total number of laser points in the laser point cloud data, Represents the probability of laser point cloud data appearing under different reflection intensities in the target group, represents the probability of laser point cloud data appearing under different reflection intensities in the non-target group, Indicates the total number of different reflection intensities; The means of the target group and the non-target group are:

[0009] in, represents the mean of the target group, represents the mean of the non-target group.

[0010] Preferably, the step 2.4: constructing an objective function based on the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities, comprises: Using the formula:

[0011] in, represents the objective function, Represents the average reflection intensity of all laser point cloud data.

[0012] Preferably, the step 4: extracting feature points from the image data includes: Step 4.1: Calculate a square feature window centered at any point on the image data; Step 4.2: Calculate the feature values ​​in the x-direction and y-direction on the feature window; Step 4.3: Construct a feature evaluation model based on the feature values; Step 4.4: Calculate the screening value of the pixel using the feature evaluation model; Step 4.5: Pixel points whose screening values ​​are greater than the preset value are taken as feature points and extracted.

[0013] Preferably, the step 4.2: calculating the characteristic values ​​in the x-direction and the y-direction on the characteristic window includes: Using the formula:

[0014] Calculate the feature values ​​in the x and y directions on the feature window; where, Represents pixel The eigenvalue in the x direction, Represents pixel The eigenvalue in the y direction, represents the Gaussian scale parameter.

[0015] Preferably, in step 4.3, it includes: Using the formula:

[0016] Construct a feature evaluation model; where Represents pixel The feature evaluation value of .

[0017] The present invention also provides a subway tunnel structure safety prediction system, comprising: Point cloud data acquisition module, used to collect laser point cloud data on subway tunnels; A laser point cloud correction module, used for performing correction processing on the laser point cloud data to obtain corrected laser point cloud data; An image data acquisition module, used to acquire image data on subway tunnels; A feature point extraction module is used to extract feature points on image data; A registration module, used for registering feature points on the image data with laser points on the corrected laser point cloud data to obtain registered laser point cloud data; The early warning module is used to issue an alarm when the value of the registered laser point cloud data is not within a preset range.

[0018] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, and wherein the computer program, when executed by the processor, implements the steps in the above-mentioned method for predicting the safety of a subway tunnel structure.

[0019] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for predicting the safety of a subway tunnel structure are implemented.

[0020] According to the specific embodiments provided by the present invention, the present invention discloses the following technical effects: The present invention relates to a subway tunnel structure safety prediction method. Compared with the prior art, the present invention can quickly identify and analyze the structural changes of the tunnel and timely discover potential safety hazards through real-time collection and processing of laser point cloud and image data.

[0021] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0023] Figure 1 A flow chart of a subway tunnel structure safety prediction method provided by the present invention; Figure 2 A schematic diagram of a subway tunnel structure safety prediction system provided by the present invention. DETAILED DESCRIPTION

[0024] In the description of the present invention, it should be understood that the terms "center", "longitudinal", "lateral", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside", "clockwise", "counterclockwise" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as limiting the present invention.

[0025] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0026] In the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be an indirect connection through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0027] See also Figure 1 , a subway tunnel structure safety prediction method, comprising: Step 1: Collect laser point cloud data on the subway tunnel; Step 2: Correcting the laser point cloud data to obtain corrected laser point cloud data; Furthermore, step 2 includes: Step 2.1: Obtain the reflection intensity of each laser point cloud data; Step 2.2: Using a preset reflection intensity threshold, the laser point cloud data is divided into a target group and a non-target group; Step 2.3: Calculate the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities; In step 2.3, the probability calculation formula for the appearance of laser point cloud data under different reflection intensities is:

[0028] in, k Indicates the preset reflection intensity threshold, represents the number of laser points with reflection intensity i, Represents the total number of laser points in the laser point cloud data, Represents the probability of laser point cloud data appearing under different reflection intensities in the target group, represents the probability of laser point cloud data appearing under different reflection intensities in the non-target group, Indicates the total number of different reflection intensities; The means of the target group and the non-target group are:

[0029] in, represents the mean of the target group, represents the mean of the non-target group.

[0030] Step 2.4: Construct an objective function based on the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities; In step 2.4, an objective function is constructed based on the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities, including: Using the formula:

[0031] in, represents the objective function, Represents the average reflection intensity of all laser point cloud data.

[0032] Step 2.5: Solve the objective function, and use the reflection intensity threshold corresponding to the solution of the objective function as the optimal threshold; Step 2.6: Using the optimal threshold, the laser point cloud data is reclassified into a new target group and a new non-target group; Step 2.7: Extract the laser point cloud data of the new target group as the corrected laser point cloud data.

[0033] Step 3: Collect image data on the subway tunnel; Step 4: Extract feature points from the image data; Furthermore, step 4 includes: Step 4.1: Calculate a square feature window centered at any point on the image data; Step 4.2: Calculate the feature values ​​in the x-direction and y-direction on the feature window; Among them, step 4.2 includes: Using the formula:

[0034] Calculate the feature values ​​in the x and y directions on the feature window; where, Represents pixel The eigenvalue in the x direction, Represents pixel The eigenvalue in the y direction, represents the Gaussian scale parameter.

[0035] Step 4.3: Construct a feature evaluation model based on the feature values; In step 4.3, the formula is used:

[0036] Construct a feature evaluation model; where Represents pixel The feature evaluation value of .

[0037] Step 4.4: Calculate the screening value of the pixel using the feature evaluation model; Step 4.5: Pixel points whose screening values ​​are greater than the preset value are taken as feature points and extracted.

[0038] Step 5: Align the feature points on the image data with the laser points on the corrected laser point cloud data to obtain the aligned laser point cloud data; Step 6: When the value of the registered laser point cloud data is not within the preset range, an alarm is issued.

[0039] The present invention can quickly identify and analyze the structural changes of the tunnel and discover potential safety hazards in a timely manner through real-time collection and processing of laser point cloud and image data.

[0040] The present invention also provides a subway tunnel structure safety prediction system, comprising: Point cloud data acquisition module, used to collect laser point cloud data on subway tunnels; A laser point cloud correction module, used for performing correction processing on the laser point cloud data to obtain corrected laser point cloud data; An image data acquisition module, used to acquire image data on subway tunnels; A feature point extraction module is used to extract feature points on image data; A registration module, used for registering feature points on the image data with laser points on the corrected laser point cloud data to obtain registered laser point cloud data; The early warning module is used to issue an alarm when the value of the registered laser point cloud data is not within a preset range.

[0041] The present invention also provides an electronic device, comprising a bus, a transceiver, a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory and the processor are connected via the bus, and is characterized in that when the computer program is executed by the processor, the steps in the above-mentioned method for predicting the safety of a subway tunnel structure are implemented. Compared with the prior art, the beneficial effects of the electronic device provided by the present invention are the same as the beneficial effects of the method for predicting the safety of a subway tunnel structure described in the above-mentioned technical solution, and are not elaborated herein.

[0042] The present invention also provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, the steps in the above-mentioned method for predicting the safety of a subway tunnel structure are implemented. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided by the present invention are the same as the beneficial effects of the method for predicting the safety of a subway tunnel structure described in the above-mentioned technical solution, which will not be repeated here.

[0043] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any technical solution that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.

Claims

1. A method for predicting the safety of subway tunnel structures, characterized in that: include: Step 1: Collect laser point cloud data on the subway tunnel; Step 2: Correcting the laser point cloud data to obtain corrected laser point cloud data; Step 3: Collect image data on the subway tunnel; Step 4: Extract feature points from the image data; Step 5: Align the feature points on the image data with the laser points on the corrected laser point cloud data to obtain the aligned laser point cloud data; Step 6: When the value of the registered laser point cloud data is not within the preset range, an alarm is issued.

2. A subway tunnel structure safety prediction method according to claim 1, characterized in that: The step 2: performing correction processing on the laser point cloud data to obtain corrected laser point cloud data, comprises: Step 2.1: Obtain the reflection intensity of each laser point cloud data; Step 2.2: Using a preset reflection intensity threshold, the laser point cloud data is divided into a target group and a non-target group; Step 2.3: Calculate the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities; Step 2.4: Construct an objective function based on the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities; Step 2.5: Solve the objective function, and use the reflection intensity threshold corresponding to the solution of the objective function as the optimal threshold; Step 2.6: Using the optimal threshold, the laser point cloud data is reclassified into a new target group and a new non-target group; Step 2.7: Extract the laser point cloud data of the new target group as the corrected laser point cloud data.

3. A subway tunnel structure safety prediction method according to claim 2, characterized in that: In step 2.3, the probability calculation formula for the appearance of laser point cloud data under different reflection intensities is: ； in, k Indicates the preset reflection intensity threshold, represents the number of laser points with reflection intensity i, Represents the total number of laser points in the laser point cloud data, Represents the probability of laser point cloud data appearing under different reflection intensities in the target group, represents the probability of laser point cloud data appearing under different reflection intensities in the non-target group, Indicates the total number of different reflection intensities; The means of the target group and the non-target group are: ； in, represents the mean of the target group, represents the mean of the non-target group.

4. A subway tunnel structure safety prediction method according to claim 3, characterized in that: The step 2.4: constructing an objective function based on the mean of the target group and the non-target group and the probability of occurrence of laser point cloud data under different reflection intensities, including: Using the formula: ； in, represents the objective function, Represents the average reflection intensity of all laser point cloud data.

5. A subway tunnel structure safety prediction method according to claim 4, characterized in that: The step 4: extracting feature points from the image data includes: Step 4.1: Calculate a square feature window centered at any point on the image data; Step 4.2: Calculate the feature values ​​in the x-direction and y-direction on the feature window; Step 4.3: Construct a feature evaluation model based on the feature values; Step 4.4: Calculate the screening value of the pixel using the feature evaluation model; Step 4.5: Pixel points whose screening values ​​are greater than the preset value are taken as feature points and extracted.

6. A subway tunnel structure safety prediction method according to claim 5, characterized in that: The step 4.2: calculating the feature values ​​in the x-direction and the y-direction on the feature window includes: Using the formula: ； Calculate the feature values ​​in the x and y directions on the feature window; where, Represents pixel The eigenvalue in the x direction, Represents pixel The eigenvalue in the y direction, represents the Gaussian scale parameter.

7. A subway tunnel structure safety prediction method according to claim 6, characterized in that: In step 4.3, it includes: Using the formula: ； Construct a feature evaluation model; where Represents pixel The feature evaluation value of .

8. A subway tunnel structure safety prediction system, characterized in that: include: Point cloud data acquisition module, used to collect laser point cloud data on subway tunnels; A laser point cloud correction module, used for performing correction processing on the laser point cloud data to obtain corrected laser point cloud data; An image data acquisition module, used to acquire image data on subway tunnels; A feature point extraction module is used to extract feature points on image data; A registration module, used for registering feature points on the image data with laser points on the corrected laser point cloud data to obtain registered laser point cloud data; The early warning module is used to issue an alarm when the value of the registered laser point cloud data is not within a preset range.

9. An electronic device, comprising a bus, a transceiver, a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the transceiver, the memory, and the processor are connected via the bus, wherein: When the computer program is executed by the processor, the steps in the subway tunnel structure safety prediction method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps in a subway tunnel structure safety prediction method as described in any one of claims 1-7 are implemented.

Images