Method and device for identifying abnormal deformation of mine tunnel in coal mine

Abstract

The application discloses a kind of coal mine passageway abnormal deformation identification method and device.Method includes: obtaining current video data collected in each camera device in current monitoring period mine passageway;The field of view range of each camera device does not coincide and covers the preset range of passageway;From current video data, extract the current point cloud data of passageway wall in preset range, and point cloud data is the feature point set of mine passageway wall;From current point cloud, determine the target point cloud at the position to be monitored, and based on the spatial coordinates of target point cloud, according to the mapping relationship between the array, start matrix and termination matrix pre-constructed, extract the theoretical sub-point cloud corresponding to target point cloud from array;Array is used to store the theoretical overall point cloud of passageway wall in preset range, and the subscript of each matrix is one-to-one corresponding with the coordinates of point in point cloud;Based on the distance between target point cloud and theoretical sub-point cloud, determine the passageway deformation result of the position where target point cloud is located.This application can quickly determine the deformation of any position in mine passageway.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of mine detection, in particular to a method and device for identifying abnormal deformation of a coal mine passageway. BACKGROUND

[0002] Coal mines are an important raw material for industrial production and are crucial to industrial development. In recent years, as the scale of coal mining has increased, safety accidents in mines have also occurred from time to time, causing great hidden dangers to mining and personnel safety. When monitoring the deformation of a mine passageway, the related technology usually uses a laser ranging method, but this method is inefficient and cannot monitor the deformation state of the mine passageway in real time.

[0003] Therefore, there is an urgent need for a method and device for identifying abnormal deformation of a coal mine passageway to solve the above problems. SUMMARY

[0004] The present application provides a method and device for identifying abnormal deformation of a coal mine passageway, which can quickly determine the deformation at any position in the mine passageway in real time. The technical solution is as follows:

[0005] In a first aspect, the present application provides a method for identifying abnormal deformation of a coal mine passageway, which comprises:

[0006] Obtaining current video data collected by each camera device in the mine passageway in the current monitoring period; the field of view of each camera device does not overlap and covers a preset range of the passageway;

[0007] Extracting current point cloud data of the passageway wall surface in the preset range from the current video data, the point cloud data being a set of feature points of the mine passageway wall surface;

[0008] Determining a target point cloud at a to-be-monitored position from the current point cloud, and based on the spatial coordinates of the target point cloud, extracting a theoretical sub-point cloud corresponding to the target point cloud from an array according to a mapping relationship between the array, a start matrix, and an end matrix; the array is used to store a theoretical overall point cloud of the passageway wall surface in the preset range, and the subscripts of each matrix correspond one-to-one to the coordinates of a point in the point cloud;

[0009] Determining the deformation result of the passageway at the position of the target point cloud based on the distance between the target point cloud and the theoretical sub-point cloud.

[0010] In a second aspect, the present application also provides a device for identifying abnormal deformation of a coal mine passageway, which comprises:

[0011] An acquisition unit is configured to acquire current video data collected by each camera device in a current monitoring period in a mine tunnel, wherein the field of view of each camera device does not overlap and covers a preset range of the tunnel.

[0012] A first extraction unit is configured to extract current point cloud data of a tunnel wall surface in the preset range from the current video data, wherein the point cloud data is a set of feature points of the tunnel wall surface.

[0013] A second extraction unit is configured to determine a target point cloud at a to-be-monitored position from the current point cloud, and extract a theoretical sub-point cloud corresponding to the target point cloud from an array based on a mapping relationship between the target point cloud and the array, a start matrix and an end matrix, wherein the array is configured to store a theoretical overall point cloud of the tunnel wall surface in the preset range, and the subscripts of each matrix correspond to the coordinates of points in the point cloud one by one.

[0014] A determination unit is configured to determine a tunnel deformation result of the position of the target point cloud based on a distance between the target point cloud and the theoretical sub-point cloud.

[0015] In a third aspect, an electronic device is provided, including a memory and a processor, the memory stores a computer program, and the processor executes the computer program to implement the method in any of the embodiments of the present specification.

[0016] In a fourth aspect, a computer readable storage medium is provided, which stores a computer program, and the computer program, when executed in a computer, causes the computer to execute the method in any of the embodiments of the present specification.

[0017] In a fifth aspect, a computer program product is provided, which includes a computer program, and the computer program, when executed by a processor, implements the steps of the method described above.

[0018] The embodiment of the present application provides a kind of coal mine passageway abnormal deformation identification method and device.The multiple camera devices can be installed in the mine passageway, and the video data in the mine passageway can be collected in real time by the camera device, including normal state video data and monitoring data at any time.The theoretical overall point cloud is extracted from the video data in normal state, and the theoretical overall point cloud is used as the standard to determine whether the passageway is deformed.Because the theoretical overall point cloud has been stored in the array in advance, and there is a mapping relationship between the array, matrix and the spatial coordinates of the point, the adjacent local point cloud of the point can be quickly searched according to the spatial coordinates of the point.Finally, when the monitoring position is determined, the distance between the target point cloud and the theoretical sub-point cloud at the position is determined, and the passageway at the position is determined according to the calculation result.The method of the present application can obtain the video data in the mine passageway in real time, and quickly identify the deformation in the mine passageway based on the obtained video data, with high identification efficiency.The abnormal deformation in the mine passageway is quickly identified, so that risk warning is realized, and personnel casualty and property loss are avoided. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or prior art description. Obviously, the drawings in the following description are some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0020] Figure 1 It is a kind of coal mine passageway abnormal deformation identification method flow chart provided by an embodiment of the present application;

[0021] Figure 2 It is a kind of coal mine passageway abnormal deformation identification device structure diagram provided by an embodiment of the present application;

[0022] Figure 3 It is a kind of hardware architecture diagram of computer equipment provided by an embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the purpose, technical scheme and advantages of the embodiments of the present application more clear, the technical scheme in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor belong to the scope of protection of the present application.

[0024] The specific implementation of the above concept will be described below.

[0025] Please refer toFigure 1 The embodiment of the present application provides a kind of coal mine passageway abnormal deformation identification method, which comprises:

[0026] Step 100, obtain the current video data collected by each camera device in the current monitoring period in mine passageway;The field of view range of each camera device does not coincide and covers the preset range of passageway;

[0027] Step 102, extract the current point cloud data of passageway wall surface in preset range from current video data, and point cloud data is the feature point set of mine passageway wall surface;

[0028] Step 104, determine the target point cloud at the position to be monitored from current point cloud, and based on the spatial coordinates of target point cloud, according to the mapping relationship between the array, start matrix and termination matrix pre-constructed, extract the theoretical sub-point cloud corresponding to target point cloud from array;Array is used to store the theoretical overall point cloud of passageway wall surface in preset range, and the subscript of each matrix is one-to-one corresponding to the coordinates of point in point cloud;

[0029] Step 106, based on the distance between target point cloud and theoretical sub-point cloud, determine the deformation result of the position of target point cloud in passageway.

[0030] In the embodiment, by installing multiple camera devices in mine passageway, video data in mine passageway can be collected in real time by camera device, including normal state video data and monitoring data at any time. The theoretical overall point cloud is extracted from the video data in normal state, and the theoretical overall point cloud is used as the standard to determine whether the passageway is deformed. Since the theoretical overall point cloud has been pre-stored in array, and there is a mapping relationship between array, matrix and point spatial coordinates, the adjacent local point cloud of point can be quickly searched according to the spatial coordinates of point. Finally, when the position to be monitored is determined, only the distance between target point cloud and theoretical sub-point cloud at the position needs to be determined, and whether the passageway at the position is deformed can be determined according to the calculation result. The method of the present application can obtain video data in mine passageway in real time, and quickly identify the deformation in mine passageway based on the obtained video data, with high identification efficiency.

[0031] In addition, when abnormal deformation of mine passageway is identified, risk can be sent to alarm LED screen for display and alarm broadcast is sent, so as to timely remind relevant personnel to handle risk, and avoid personnel casualty and property loss.

[0032] The execution mode of each step is described below Figure 1

[0033] Firstly, for step 100, obtain the current video data collected by each camera device in the current monitoring period in mine passageway.

[0034] ​In this step, each camera is arranged at intervals and installed at key points in the passageway, and the field of view of each camera does not overlap and covers the preset range of the passageway. Each camera uses a camera with no less than 400W pixels, and each camera is used to collect video signals in the mine passageway.

[0035] In step 102, the current point cloud data of the passageway wall surface in the preset range is extracted from the current video data.

[0036] In this step, the extraction of point cloud data from the video is a common means in the field of feature extraction, which will not be repeated here. The point cloud data is a set of feature points of the mine passageway wall surface, and the feature points are points with a gray value or texture characteristics higher than a preset value. The preset value is determined according to user requirements, which is not limited in this application.

[0037] In step 104, the target point cloud at the monitoring position is determined from the current point cloud, and based on the spatial coordinates of the target point cloud, the theoretical sub-point cloud corresponding to the target point cloud is extracted from the array according to the mapping relationship between the array, the start matrix and the end matrix.

[0038] In this step, the theoretical overall point cloud is obtained by collecting video data in the preset range of the mine passageway using a camera under normal conditions in the coal mine passageway, and extracting feature points from the video data. The theoretical overall point cloud is used to represent the normal state of the mine passageway wall surface. In this normal state, the mine passageway will not collapse and other risks, and safe production can be carried out.

[0039] In some embodiments, the dimensions of the start matrix and the end matrix are determined based on the boundary of the overall point cloud of the passageway wall surface in the preset range and the size of the preset grid, and the calculation formula is as follows:

[0040]

[0041] In the formula, A x , A y and A z are the dimensions of the matrix in the x, y and z directions respectively; x max , x min , y max , y min , z max and z min are the maximum boundary coordinates and the minimum boundary coordinates of the overall point cloud in the x, y and z directions respectively; w x , w x and w x are the sizes of the grid in the x, y and z directions respectively; represents rounding up.

[0042] In some embodiments, the mapping relationship between the array and each matrix is determined as follows:

[0043] S1, the position coordinates of each point in the theoretical overall point cloud corresponding to the grid in the entire space grid are calculated, and the position code of the grid is calculated based on the position coordinates of the grid.

[0044] In this step, the position code of the grid is calculated by the following formula:

[0045] p = x' + A x (y' + z' A y )

[0046] In the formula, p represents the position code of the grid; (x, y, z) represents the spatial coordinates of the point in the point cloud, and (x', y', z') is the position coordinates of the grid corresponding to the point (x, y, z), wherein, represents the floor function.

[0047] S2, the encoding of each point in the theoretical overall point cloud and the position code of the grid corresponding thereto are taken as a data pair, and each data pair is stored in the array in the order of the position code from large to small, each data pair corresponding to an array subscript.

[0048] In this step, the overall point cloud includes a plurality of points, each point having an encoding, which is used to represent the number of points in the point cloud. When the point cloud is determined, the encoding of each point in the point cloud and its spatial coordinates are also determined. Assuming that the encoding of a point is d, the data pair can be represented as (d, p). According to the value of p, they are stored in the array in order. For example, assuming that the encoding of a point is 231, and the position code of the grid corresponding thereto is 12, the data pair is represented as (231, 12). Let (231, 12) be stored in the position of the 10th element of the array, then it is indicated that the data pair (231, 12) corresponds to the array subscript 10, that is, the 10th element in the array is (231, 12). By analogy, the corresponding relationship between each data pair and the array subscript can be obtained.

[0049] S3, the starting matrix subscript and the terminal matrix subscript corresponding to each position code in each data pair are calculated by traversing the array.

[0050] In this step, after each data pair is stored in the array, the corresponding relationship between each data pair and the array subscript, that is, the corresponding relationship between the grid position code in the data pair and the array subscript, can be determined.

[0051] S4, when the number of same position encodings is multiple, record the start subscript and the end subscript of the position encoding in the array; otherwise, take the array subscript corresponding to the position encoding as both the start subscript and the end subscript; store the start subscript of the position encoding in the array at the element position corresponding to the start matrix subscript, and store the end subscript of the position encoding in the array at the element position corresponding to the end matrix subscript.

[0052] In this step, there can be multiple p's, since each p corresponds to an array subscript, the subscript of the first p is stored as the start subscript of the p, and the subscript of the last p is stored as the end subscript of the p. When there is only one p, the array subscript corresponding to the p is taken as both the start subscript and the end subscript. Then, the mapping relationship between the array and each matrix is represented by the following formula:

[0053] S(m, n) = sz s E(m, n) = sz e

[0054] In the formula, S(m, n) represents the start matrix subscript corresponding to the mth row and the nth column of the matrix; E(m, n) represents the end matrix subscript corresponding to the mth row and the nth column of the matrix; sz s represents the start subscript of the array; sz e represents the end subscript of the array.

[0055] By analogy, the mapping relationship between the array and each matrix is obtained.

[0056] In some embodiments, step 104 is implemented in the following manner:

[0057] Determine the core points in the target point cloud, and for each core point, perform the following steps:

[0058] Calculate the position coordinates of the core grid where the core point is located based on the coordinates of the core point; calculate the start matrix subscript and the end matrix subscript corresponding to the core grid based on the position coordinates of the core grid; determine the start subscript and the end subscript of the array corresponding to the core point based on the start matrix subscript and the end matrix subscript, and take the points of the array between the start subscript and the end subscript as the adjacent point cloud of the core point;

[0059] Take each set of adjacent point clouds as the theoretical sub-point cloud corresponding to the target point cloud.

[0060] In this step, the number of core points is at least one. The position of the core point can be determined according to the geometric position, or can be determined according to the customer's requirements, which is not limited in the present application.

[0061] The starting matrix index and the ending matrix index (m, n) of the core grid are calculated according to the position coordinates of the core grid by the following formula, wherein: m = x', n = y' + z' Ay.

[0062] After (m, n) is determined, the corresponding array starting index sz s and the ending index sz e of the core point are determined according to the mapping relationship, and the point between the data pairs stored in sz s ~ sz e is taken as the adjacent point cloud of the core point.

[0063] Finally, for step 106, the channel deformation result of the position where the target point cloud is located is determined based on the distance between the target point cloud and the theoretical sub-point cloud, including:

[0064] For each detection point in the target point cloud, the following is performed: finding the nearest theoretical point from the theoretical sub-point cloud to the detection point, and calculating the distance between the detection point and the theoretical point;

[0065] For each distance, it is judged whether the distance exceeds the distance threshold, and if it exceeds, the corresponding detection point is marked as an abnormal point;

[0066] The total number of all abnormal points is counted, and if the total number exceeds a set number, it is determined that the channel at the position where the target point cloud is located has abnormal deformation; otherwise, it is determined that the deformation of the channel at the position where the target point cloud is located is within the allowable range.

[0067] In this step, the theoretical point represents the normal state of the mine channel, therefore, the smaller the distance between the detection point and its corresponding theoretical point, the smaller the deformation of the channel. When all distances are less than the distance threshold, it is the best state, indicating that the channel is very safe. When most of the distances are less than the distance threshold, it indicates that there is deformation but does not affect personnel safety and safety production. Otherwise, it represents the risk of collapse.

[0068] In some embodiments, after the channel deformation result of the position where the target point cloud is located is determined, it further includes:

[0069] The deformation result is sent to a pre-set alarm LED screen to display the recognition result by using the LED screen. When the recognition result is that the mine channel has a risk, an alarm broadcast can also be sent to remind relevant personnel to quickly handle the risk to avoid personnel casualties and property losses.

[0070] As shown in Figure 2 , Figure 3 , an embodiment of the present application provides an identification device for abnormal deformation of a coal mine channel. The device embodiment can be realized by software, or realized by hardware or a combination of software and hardware. From the hardware layer, as shown in Figure 2As shown in the figure, a hardware architecture diagram of a computing device where a coal mine tunnel abnormal deformation identification device according to an embodiment of the present application is located, in addition to Figure 2 In addition to the processor, the memory, the network interface, and the non-volatile memory shown, the computing device where the device in the embodiment is usually also can include other hardware, such as a forwarding chip responsible for processing packets, and the like. Taking software implementation as an example, as shown in the figure, as a logically meaningful device, it is formed by the CPU of the computing device where it is located reading the corresponding computer program in the non-volatile memory into the memory and running. Figure 3

[0071] Please refer to Figure 3 The embodiment of the present application provides a coal mine tunnel abnormal deformation identification device, and the device comprises:

[0072] The acquisition unit 300 is configured to acquire current video data collected by each camera device in the current monitoring period in the mine tunnel; the field of view ranges of the camera devices do not coincide and cover a preset range of the tunnel;

[0073] The first extraction unit 302 is configured to extract current point cloud data of the tunnel wall surface in the preset range from the current video data, and the point cloud data is a feature point set of the tunnel wall surface;

[0074] The second extraction unit 304 is configured to determine a target point cloud at a to-be-monitored position from the current point cloud, and based on the spatial coordinates of the target point cloud, according to a mapping relationship between an array, a start matrix and a termination matrix constructed in advance, extract a theoretical sub-point cloud corresponding to the target point cloud from the array; the array is configured to store a theoretical overall point cloud of the tunnel wall surface in the preset range, and the subscripts of each matrix are one-to-one corresponding to the coordinates of the points in the point cloud;

[0075] The determination unit 306 is configured to determine a tunnel deformation result of the position where the target point cloud is located based on the distance between the target point cloud and the theoretical sub-point cloud.

[0076] In some embodiments, each camera device adopts a camera with no less than 400W pixels, and each camera is configured to collect a video signal in the mine tunnel.

[0077] In some embodiments, the theoretical overall point cloud is obtained by collecting video data in the preset range of the mine tunnel under normal circumstances using the camera device and performing feature point extraction on the video data.

[0078] The theoretical overall point cloud is configured to represent the normal state of the tunnel wall surface.

[0079] In some embodiments, the dimensions of each matrix are determined based on the boundary of the overall point cloud of the tunnel wall surface in the preset range and the size of the preset grid, and the calculation formula is as follows:​

[0080]

[0081] wherein A x , A y and A z are the dimensions of the matrix in x, y, z directions respectively; x max , x min , y max , y min , z max and z min are the maximum and minimum boundary coordinates of the whole point cloud in x, y, z directions respectively; w x , w y and w z are the sizes of the grid in x, y, z directions respectively; represents rounding up.

[0082] In some embodiments, the mapping relationship between the array and each matrix is determined as follows:

[0083] calculating the position coordinates of the grid corresponding to each point in the theoretical whole point cloud in the whole space grid, and calculating the position encoding of the grid based on the position coordinates of the grid;

[0084] taking the encoding of each point in the theoretical whole point cloud and the position encoding of the grid corresponding thereto as a data pair, and storing each data pair in the array in the order of decreasing position encoding, each data pair corresponding to an array subscript;

[0085] traversing the array to calculate the starting matrix subscript and the ending matrix subscript corresponding to each position encoding in each data pair;

[0086] when the number of the same position encoding is more than one, recording the starting subscript and the ending subscript of the position encoding in the array; otherwise, taking the array subscript corresponding to the position encoding as both the starting subscript and the ending subscript; storing the starting subscript of the position encoding in the array at the element position corresponding to the starting matrix subscript, and storing the ending subscript of the position encoding in the array at the element position corresponding to the ending matrix subscript;

[0087] by analogy, the mapping relationship between the array and each matrix is obtained.

[0088] In some embodiments, the second extraction unit 304 is configured to perform the following operations:

[0089] determining the core points in the target point cloud, and for each core point, performing the following operations:

[0090] calculating a position coordinate of the core grid where the core point is based on the coordinate of the core point; calculating a start matrix index and a terminal matrix index corresponding to the core grid based on the position coordinate of the core grid; determining a start index and a terminal index of an array corresponding to the core point based on the start matrix index and the terminal matrix index, and taking points of the array between the start index and the terminal index as the neighboring point cloud of the core point;

[0091] taking each set of the neighboring point cloud as a theoretical sub-point cloud corresponding to the target point cloud.

[0092] In some embodiments, the determining unit 306 is configured to perform the following operations:

[0093] For each detection point in the target point cloud, the following operations are performed: finding a theoretical point closest to the detection point from the theoretical sub-point cloud, and calculating a distance between the detection point and the theoretical point;

[0094] For each distance, it is judged whether the distance exceeds a distance threshold, and if so, the corresponding detection point is marked as an abnormal point.

[0095] The total number of all abnormal points is counted, and if the total number exceeds a set number, it is determined that the channel at the position of the target point cloud has an abnormal deformation; otherwise, it is determined that the deformation of the channel at the position of the target point cloud is within an allowable range.

[0096] It should be noted that: the coal mine tunnel abnormal deformation recognition device provided in the above embodiments is only exemplified by the division of the above functional modules, and in actual application, the above functions can be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. In addition, the coal mine tunnel abnormal deformation recognition device and the coal mine tunnel abnormal deformation recognition method provided in the above embodiments belong to the same concept, and the specific implementation process is detailed in the method embodiments, which will not be repeated here.

[0097] Embodiments of the present application also provide a computer device, which refers to Figure 3 The computer device includes a processor and a memory, and the memory stores at least one instruction, at least one program, a code set or an instruction set. The at least one instruction, at least one program, code set or instruction set is loaded and executed by the processor to implement the coal mine tunnel abnormal deformation recognition method provided by the above method embodiments.

[0098] The embodiment of the present application further provides a computer readable storage medium, and at least one instruction, at least one program, a code set or an instruction set are stored on the computer readable storage medium, and the at least one instruction, the at least one program, the code set or the instruction set are loaded and executed by a processor to realize the coal mine tunnel abnormal deformation identification method provided by each method embodiment.

[0099] The embodiment of the present application further provides a computer program product, and the computer program product comprises a computer program, the computer program is read by a processor of a computer device from a computer readable storage medium, and the processor executes the computer program, so that the computer device executes the coal mine tunnel abnormal deformation identification method described in any one of the above embodiments.

[0100] For the convenience of description, the above system or device is described in various modules or units in terms of functions. Of course, in the implementation of the present application, the functions of each unit can be implemented in the same or multiple software and / or hardware.

[0101] From the above description of the embodiments, those skilled in the art can clearly understand that the present application can be implemented by means of software and necessary general hardware platforms. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which can be stored in a storage medium, such as a ROM / RAM, a magnetic disk, an optical disk, etc., and includes a plurality of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute the methods described in each embodiment or some parts of the embodiments of the present application.

[0102] Finally, it should be noted that, in this document, relational terms such as first and second, and third and fourth, are used solely to distinguish one entity or action from another entity or action, without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises", "comprising", or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but can include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without more limitations, an element preceded by "comprises a" does not, without more constraints, foreclose the existence of additional identical elements in the process, method, article, or apparatus that comprises the recited element.

[0103] The above merely describes the preferred embodiments of the present application, and it should be pointed out that, for those skilled in the art, some improvements and refinements can be made without departing from the principles of the present application, and these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method for identifying abnormal deformation of a mine roadway in a coal mine, characterized in that, The method comprises: acquiring current video data collected by each camera device in a current monitoring period in a mine tunnel; the field of view ranges of the camera devices do not overlap and cover a preset range of the tunnel; extracting current point cloud data of a tunnel wall surface in the preset range from the current video data; the point cloud data is a set of feature points of the tunnel wall surface; determining a target point cloud at a to-be-monitored position from the current point cloud, and extracting a theoretical sub-point cloud corresponding to the target point cloud from an array according to a mapping relationship between a start matrix and an end matrix pre-constructed based on spatial coordinates of the target point cloud; the array is used to store a theoretical overall point cloud of the tunnel wall surface in the preset range, and the subscripts of each matrix correspond to the coordinates of points in the point cloud one by one; determining a tunnel deformation result of the position where the target point cloud is located based on the distance between the target point cloud and the theoretical sub-point cloud; the dimensions of each matrix are determined based on the boundary of the overall point cloud of the tunnel wall surface in the preset range and the size of a preset grid, and the calculation formula is as follows: In the formula, , and are the dimensions of the matrix in x , y , z three directions respectively; , , , , and are the maximum and minimum boundary coordinates of the overall point cloud in x , y , z three directions respectively; , and are the sizes of the grid in x , y , z three directions respectively; represents rounding up. the mapping relationship between the array and each matrix is determined by the following method: calculating the position coordinates of the grid corresponding to each point in the theoretical overall point cloud in the entire space grid, and calculating the position encoding of the grid based on the position coordinates of the grid; storing each point in the theoretical overall point cloud and the position encoding of the grid corresponding to the point as a data pair, and storing each data pair in the array in descending order of the position encoding; each data pair corresponds to an array subscript; traversing the array to calculate the start matrix subscript and the end matrix subscript corresponding to each position encoding in each data pair; when the number of the same position encoding is more than one, the start subscript and the end subscript of the position encoding in the array are recorded; otherwise, the array subscript corresponding to the position encoding is used as both the start subscript and the end subscript; the element position corresponding to the start matrix subscript stores the start subscript of the position encoding in the array, and the element position corresponding to the end matrix subscript stores the end subscript of the position encoding in the array; by analogy, the mapping relationship between the array and each matrix is obtained; the position encoding of the grid is calculated by the following formula: where p represents the position encoding of the grid; denotes the spatial coordinates of a point in the point cloud, is a point the position coordinates of the corresponding grid, where, ; ; ; denotes the floor function.

2. The method of claim 1, wherein, each camera device adopts a camera with no less than 400W pixels, and each camera is used to collect a video signal in the mine tunnel.

3. The method of claim 1, wherein, The theoretical overall point cloud is obtained by collecting video data in the preset range of the mine tunnel under normal conditions of the mine tunnel using the camera device and extracting feature points from the video data. The theoretical overall point cloud is used to represent the normal state of the tunnel wall surface.

4. The method of claim 1, wherein, The method comprises: determining core points in the target point cloud, and performing the following operations for each core point: calculating position coordinates of the core grid where the core point is based on the coordinates of the core point; calculating a start matrix index and a termination matrix index corresponding to the core grid based on the position coordinates of the core grid; determining a start index and a termination index of an array corresponding thereto based on the start matrix index and the termination matrix index, and taking points of the array between the start index and the termination index as the neighboring point cloud of the core point; taking each set of the neighboring point cloud as a theoretical sub-point cloud corresponding to the target point cloud.

5. The method of claim 1, wherein, determining a channel deformation result at the position where the target point cloud is based on distances between the target point cloud and the theoretical sub-point cloud, including: for each detection point in the target point cloud, performing: finding a theoretical point closest to the detection point from the theoretical sub-point cloud, and calculating a distance between the detection point and the theoretical point; for each distance, judging whether the distance exceeds a distance threshold, and if so, marking the corresponding detection point as an abnormal point; statistically counting a total number of all abnormal points, and if the total number exceeds a set number, determining that the channel at the position where the target point cloud is has an abnormal deformation; otherwise, determining that the deformation of the channel at the position where the target point cloud is is within an allowable range.

6. A device for identifying abnormal deformation of a mine roadway in a coal mine, characterized in that, The device for implementing the method of any one of claims 1-5 comprises: an acquisition unit configured to acquire current video data collected by each camera device in a current monitoring period in a mine channel; the field of view ranges of the camera devices do not overlap and cover a preset range of the channel; a first extraction unit configured to extract current point cloud data of a channel wall surface in the preset range from the current video data, the point cloud data being a set of feature points of the channel wall surface in the mine; a second extraction unit configured to determine a target point cloud at a to-be-monitored position from the current point cloud, and extract a theoretical sub-point cloud corresponding to the target point cloud from an array based on a mapping relationship between the array, a start matrix, and a termination matrix according to spatial coordinates of the target point cloud; the array is configured to store a theoretical overall point cloud of the channel wall surface in the preset range, and the indices of each matrix correspond to coordinates of points in the point cloud one by one; a determination unit configured to determine a channel deformation result at the position where the target point cloud is based on distances between the target point cloud and the theoretical sub-point cloud.

7. A computing device comprising a memory and a processor, the memory storing a computer program, and the processor implementing the method of any one of claims 1-5 when executing the computer program.

8. A computer-readable storage medium storing a computer program, the computer program causing a computer to execute the method of any one of claims 1-5 when executed in the computer.

Images